Search

The new paradigm of syntactic pattern recognition, SPR, which uses multi-derivational parsing of vague languages is introduced in the paper. The methodology proposed addresses the issue of the recognition of vague/distorted patterns which is one of the important open problems in the area. The concept of the vague language of patterns and the efficient parsing method based on the class of dynamically programmed grammars are introduced. A vague language is defined with vague primitives which are vectors of "neighboring" primitives associated with measures of distance, probability, fuzziness, etc. The use of vague primitives allows us to identify b best structural templates during multi-derivational parsing that can be used for getting more adequate final result. The generic architecture of SPR system based on the approach proposed together with the system's applications for short-term electrical load forecasting and for analysis of ultrasound images in order to diagnose congenital defects of fetal palates are presented. The results of the experimental studies are discussed.

Human parsing has attracted considerable research interest due to its broad potential applications in the computer vision community. In this paper, we explore several useful properties, including high-resolution representation, auxiliary guidance, and model robustness, which collectively contribute to a novel method for accurate human parsing in both simple and complex scenes. Starting from simple scenes: we propose the boundary-aware hybrid resolution network (BHRN), an advanced human parsing network. BHRN utilizes deconvolutional layers and multi-scale supervision to generate rich high-resolution representations. Additionally, it includes an edge perceiving branch designed to enhance the fineness of part boundaries. Building on BHRN, we construct a dual-task mutual learning (DTML) framework. It not only provides implicit guidance to assist the parser by incorporating boundary features, but also explicitly maintains the high-order consistency between the parsing prediction and the ground truth. Toward complex scenes: we develop a domain transform method to enhance the model robustness. By transforming the input space from the spatial domain to the polar harmonic Fourier moment domain, the mapping relationship to the output semantic space is highly stable. This transformation yields robust representations for both clean and corrupted data. When evaluated on standard benchmark datasets, our method achieves superior performance compared to state-of-the-art human parsing methods. Furthermore, our domain transform strategy significantly improves the robustness of DTML dramatically in most complex scenes.

Existing studies on knowledge distillation typically focus on teacher-centered methods, in which the teacher network is trained according to its own standards before transferring the learned knowledge to a student one. However, due to differences in network structure between the teacher and the student, the knowledge learned by the former may not be desired by the latter. Inspired by human educational wisdom, this paper proposes a Student-Centered Distillation (SCD) method that enables the teacher network to adjust its knowledge transfer according to the student network's needs. We implemented SCD based on various human educational wisdom, e.g., the teacher network identified and learned the knowledge desired by the student network on the validation set, and then transferred it to the latter through the training set. To address the problems of current deficiency knowledge, hard sample learning and knowledge forgetting faced by a student network in the learning process, we introduce and improve Proportional-Integral-Derivative (PID) algorithms from automation fields to make them effective in identifying the current knowledge required by the student network. Furthermore, we propose a curriculum learning-based fuzzy strategy and apply it to the proposed PID control algorithm, such that the student network in SCD can actively pay attention to the learning of challenging samples after with certain knowledge. The overall performance of SCD is verified in multiple tasks by comparing it with state-of-the-art ones. Experimental results show that our student-centered distillation method outperforms existing teacher-centered ones.

Text-to-speech (TTS) has made rapid progress in both academia and industry in recent years. Some questions naturally arise that whether a TTS system can achieve human-level quality, how to define/judge that quality, and how to achieve it. In this paper, we answer these questions by first defining the human-level quality based on the statistical significance of subjective measure and introducing appropriate guidelines to judge it, and then developing a TTS system called NaturalSpeech that achieves human-level quality on benchmark datasets. Specifically, we leverage a variational auto-encoder (VAE) for end-to-end text-to-waveform generation, with several key modules to enhance the capacity of the prior from text and reduce the complexity of the posterior from speech, including phoneme pre-training, differentiable duration modeling, bidirectional prior/posterior modeling, and a memory mechanism in VAE. Experimental evaluations on the popular LJSpeech dataset show that our proposed NaturalSpeech achieves -0.01 CMOS (comparative mean opinion score) to human recordings at the sentence level, with Wilcoxon signed rank test at p-level p >> 0.05, which demonstrates no statistically significant difference from human recordings for the first time.

Explainable AI (XAI) is widely viewed as a sine qua non for ever-expanding AI research. A better understanding of the needs of XAI users, as well as human-centered evaluations of explainable models are both a necessity and a challenge. In this paper, we explore how human-computer interaction (HCI) and AI researchers conduct user studies in XAI applications based on a systematic literature review. After identifying and thoroughly analyzing 97 core papers with human-based XAI evaluations over the past five years, we categorize them along the measured characteristics of explanatory methods, namely trust, understanding, usability, and human-AI collaboration performance. Our research shows that XAI is spreading more rapidly in certain application domains, such as recommender systems than in others, but that user evaluations are still rather sparse and incorporate hardly any insights from cognitive or social sciences. Based on a comprehensive discussion of best practices, i.e., common models, design choices, and measures in user studies, we propose practical guidelines on designing and conducting user studies for XAI researchers and practitioners. Lastly, this survey also highlights several open research directions, particularly linking psychological science and human-centered XAI.

Image segmentation is fundamental task for medical image analysis, whose accuracy is improved by the development of neural networks. However, the existing algorithms that achieve high-resolution performance require high-resolution input, resulting in substantial computational expenses and limiting their applicability in the medical field. Several studies have proposed dual-stream learning frameworks incorporating a super-resolution task as auxiliary. In this paper, we rethink these frameworks and reveal that the feature similarity between tasks is insufficient to constrain vessels or lesion segmentation in the medical field, due to their small proportion in the image. To address this issue, we propose a DS2F (Dual-Stream Shared Feature) framework, including a Shared Feature Extraction Module (SFEM). Specifically, we present Multi-Scale Cross Gate (MSCG) utilizing multi-scale features as a novel example of SFEM. Then we define a proxy task and proxy loss to enable the features focus on the targets based on the assumption that a limited set of shared features between tasks is helpful for their performance. Extensive experiments on six publicly available datasets across three different scenarios are conducted to verify the effectiveness of our framework. Furthermore, various ablation studies are conducted to demonstrate the significance of our DS2F.

Gait depicts individuals' unique and distinguishing walking patterns and has become one of the most promising biometric features for human identification. As a fine-grained recognition task, gait recognition is easily affected by many factors and usually requires a large amount of completely annotated data that is costly and insatiable. This paper proposes a large-scale self-supervised benchmark for gait recognition with contrastive learning, aiming to learn the general gait representation from massive unlabelled walking videos for practical applications via offering informative walking priors and diverse real-world variations. Specifically, we collect a large-scale unlabelled gait dataset GaitLU-1M consisting of 1.02M walking sequences and propose a conceptually simple yet empirically powerful baseline model GaitSSB. Experimentally, we evaluate the pre-trained model on four widely-used gait benchmarks, CASIA-B, OU-MVLP, GREW and Gait3D with or without transfer learning. The unsupervised results are comparable to or even better than the early model-based and GEI-based methods. After transfer learning, GaitSSB outperforms existing methods by a large margin in most cases, and also showcases the superior generalization capacity. Further experiments indicate that the pre-training can save about 50% and 80% annotation costs of GREW and Gait3D. Theoretically, we discuss the critical issues for gait-specific contrastive framework and present some insights for further study. As far as we know, GaitLU-1M is the first large-scale unlabelled gait dataset, and GaitSSB is the first method that achieves remarkable unsupervised results on the aforementioned benchmarks.

Contrastive learning, which aims to capture general representation from unlabeled images to initialize the medical analysis models, has been proven effective in alleviating the high demand for expensive annotations. Current methods mainly focus on instance-wise comparisons to learn the global discriminative features, however, pretermitting the local details to distinguish tiny anatomical structures, lesions, and tissues. To address this challenge, in this paper, we propose a general unsupervised representation learning framework, named local discrimination (LD), to learn local discriminative features for medical images by closely embedding semantically similar pixels and identifying regions of similar structures across different images. Specifically, this model is equipped with an embedding module for pixel-wise embedding and a clustering module for generating segmentation. And these two modules are unified by optimizing our novel region discrimination loss function in a mutually beneficial mechanism, which enables our model to reflect structure information as well as measure pixel-wise and region-wise similarity. Furthermore, based on LD, we propose a center-sensitive one-shot landmark localization algorithm and a shape-guided cross-modality segmentation model to foster the generalizability of our model. When transferred to downstream tasks, the learned representation by our method shows a better generalization, outperforming representation from 18 state-of-the-art (SOTA) methods and winning 9 out of all 12 downstream tasks. Especially for the challenging lesion segmentation tasks, the proposed method achieves significantly better performance.

Decoding brain activity from non-invasive electroencephalography (EEG) is crucial for brain-computer interfaces (BCIs) and the study of brain disorders. Notably, end-to-end EEG decoding has gained widespread popularity in recent years owing to the remarkable advances in deep learning research. However, many EEG studies suffer from limited sample sizes, making it difficult for existing deep learning models to effectively generalize to highly noisy EEG data. To address this fundamental limitation, this paper proposes a novel end-to-end EEG decoding algorithm that utilizes a low-rank weight matrix to encode both spatio-temporal filters and the classifier, all optimized under a principled sparse Bayesian learning (SBL) framework. Importantly, this SBL framework also enables us to learn hyperparameters that optimally penalize the model in a Bayesian fashion. The proposed decoding algorithm is systematically benchmarked on five motor imagery BCI EEG datasets ( N=192) and an emotion recognition EEG dataset ( N=45), in comparison with several contemporary algorithms, including end-to-end deep-learning-based EEG decoding algorithms. The classification results demonstrate that our algorithm significantly outperforms the competing algorithms while yielding neurophysiologically meaningful spatio-temporal patterns. Our algorithm therefore advances the state-of-the-art by providing a novel EEG-tailored machine learning tool for decoding brain activity.

Previous human parsing methods are limited to parsing humans into pre-defined classes, which is inflexible for practical fashion applications that often have new fashion item classes. In this paper, we define a novel one-shot human parsing (OSHP) task that requires parsing humans into an open set of classes defined by any test example. During training, only base classes are exposed, which only overlap with part of the test-time classes. To address three main challenges in OSHP, i.e., small sizes, testing bias, and similar parts, we devise an End-to-end One-shot human Parsing Network (EOP-Net). Firstly, an end-to-end human parsing framework is proposed to parse the query image into both coarse-grained and fine-grained human classes, which embeds rich semantic information that is shared across different granularities to identify the small-sized human classes. Then, we gradually smooth the training-time static prototypes to get robust class representations. Moreover, we employ a dynamic objective to encourage the network enhancing features' representational capability in the early training phase while improving features' transferability in the late training phase. Therefore, our method can quickly adapt to the novel classes and mitigate the testing bias issue. In addition, we add a contrastive loss at the prototype level to enforce inter-class distances, thereby discriminating the similar parts. For comprehensive evaluations on the new task, we tailor three existing popular human parsing benchmarks to the OSHP task. Experiments demonstrate that EOP-Net outperforms representative one-shot segmentation models by large margins and serves as a strong baseline for further research.

The commonsense natural language inference (CNLI) tasks aim to select the most likely follow-up statement to a contextual description of ordinary, everyday events and facts. Current approaches to transfer learning of CNLI models across tasks require many labeled data from the new task. This paper presents a way to reduce this need for additional annotated training data from the new task by leveraging symbolic knowledge bases, such as ConceptNet. We formulate a teacher-student framework for mixed symbolic-neural reasoning, with the large-scale symbolic knowledge base serving as the teacher and a trained CNLI model as the student. This hybrid distillation process involves two steps. The first step is a symbolic reasoning process. Given a collection of unlabeled data, we use an abductive reasoning framework based on Grenander's pattern theory to create weakly labeled data. Pattern theory is an energy-based graphical probabilistic framework for reasoning among random variables with varying dependency structures. In the second step, the weakly labeled data, along with a fraction of the labeled data, is used to transfer-learn the CNLI model into the new task. The goal is to reduce the fraction of labeled data required. We demonstrate the efficacy of our approach by using three publicly available datasets (OpenBookQA, SWAG, and HellaSWAG) and evaluating three CNLI models (BERT, LSTM, and ESIM) that represent different tasks. We show that, on average, we achieve 63% of the top performance of a fully supervised BERT model with no labeled data. With only 1,000 labeled samples, we can improve this performance to 72%. Interestingly, without training, the teacher mechanism itself has significant inference power. The pattern theory framework achieves 32.7% accuracy on OpenBookQA, outperforming transformer-based models such as GPT (26.6%), GPT-2 (30.2%), and BERT (27.1%) by a significant margin. We demonstrate that the framework can be generalized to successfully train neural CNLI models using knowledge distillation under unsupervised and semi-supervised learning settings. Our results show that it outperforms all unsupervised and weakly supervised baselines and some early supervised approaches, while offering competitive performance with fully supervised baselines. Additionally, we show that the abductive learning framework can be adapted for other downstream tasks, such as unsupervised semantic textual similarity, unsupervised sentiment classification, and zero-shot text classification, without significant modification to the framework. Finally, user studies show that the generated interpretations enhance its explainability by providing key insights into its reasoning mechanism.

Training state-of-the-art models for human pose estimation in videos requires datasets with annotations that are really hard and expensive to obtain. Although transformers have been recently utilized for body pose sequence modeling, related methods rely on pseudo-ground truth to augment the currently limited training data available for learning such models. In this paper, we introduce PoseBERT, a transformer module that is fully trained on 3D Motion Capture (MoCap) data via masked modeling. It is simple, generic and versatile, as it can be plugged on top of any image-based model to transform it in a video-based model leveraging temporal information. We showcase variants of PoseBERT with different inputs varying from 3D skeleton keypoints to rotations of a 3D parametric model for either the full body (SMPL) or just the hands (MANO). Since PoseBERT training is task agnostic, the model can be applied to several tasks such as pose refinement, future pose prediction or motion completion without finetuning. Our experimental results validate that adding PoseBERT on top of various state-of-the-art pose estimation methods consistently improves their performances, while its low computational cost allows us to use it in a real-time demo for smoothly animating a robotic hand via a webcam. Test code and models are available at https://github.com/naver/posebert.

As powerful as fine-grained visual classification (FGVC) is, responding your query with a bird name of "Whip-poor-will" or "Mallard" probably does not make much sense. This however commonly accepted in the literature, underlines a fundamental question interfacing AI and human - what constitutes transferable knowledge for human to learn from AI? This paper sets out to answer this very question using FGVC as a test bed. Specifically, we envisage a scenario where a trained FGVC model (the AI expert) functions as a knowledge provider in enabling average people (you and me) to become better domain experts ourselves. Assuming an AI expert trained using expert human labels, we anchor our focus on asking and providing solutions for two questions: (i) what is the best transferable knowledge we can extract from AI, and (ii) what is the most practical means to measure the gains in expertise given that knowledge? We propose to represent knowledge as highly discriminative visual regions that are expert-exclusive and instantiate it via a novel multi-stage learning framework. A human study of 15,000 trials shows our method is able to consistently improve people of divergent bird expertise to recognise once unrecognisable birds. We further propose a crude but benchmarkable metric TEMI and therefore allow future efforts in this direction to be comparable to ours without the need of large-scale human studies.

Compared with the progress made on human activity classification, much less success has been achieved on human interaction understanding (HIU). Apart from the latter task is much more challenging, the main causation is that recent approaches learn human interactive relations via shallow graphical representations, which are inadequate to model complicated human interactive-relations. This paper proposes a deep consistency-aware framework aiming at tackling the grouping and labelling inconsistencies in HIU. This framework consists of three components, including a backbone CNN to extract image features, a factor graph network to implicitly learn higher-order consistencies among labelling and grouping variables, and a consistency-aware reasoning module to explicitly enforcing consistencies. The last module is inspired by our key observation that the consistency-aware reasoning bias can be embedded into an energy function or a particular loss function, minimizing which delivers consistent predictions. An efficient mean-field inference algorithm is proposed, such that all modules of our network could be trained in an end-to-end fashion. Experimental results demonstrate that the two proposed consistency-learning modules complement each other, and both make considerable contributions in achieving leading performance on three benchmarks of HIU. The effectiveness of the proposed approach is further validated by experiments on detecting human-object interactions.

Decoding human visual neural representations is a challenging task with great scientific significance in revealing vision-processing mechanisms and developing brain-like intelligent machines. Most existing methods are difficult to generalize to novel categories that have no corresponding neural data for training. The two main reasons are 1) the under-exploitation of the multimodal semantic knowledge underlying the neural data and 2) the small number of paired (stimuli-responses) training data. To overcome these limitations, this paper presents a generic neural decoding method called BraVL that uses multimodal learning of brain-visual-linguistic features. We focus on modeling the relationships between brain, visual and linguistic features via multimodal deep generative models. Specifically, we leverage the mixture-of-product-of-experts formulation to infer a latent code that enables a coherent joint generation of all three modalities. To learn a more consistent joint representation and improve the data efficiency in the case of limited brain activity data, we exploit both intra- and inter-modality mutual information maximization regularization terms. In particular, our BraVL model can be trained under various semi-supervised scenarios to incorporate the visual and textual features obtained from the extra categories. Finally, we construct three trimodal matching datasets, and the extensive experiments lead to some interesting conclusions and cognitive insights: 1) decoding novel visual categories from human brain activity is practically possible with good accuracy; 2) decoding models using the combination of visual and linguistic features perform much better than those using either of them alone; 3) visual perception may be accompanied by linguistic influences to represent the semantics of visual stimuli.

In human and hand pose estimation, heatmaps are a crucial intermediate representation for a body or hand keypoint. Two popular methods to decode the heatmap into a final joint coordinate are via an argmax, as done in heatmap detection, or via softmax and expectation, as done in integral regression. Integral regression is learnable end-to-end, but has lower accuracy than detection. This paper uncovers an induced bias from integral regression that results from combining the softmax and the expectation operation. This bias often forces the network to learn degenerately localized heatmaps, obscuring the keypoint's true underlying distribution and leads to lower accuracies. Training-wise, by investigating the gradients of integral regression, we show that the implicit guidance of integral regression to update the heatmap makes it slower to converge than detection. To counter the above two limitations, we propose Bias Compensated Integral Regression (BCIR), an integral regression-based framework that compensates for the bias. BCIR also incorporates a Gaussian prior loss to speed up training and improve prediction accuracy. Experimental results on both the human body and hand benchmarks show that BCIR is faster to train and more accurate than the original integral regression, making it competitive with state-of-the-art detection methods.

In this paper, we study a challenging but less-touched problem in cross-modal retrieval, i.e., partially mismatched pairs (PMPs). Specifically, in real-world scenarios, a huge number of multimedia data (e.g., the Conceptual Captions dataset) are collected from the Internet, and thus it is inevitable to wrongly treat some irrelevant cross-modal pairs as matched. Undoubtedly, such a PMP problem will remarkably degrade the cross-modal retrieval performance. To tackle this problem, we derive a unified theoretical Robust Cross-modal Learning framework (RCL) with an unbiased estimator of the cross-modal retrieval risk, which aims to endow the cross-modal retrieval methods with robustness against PMPs. In detail, our RCL adopts a novel complementary contrastive learning paradigm to address the following two challenges, i.e., the overfitting and underfitting issues. On the one hand, our method only utilizes the negative information which is much less likely false compared with the positive information, thus avoiding the overfitting issue to PMPs. However, these robust strategies could induce underfitting issues, thus making training models more difficult. On the other hand, to address the underfitting issue brought by weak supervision, we present to leverage of all available negative pairs to enhance the supervision contained in the negative information. Moreover, to further improve the performance, we propose to minimize the upper bounds of the risk to pay more attention to hard samples. To verify the effectiveness and robustness of the proposed method, we carry out comprehensive experiments on five widely-used benchmark datasets compared with nine state-of-the-art approaches w.r.t. the image-text and video-text retrieval tasks. The code is available at https://github.com/penghu-cs/RCL.

Removing the undesired moiré patterns from images capturing the contents displayed on screens is of increasing research interest, as the need for recording and sharing the instant information conveyed by the screens is growing. Previous demoiréing methods provide limited investigations into the formation process of moiré patterns to exploit moiré-specific priors for guiding the learning of demoiréing models. In this paper, we investigate the moiré pattern formation process from the perspective of signal aliasing, and correspondingly propose a coarse-to-fine disentangling demoiréing framework. In this framework, we first disentangle the moiré pattern layer and the clean image with alleviated ill-posedness based on the derivation of our moiré image formation model. Then we refine the demoiréing results exploiting both the frequency domain features and edge attention, considering moiré patterns' property on spectrum distribution and edge intensity revealed in our aliasing based analysis. Experiments on several datasets show that the proposed method performs favorably against state-of-the-art methods. Besides, the proposed method is validated to adapt well to different data sources and scales, especially on the high-resolution moiré images.

The widespread arising of data size gives rise to the necessity of undertaking large-scale data clustering tasks. To do so, the bipartite graph theory is frequently applied to design a scalable algorithm, which depicts the relations between samples and a few anchors, instead of binding pairwise samples. However, the bipartite graphs and existing spectral embedding methods ignore the explicit cluster structure learning. They have to obtain cluster labels by using post-processing like K-Means. More than that, existing anchor-based approaches always acquire anchors by using centroids of K-Means or a few random samples, both of which are time-saving but performance-unstable. In this paper, we investigate the scalability, stableness and integration in large-scale graph clustering. We propose a cluster-structured graph learning model, thus obtaining a c-connected ( c is the cluster number) bipartite graph and also getting discrete labels straightforward. Taking data feature or pairwise relation as a start point, we further design an initialization-independent anchor selection strategy. Experimental results reported for synthetic and real-world datasets demonstrate the proposed method outperforms its peers.

One fundamental challenge of instance-level human analysis is to decouple instances in crowded scenes, where multiple persons are overlapped with each other. This paper proposes the Contextual Instance Decoupling (CID), which presents a new pipeline of decoupling persons for multi-person instance-level analysis. Instead of relying on person bounding boxes to spatially differentiate persons, CID decouples persons in an image into multiple instance-aware feature maps. Each of those feature maps is hence adopted to infer instance-level cues for a specific person, e.g., keypoints, instance mask or part segmentation masks. Compared with bounding box detection, CID is differentiable and robust to detection errors. Decoupling persons into different feature maps also allows to isolate distractions from other persons, and explore context cues at scales larger than the bounding box size. Extensive experiments on various tasks including multi-person pose estimation, person foreground segmentation, and part segmentation, show that CID consistently outperforms previous methods in both accuracy and efficiency. For instance, it achieves 71.3% AP on CrowdPose in multi-person pose estimation, outperforming the recent single-stage DEKR by 5.6%, the bottom-up CenterAttention by 3.7%, and the top-down JC-SPPE by 5.3%. This advantage sustains on multi-person segmentation and part segmentation tasks.

Existing image-based rendering methods usually adopt depth-based image warping operation to synthesize novel views. In this paper, we reason the essential limitations of the traditional warping operation to be the limited neighborhood and only distance-based interpolation weights. To this end, we propose content-aware warping, which adaptively learns the interpolation weights for pixels of a relatively large neighborhood from their contextual information via a lightweight neural network. Based on this learnable warping module, we propose a new end-to-end learning-based framework for novel view synthesis from a set of input source views, in which two additional modules, namely confidence-based blending and feature-assistant spatial refinement, are naturally proposed to handle the occlusion issue and capture the spatial correlation among pixels of the synthesized view, respectively. Besides, we also propose a weight-smoothness loss term to regularize the network. Experimental results on light field datasets with wide baselines and multi-view datasets show that the proposed method significantly outperforms state-of-the-art methods both quantitatively and visually. The source code is publicly available at https://github.com/MantangGuo/CW4VS.

The rapid development of deep learning has made a great progress in image segmentation, one of the fundamental tasks of computer vision. However, the current segmentation algorithms mostly rely on the availability of pixel-level annotations, which are often expensive, tedious, and laborious. To alleviate this burden, the past years have witnessed an increasing attention in building label-efficient, deep-learning-based image segmentation algorithms. This paper offers a comprehensive review on label-efficient image segmentation methods. To this end, we first develop a taxonomy to organize these methods according to the supervision provided by different types of weak labels (including no supervision, inexact supervision, incomplete supervision and inaccurate supervision) and supplemented by the types of segmentation problems (including semantic segmentation, instance segmentation and panoptic segmentation). Next, we summarize the existing label-efficient image segmentation methods from a unified perspective that discusses an important question: how to bridge the gap between weak supervision and dense prediction - the current methods are mostly based on heuristic priors, such as cross-pixel similarity, cross-label constraint, cross-view consistency, and cross-image relation. Finally, we share our opinions about the future research directions for label-efficient deep image segmentation.

Previous works for LiDAR-based 3D object detection mainly focus on the single-frame paradigm. In this paper, we propose to detect 3D objects by exploiting temporal information in multiple frames, i.e., point cloud videos. We empirically categorize the temporal information into short-term and long-term patterns. To encode the short-term data, we present a Grid Message Passing Network (GMPNet), which considers each grid (i.e., the grouped points) as a node and constructs a k-NN graph with the neighbor grids. To update features for a grid, GMPNet iteratively collects information from its neighbors, thus mining the motion cues in grids from nearby frames. To further aggregate long-term frames, we propose an Attentive Spatiotemporal Transformer GRU (AST-GRU), which contains a Spatial Transformer Attention (STA) module and a Temporal Transformer Attention (TTA) module. STA and TTA enhance the vanilla GRU to focus on small objects and better align moving objects. Our overall framework supports both online and offline video object detection in point clouds. We implement our algorithm based on prevalent anchor-based and anchor-free detectors. Evaluation results on the challenging nuScenes benchmark show superior performance of our method, achieving first on the leaderboard (at the time of paper submission) without any "bells and whistles." Our source code is available at https://github.com/shenjianbing/GMP3D.

Low-rank self-representation based subspace learning has confirmed its great effectiveness in a broad range of applications. Nevertheless, existing studies mainly focus on exploring the global linear subspace structure, and cannot commendably handle the case where the samples approximately (i.e., the samples contain data errors) lie in several more general affine subspaces. To overcome this drawback, in this paper, we innovatively propose to introduce affine and nonnegative constraints into low-rank self-representation learning. While simple enough, we provide their underlying theoretical insight from a geometric perspective. The union of two constraints geometrically restricts each sample to be expressed as a convex combination of other samples in the same subspace. In this way, when exploring the global affine subspace structure, we can also consider the specific local distribution of data in each subspace. To comprehensively demonstrate the benefits of introducing two constraints, we instantiate three low-rank self-representation methods ranging from single-view low-rank matrix learning to multi-view low-rank tensor learning. We carefully design the solution algorithms to efficiently optimize the proposed three approaches. Extensive experiments are conducted on three typical tasks, including single-view subspace clustering, multi-view subspace clustering, and multi-view semi-supervised classification. The notably superior experimental results powerfully verify the effectiveness of our proposals.

Speech disentanglement aims to decompose independent causal factors of speech signals into separate codes. Perfect disentanglement benefits to a broad range of speech processing tasks. This paper presents a simple but effective disentanglement approach based on cycle consistency loss and random factor substitution. This leads to a novel random cycle (RC) loss that enforces analysis-and-resynthesis consistency, a main principle of reductionism. We theoretically demonstrate that the proposed RC loss can achieve independent codes if well optimized, which in turn leads to superior disentanglement when combined with information bottleneck (IB). Extensive simulation experiments were conducted to understand the properties of the RC loss, and experimental results on voice conversion further demonstrate the practical merit of the proposal. Source code and audio samples can be found on the webpage http://rc.cslt.org.

Neural networks often make predictions relying on the spurious correlations from the datasets rather than the intrinsic properties of the task of interest, facing with sharp degradation on out-of-distribution (OOD) test data. Existing de-bias learning frameworks try to capture specific dataset bias by annotations but they fail to handle complicated OOD scenarios. Others implicitly identify the dataset bias by special design low capability biased models or losses, but they degrade when the training and testing data are from the same distribution. In this paper, we propose a General Greedy De-bias learning framework (GGD), which greedily trains the biased models and base model. The base model is encouraged to focus on examples that are hard to solve with biased models, thus remaining robust against spurious correlations in the test stage. GGD largely improves models' OOD generalization ability on various tasks, but sometimes over-estimates the bias level and degrades on the in-distribution test. We further re-analyze the ensemble process of GGD and introduce the Curriculum Regularization inspired by curriculum learning, which achieves a good trade-off between in-distribution (ID) and out-of-distribution performance. Extensive experiments on image classification, adversarial question answering, and visual question answering demonstrate the effectiveness of our method. GGD can learn a more robust base model under the settings of both task-specific biased models with prior knowledge and self-ensemble biased model without prior knowledge. Codes are available at https://github.com/GeraldHan/GGD.

Interest point detection methods are gaining more attention and are widely applied in computer vision tasks such as image retrieval and 3D reconstruction. However, there still exist two main problems to be solved: (1) from the perspective of mathematical representations, the differences among edges, corners, and blobs have not been convincingly explained and the relationships among the amplitude response, scale factor, and filtering orientation for interest points have not been thoroughly explained; (2) the existing design mechanism for interest point detection does not show how to accurately obtain intensity variation information on corners and blobs. In this paper, the first- and second-order Gaussian directional derivative representations of a step edge, four common genres of corners, an anisotropic-type blob, and an isotropic-type blob are analyzed and derived. Multiple interest point characteristics are discovered. The characteristics for interest points that we obtained help us describe the differences among edges, corners, and blobs, explain why the existing interest point detection methods with multiple scales cannot properly obtain interest points from images, and present novel corner and blob detection methods. Extensive experiments demonstrate the superiority of our proposed methods in terms of detection performance, robustness to affine transformations, noise, image matching, and 3D reconstruction.

This paper addresses the challenge of novel view synthesis for a human performer from a very sparse set of camera views. Some recent works have shown that learning implicit neural representations of 3D scenes achieves remarkable view synthesis quality given dense input views. However, the representation learning will be ill-posed if the views are highly sparse. To solve this ill-posed problem, our key idea is to integrate observations over video frames. To this end, we propose Neural Body, a new human body representation which assumes that the learned neural representations at different frames share the same set of latent codes anchored to a deformable mesh, so that the observations across frames can be naturally integrated. The deformable mesh also provides geometric guidance for the network to learn 3D representations more efficiently. Furthermore, we combine Neural Body with implicit surface models to improve the learned geometry. To evaluate our approach, we perform experiments on both synthetic and real-world data, which show that our approach outperforms prior works by a large margin on novel view synthesis and 3D reconstruction. We also demonstrate the capability of our approach to reconstruct a moving person from a monocular video on the People-Snapshot dataset.

Asymmetric kernels naturally exist in real life, e.g., for conditional probability and directed graphs. However, most of the existing kernel-based learning methods require kernels to be symmetric, which prevents the use of asymmetric kernels. This paper addresses the asymmetric kernel-based learning in the framework of the least squares support vector machine named AsK-LS, resulting in the first classification method that can utilize asymmetric kernels directly. We will show that AsK-LS can learn with asymmetric features, namely source and target features, while the kernel trick remains applicable, i.e., the source and target features exist but are not necessarily known. Besides, the computational burden of AsK-LS is as cheap as dealing with symmetric kernels. Experimental results on various tasks, including Corel, PASCAL VOC, Satellite, directed graphs, and UCI database, all show that in the case asymmetric information is crucial, the proposed AsK-LS can learn with asymmetric kernels and performs much better than the existing kernel methods that rely on symmetrization to accommodate asymmetric kernels.

Modern medical imaging techniques, such as ultrasound (US) and cardiac magnetic resonance (MR) imaging, have enabled the evaluation of myocardial deformation directly from an image sequence. While many traditional cardiac motion tracking methods have been developed for the automated estimation of the myocardial wall deformation, they are not widely used in clinical diagnosis, due to their lack of accuracy and efficiency. In this paper, we propose a novel deep learning-based fully unsupervised method, SequenceMorph, for in vivo motion tracking in cardiac image sequences. In our method, we introduce the concept of motion decomposition and recomposition. We first estimate the inter-frame (INF) motion field between any two consecutive frames, by a bi-directional generative diffeomorphic registration neural network. Using this result, we then estimate the Lagrangian motion field between the reference frame and any other frame, through a differentiable composition layer. Our framework can be extended to incorporate another registration network, to further reduce the accumulated errors introduced in the INF motion tracking step, and to refine the Lagrangian motion estimation. By utilizing temporal information to perform reasonable estimations of spatio-temporal motion fields, this novel method provides a useful solution for image sequence motion tracking. Our method has been applied to US (echocardiographic) and cardiac MR (untagged and tagged cine) image sequences; the results show that SequenceMorph is significantly superior to conventional motion tracking methods, in terms of the cardiac motion tracking accuracy and inference efficiency.

Point clouds are characterized by irregularity and unstructuredness, which pose challenges in efficient data exploitation and discriminative feature extraction. In this paper, we present an unsupervised deep neural architecture called Flattening-Net to represent irregular 3D point clouds of arbitrary geometry and topology as a completely regular 2D point geometry image (PGI) structure, in which coordinates of spatial points are captured in colors of image pixels. Intuitively, Flattening-Net implicitly approximates a locally smooth 3D-to-2D surface flattening process while effectively preserving neighborhood consistency. As a generic representation modality, PGI inherently encodes the intrinsic property of the underlying manifold structure and facilitates surface-style point feature aggregation. To demonstrate its potential, we construct a unified learning framework directly operating on PGIs to achieve diverse types of high-level and low-level downstream applications driven by specific task networks, including classification, segmentation, reconstruction, and upsampling. Extensive experiments demonstrate that our methods perform favorably against the current state-of-the-art competitors.

Image-to-image translation (i2i) networks suffer from entanglement effects in presence of physics-related phenomena in target domain (such as occlusions, fog, etc), lowering altogether the translation quality, controllability and variability. In this paper, we propose a general framework to disentangle visual traits in target images. Primarily, we build upon collection of simple physics models, guiding the disentanglement with a physical model that renders some of the target traits, and learning the remaining ones. Because physics allows explicit and interpretable outputs, our physical models (optimally regressed on target) allows generating unseen scenarios in a controllable manner. Secondarily, we show the versatility of our framework to neural-guided disentanglement where a generative network is used in place of a physical model in case the latter is not directly accessible. Altogether, we introduce three strategies of disentanglement being guided from either a fully differentiable physics model, a (partially) non-differentiable physics model, or a neural network. The results show our disentanglement strategies dramatically increase performances qualitatively and quantitatively in several challenging scenarios for image translation.

Non-rigid 3D registration, which deforms a source 3D shape in a non-rigid way to align with a target 3D shape, is a classical problem in computer vision. Such problems can be challenging because of imperfect data (noise, outliers and partial overlap) and high degrees of freedom. Existing methods typically adopt the l p type robust norm to measure the alignment error and regularize the smoothness of deformation, and use a proximal algorithm to solve the resulting non-smooth optimization problem. However, the slow convergence of such algorithms limits their wide applications. In this paper, we propose a formulation for robust non-rigid registration based on a globally smooth robust norm for alignment and regularization, which can effectively handle outliers and partial overlaps. The problem is solved using the majorization-minimization algorithm, which reduces each iteration to a convex quadratic problem with a closed-form solution. We further apply Anderson acceleration to speed up the convergence of the solver, enabling the solver to run efficiently on devices with limited compute capability. Extensive experiments demonstrate the effectiveness of our method for non-rigid alignment between two shapes with outliers and partial overlaps, with quantitative evaluation showing that it outperforms state-of-the-art methods in terms of registration accuracy and computational speed. The source code is available at https://github.com/yaoyx689/AMM_NRR.

We present RoReg, a novel point cloud registration framework that fully exploits oriented descriptors and estimated local rotations in the whole registration pipeline. Previous methods mainly focus on extracting rotation-invariant descriptors for registration but unanimously neglect the orientations of descriptors. In this paper, we show that the oriented descriptors and the estimated local rotations are very useful in the whole registration pipeline, including feature description, feature detection, feature matching, and transformation estimation. Consequently, we design a novel oriented descriptor RoReg-Desc and apply RoReg-Desc to estimate the local rotations. Such estimated local rotations enable us to develop a rotation-guided detector, a rotation coherence matcher, and a one-shot-estimation RANSAC, all of which greatly improve the registration performance. Extensive experiments demonstrate that RoReg achieves state-of-the-art performance on the widely-used 3DMatch and 3DLoMatch datasets, and also generalizes well to the outdoor ETH dataset. In particular, we also provide in-depth analysis on each component of RoReg, validating the improvements brought by oriented descriptors and the estimated local rotations. Source code and supplementary material are available at https://github.com/HpWang-whu/RoReg.

With convolution operations, Convolutional Neural Networks (CNNs) are good at extracting local features but experience difficulty to capture global representations. With cascaded self-attention modules, vision transformers can capture long-distance feature dependencies but unfortunately deteriorate local feature details. In this paper, we propose a hybrid network structure, termed Conformer, to take both advantages of convolution operations and self-attention mechanisms for enhanced representation learning. Conformer roots in feature coupling of CNN local features and transformer global representations under different resolutions in an interactive fashion. Conformer adopts a dual structure so that local details and global dependencies are retained to the maximum extent. We also propose a Conformer-based detector (ConformerDet), which learns to predict and refine object proposals, by performing region-level feature coupling in an augmented cross-attention fashion. Experiments on ImageNet and MS COCO datasets validate Conformer's superiority for visual recognition and object detection, demonstrating its potential to be a general backbone network.

Multi-dimensional prediction models of the pandemic diseases should be constructed in a way to reflect their peculiar epidemiological characters. In this paper, a graph theory-based constrained multi-dimensional (CM) mathematical and meta-heuristic algorithms (MA) are formed to learn the unknown parameters of a large-scale epidemiological model. The specified parameter signs and the coupling parameters of the sub-models constitute the constraints of the optimization problem. In addition, magnitude constraints on the unknown parameters are imposed to proportionally weight the input-output data importance. To learn these parameters, a gradient-based CM recursive least square (CM-RLS) algorithm, and three search-based MAs; namely, the CM particle swarm optimization (CM-PSO), the CM success history-based adaptive differential evolution (CM-SHADE), and the CM-SHADEWO enriched with the whale optimization (WO) algorithms are constructed. The traditional SHADE algorithm was the winner of the 2018 IEEE congress on evolutionary computation (CEC) and its versions in this paper are modified to create more certain parameter search spaces. The results obtained under the equal conditions show that the mathematical optimization algorithm CM-RLS outperforms the MA algorithms, which is expected since it uses the available gradient information. However, the search-based CM-SHADEWO algorithm is able to capture the dominant character of the CM optimization solution and produce satisfactory estimates in the presence of the hard constraints, uncertainties and lack of gradient information.

Recently, many advances in inverse rendering are achieved by high-dimensional lighting representations and differentiable rendering. However, multi-bounce lighting effects can hardly be handled correctly in scene editing using high-dimensional lighting representations, and light source model deviation and ambiguities exist in differentiable rendering methods. These problems limit the applications of inverse rendering. In this paper, we present a multi-bounce inverse rendering method based on Monte Carlo path tracing, to enable correct complex multi-bounce lighting effects rendering in scene editing. We propose a novel light source model that is more suitable for light source editing in indoor scenes, and design a specific neural network with corresponding disambiguation constraints to alleviate ambiguities during the inverse rendering. We evaluate our method on both synthetic and real indoor scenes through virtual object insertion, material editing, relighting tasks, and so on. The results demonstrate that our method achieves better photo-realistic quality.

Food recognition plays an important role in food choice and intake, which is essential to the health and well-being of humans. It is thus of importance to the computer vision community, and can further support many food-oriented vision and multimodal tasks, e.g., food detection and segmentation, cross-modal recipe retrieval and generation. Unfortunately, we have witnessed remarkable advancements in generic visual recognition for released large-scale datasets, yet largely lags in the food domain. In this paper, we introduce Food2K, which is the largest food recognition dataset with 2,000 categories and over 1 million images. Compared with existing food recognition datasets, Food2K bypasses them in both categories and images by one order of magnitude, and thus establishes a new challenging benchmark to develop advanced models for food visual representation learning. Furthermore, we propose a deep progressive region enhancement network for food recognition, which mainly consists of two components, namely progressive local feature learning and region feature enhancement. The former adopts improved progressive training to learn diverse and complementary local features, while the latter utilizes self-attention to incorporate richer context with multiple scales into local features for further local feature enhancement. Extensive experiments on Food2K demonstrate the effectiveness of our proposed method. More importantly, we have verified better generalization ability of Food2K in various tasks, including food image recognition, food image retrieval, cross-modal recipe retrieval, food detection and segmentation. Food2K can be further explored to benefit more food-relevant tasks including emerging and more complex ones (e.g., nutritional understanding of food), and the trained models on Food2K can be expected as backbones to improve the performance of more food-relevant tasks. We also hope Food2K can serve as a large scale fine-grained visual recognition benchmark, and contributes to the development of large scale fine-grained visual analysis.

Current survival analysis of cancers confronts two key issues. While comprehensive perspectives provided by data from multiple modalities often promote the performance of survival models, data with inadequate modalities at the testing phase are more ubiquitous in clinical scenarios, which makes multi-modality approaches not applicable. Additionally, incomplete observations (i.e., censored instances) bring a unique challenge for survival analysis, to tackle which, some models have been proposed based on certain strict assumptions or attribute distributions that, however, may limit their applicability. In this paper, we present a mutual-assistance learning paradigm for standalone mono-modality survival analysis of cancers. The mutual assistance implies the cooperation of multiple components and embodies three aspects: 1) it leverages the knowledge of multi-modality data to guide the representation learning of an individual modality via mutual-assistance similarity and geometry constraints; 2) it formulates mutual-assistance regression and ranking functions independent of strong hypotheses to estimate the relative risk, in which a bias vector is introduced to efficiently cope with the censoring problem; 3) it integrates representation learning and survival modeling into a unified mutual-assistance framework for alleviating the requirement of attribute distributions. Extensive experiments on several datasets demonstrate our method can significantly improve the performance of mono-modality survival model.

The popularity of egocentric cameras and their always-on nature has lead to the abundance of day long first-person videos. The highly redundant nature of these videos and extreme camera-shakes make them difficult to watch from beginning to end. These videos require efficient summarization tools for consumption. However, traditional summarization techniques developed for static surveillance videos or highly curated sports videos and movies are either not suitable or simply do not scale for such hours long videos in the wild. On the other hand, specialized summarization techniques developed for egocentric videos limit their focus to important objects and people. This paper presents a novel unsupervised reinforcement learning framework to summarize egocentric videos both in terms of length and the content. The proposed framework facilitates incorporating various prior preferences such as faces, places, or scene diversity and interactive user choice in terms of including or excluding the particular type of content. This approach can also be adapted to generate summaries of various lengths, making it possible to view even 1-minute summaries of one's entire day. When using the facial saliency-based reward, we show that our approach generates summaries focusing on social interactions, similar to the current state-of-the-art (SOTA). The quantitative comparisons on the benchmark Disney dataset show that our method achieves significant improvement in Relaxed F-Score (RFS) (29.60 compared to 19.21 from SOTA), BLEU score (0.68 compared to 0.67 from SOTA), Average Human Ranking (AHR), and unique events covered. Finally, we show that our technique can be applied to summarize traditional, short, hand-held videos as well, where we improve the SOTA F-score on benchmark SumMe and TVSum datasets from 41.4 to 46.40 and 57.6 to 58.3 respectively. We also provide a Pytorch implementation and a web demo at https://pravin74.github.io/Int-sum/index.html.

Noninvasive medical neuroimaging has yielded many discoveries about the brain connectivity. Several substantial techniques mapping morphological, structural and functional brain connectivities were developed to create a comprehensive road map of neuronal activities in the human brain -namely brain graph. Relying on its non-euclidean data type, graph neural network (GNN) provides a clever way of learning the deep graph structure and it is rapidly becoming the state-of-the-art leading to enhanced performance in various network neuroscience tasks. Here we review current GNN-based methods, highlighting the ways that they have been used in several applications related to brain graphs such as missing brain graph synthesis and disease classification. We conclude by charting a path toward a better application of GNN models in network neuroscience field for neurological disorder diagnosis and population graph integration. The list of papers cited in our work is available at https://github.com/basiralab/GNNs-in-Network-Neuroscience.

For long-tailed distributed data, existing classification models often learn overwhelmingly on the head classes while ignoring the tail classes, resulting in poor generalization capability. To address this problem, we thereby propose a new approach in this paper, in which a key point sensitive (KPS) loss is presented to regularize the key points strongly to improve the generalization performance of the classification model. Meanwhile, in order to improve the performance on tail classes, the proposed KPS loss also assigns relatively large margins on tail classes. Furthermore, we propose a gradient adjustment (GA) optimization strategy to re-balance the gradients of positive and negative samples for each class. By virtue of the gradient analysis of the loss function, it is found that the tail classes always receive negative signals during training, which misleads the tail prediction to be biased towards the head. The proposed GA strategy can circumvent excessive negative signals on tail classes and further improve the overall classification accuracy. Extensive experiments conducted on long-tailed benchmarks show that the proposed method is capable of significantly improving the classification accuracy of the model in tail classes while maintaining competent performance in head classes.

Occlusions between human and objects, especially for the activities of human-object interactions, are very common in practical applications. However, most of the existing approaches for 3D human shape and pose estimation require that human bodies are well captured without occlusions or with minor self-occlusions. In this paper, we focus on the problem of directly estimating the object-occluded human shape and pose from single color images. Our key idea is to utilize a partial UV map to represent an object-occluded human body, and the full 3D human shape estimation is ultimately converted as an image inpainting problem. We propose a novel two-branch network architecture to train an end-to-end regressor via a latent distribution consistency, which also includes a novel visible feature sub-net to extract the human information from object-occluded color images. To supervise the network training, we further build a novel dataset named as 3DOH50K. Several experiments are conducted to reveal the effectiveness of the proposed method. Experimental results demonstrate that the proposed method achieves state-of-the-art compared with previous methods. The dataset and codes are publicly available at https://www.yangangwang.com/papers/ZHANG-OOH-2020-03.html.

This paper investigates the task of 2D whole-body human pose estimation, which aims to localize dense landmarks on the entire human body including body, feet, face, and hands. We propose a single-network approach, termed ZoomNet, to take into account the hierarchical structure of the full human body and solve the scale variation of different body parts. We further propose a neural architecture search framework, termed ZoomNAS, to promote both the accuracy and efficiency of whole-body pose estimation. ZoomNAS jointly searches the model architecture and the connections between different sub-modules, and automatically allocates computational complexity for searched sub-modules. To train and evaluate ZoomNAS, we introduce the first large-scale 2D human whole-body dataset, namely COCO-WholeBody V1.0, which annotates 133 keypoints for in-the-wild images. Extensive experiments demonstrate the effectiveness of ZoomNAS and the significance of COCO-WholeBody V1.0.

Recent deep face hallucination methods show stunning performance in super-resolving severely degraded facial images, even surpassing human ability. However, these algorithms are mainly evaluated on non-public synthetic datasets. It is thus unclear how these algorithms perform on public face hallucination datasets. Meanwhile, most of the existing datasets do not well consider the distribution of races, which makes face hallucination methods trained on these datasets biased toward some specific races. To address the above two problems, in this paper, we build a public Ethnically Diverse Face dataset, EDFace-Celeb-1 M, and design a benchmark task for face hallucination. Our dataset includes 1.7 million photos that cover different countries, with relatively balanced race composition. To the best of our knowledge, it is the largest-scale and publicly available face hallucination dataset in the wild. Associated with this dataset, this paper also contributes various evaluation protocols and provides comprehensive analysis to benchmark the existing state-of-the-art methods. The benchmark evaluations demonstrate the performance and limitations of state-of-the-art algorithms. https://github.com/HDCVLab/EDFace-Celeb-1M.

Food is significant to human daily life. In this paper, we are interested in learning structural representations for lengthy recipes, that can benefit the recipe generation and food cross-modal retrieval tasks. Different from the common vision-language data, here the food images contain mixed ingredients and target recipes are lengthy paragraphs, where we do not have annotations on structure information. To address the above limitations, we propose a novel method to unsupervisedly learn the sentence-level tree structures for the cooking recipes. Our approach brings together several novel ideas in a systematic framework: (1) exploiting an unsupervised learning approach to obtain the sentence-level tree structure labels before training; (2) generating trees of target recipes from images with the supervision of tree structure labels learned from (1); and (3) integrating the learned tree structures into the recipe generation and food cross-modal retrieval procedure. Our proposed model can produce good-quality sentence-level tree structures and coherent recipes. We achieve the state-of-the-art recipe generation and food cross-modal retrieval performance on the benchmark Recipe1M dataset.

This paper presents a new large multiview dataset called HUMBI for human body expressions with natural clothing. The goal of HUMBI is to facilitate modeling view-specific appearance and geometry of five primary body signals including gaze, face, hand, body, and garment from assorted people. 107 synchronized HD cameras are used to capture 772 distinctive subjects across gender, ethnicity, age, and style. With the multiview image streams, we reconstruct the geometry of body expressions using 3D mesh models, which allows representing view-specific appearance. We demonstrate that HUMBI is highly effective in learning and reconstructing a complete human model and is complementary to the existing datasets of human body expressions with limited views and subjects such as MPII-Gaze, Multi-PIE, Human3.6M, and Panoptic Studio datasets. Based on HUMBI, we formulate a new benchmark challenge of a pose-guided appearance rendering task that aims to substantially extend photorealism in modeling diverse human expressions in 3D, which is the key enabling factor of authentic social tele-presence. HUMBI is publicly available at http://humbi-data.net.

Predicting human motion from historical pose sequence is crucial for a machine to succeed in intelligent interactions with humans. One aspect that has been obviated so far, is the fact that how we represent the skeletal pose has a critical impact on the prediction results. Yet there is no effort that investigates across different pose representation schemes. We conduct an indepth study on various pose representations with a focus on their effects on the motion prediction task. Moreover, recent approaches build upon off-the-shelf RNN units for motion prediction. These approaches process input pose sequence sequentially and inherently have difficulties in capturing long-term dependencies. In this paper, we propose a novel RNN architecture termed AHMR (Attentive Hierarchical Motion Recurrent network) for motion prediction which simultaneously models local motion contexts and a global context. We further explore a geodesic loss and a forward kinematics loss for the motion prediction task, which have more geometric significance than the widely employed L2 loss. Interestingly, we applied our method to a range of articulate objects including human, fish, and mouse. Empirical results show that our approach outperforms the state-of-the-art methods in short-term prediction and achieves much enhanced long-term prediction proficiency, such as retaining natural human-like motions over 50 seconds predictions. Our codes are released.

Neuromorphic vision sensor is a new bio-inspired imaging paradigm emerged in recent years. It uses the asynchronous spike signals instead of the traditional frame-based manner to achieve ultra-high speed sampling. Unlike the dynamic vision sensor (DVS) that perceives movement by imitating the retinal periphery, the spike camera was developed recently to perceive fine textures by simulating a small retinal region called the fovea. For this new type of neuromorphic camera, how to reconstruct ultra-high speed visual images from spike data becomes an important yet challenging issue in visual scene perception, analysis, and recognition applications. In this paper, a bio-inspired visual reconstruction framework for the spike camera is proposed for the first time. Its core idea is to use the biologically inspired adaptive adjustment mechanisms, combined with the spatiotemporal spike information extracted by the proposed model, to reconstruct the full texture of natural scenes in an ultra-high temporal resolution. Specifically, the proposed model consists of a motion local excitation layer, a spike refining layer and a visual reconstruction layer motivated by the bio-realistic leaky integrate-and-fire (LIF) neurons and synapse connection with spike-timing dependent plasticity (STDP) rule. To evaluate the performance, a spike dataset was constructed for normal and high-speed scenes in real-world recorded by the spike camera. The experimental results show that the proposed approach can reconstruct the visual images with 40,000 frames per second in both normal and high-speed scenes, while achieving high dynamic range and high image quality.

The classification of deformable protein shapes, based solely on their macromolecular surfaces, is a challenging problem in protein-protein interaction prediction and protein design. Shape classification is made difficult by the fact that proteins are dynamic, flexible entities with high geometrical complexity. In this paper, we introduce a novel description for such deformable shapes. This description is based on the bifractional Fokker-Planck and Dirac-Kähler equations. These equations analyse and probe protein shapes in terms of a scalar, vectorial and non-commuting quaternionic field, allowing for a more comprehensive description of the protein shapes. An underlying non-Markovian Lévy random walk establishes geometrical relationships between distant regions while recalling previous analyses. Classification is performed with a multiobjective deep hierarchical pyramidal neural network, thus performing a multilevel analysis of the description. Our approach is applied to the SHREC'19 dataset for deformable protein shapes classification and to the SHREC'16 dataset for deformable partial shapes classification, demonstrating the effectiveness and generality of our approach.