Search

Existing Multimodal Large Language Models (MLLMs) increasingly emphasize complex understanding of various visual elements, including multiple objects, text information, and spatial relations. Their development for comprehensive visual perception hinges on the availability of high-quality image-text datasets that offer diverse visual elements and throughout image descriptions. However, the scarcity of such hyper-detailed datasets currently hinders progress within the MLLM community. The bottleneck stems from the limited perceptual capabilities of current caption engines, which fall short in providing complete and accurate annotations. To facilitate the cutting-edge research of MLLMs on comprehensive vision perception, we thereby propose Perceptual Fusion, using a low-budget but highly effective caption engine for complete and accurate image descriptions. Specifically, Perceptual Fusion integrates diverse perception experts as image priors to provide explicit information on visual elements and adopts an efficient MLLM as a centric pivot to mimic advanced MLLMs' perception abilities. We carefully select 1M highly representative images from uncurated LAION dataset and generate dense descriptions using our engine, dubbed DenseFusion-1M. Extensive experiments validate that our engine outperforms its counterparts, where the resulting dataset significantly improves the perception and cognition abilities of existing MLLMs across diverse vision-language benchmarks, especially with high-resolution images as inputs. The dataset and code are publicly available at https://github.com/baaivision/DenseFusion.

Coding, which targets compressing and reconstructing data, and intelligence, often regarded at an abstract computational level as being centered around model learning and prediction, interweave recently to give birth to a series of significant progress. The recent trends demonstrate the potential homogeneity of these two fields, especially when deep-learning models aid these two categories for better probability modeling. For better understanding and describing from a unified perspective, inspired by the basic generally recognized principles in cognitive psychology, we formulate a novel problem of Coding for Intelligence from the category theory view. Based on the three axioms: existence of ideal coding, existence of practical coding, and compactness promoting generalization, we derive a general framework to understand existing methodologies, namely that, coding captures the intrinsic relationships of objects as much as possible, while ignoring information irrelevant to downstream tasks. This framework helps identify the challenges and essential elements in solving the specific derived Minimal Description Length (MDL) optimization problem from a broader range, providing opportunities to build a more intelligent system for handling multiple tasks/applications with coding ideas/tools. Centering on those elements, we systematically review recent processes of towards optimizing the MDL problem in more comprehensive ways from data, model, and task perspectives, and reveal their impacts on the potential CfI technical routes. After that, we also present new technique paths to fulfill CfI and provide potential solutions with preliminary experimental evidence. Last, further directions and remaining issues are discussed as well. The discussion shows our theory can reveal many phenomena and insights about large foundation models, which mutually corroborate with recent practices in feature learning.

Transfer learning has become crucial in computer vision tasks due to the vast availability of pre-trained deep learning models. However, selecting the optimal pre-trained model from a diverse pool for a specific downstream task remains a challenge. Existing methods for measuring the transferability of pre-trained models rely on statistical correlations between encoded static features and task labels, but they overlook the impact of underlying representation dynamics during fine-tuning, leading to unreliable results, especially for self-supervised models. In this paper, we present an insightful physics-inspired approach named PED to address these challenges. We reframe the challenge of model selection through the lens of potential energy and directly model the interaction forces that influence fine-tuning dynamics. By capturing the motion of dynamic representations to decline the potential energy within a force-driven physical model, we can acquire an enhanced and more stable observation for estimating transferability. The experimental results on 10 downstream tasks and 12 self-supervised models demonstrate that our approach can seamlessly integrate into existing ranking techniques and enhance their performances, revealing its effectiveness for the model selection task and its potential for understanding the mechanism in transfer learning. Code will be available at https://github.com/lixiaotong97/PED., Comment: Accepted by ICCV 2023

Though deep neural networks have achieved impressive success on various vision tasks, obvious performance degradation still exists when models are tested in out-of-distribution scenarios. In addressing this limitation, we ponder that the feature statistics (mean and standard deviation), which carry the domain characteristics of the training data, can be properly manipulated to improve the generalization ability of deep learning models. Existing methods commonly consider feature statistics as deterministic values measured from the learned features and do not explicitly model the uncertain statistics discrepancy caused by potential domain shifts during testing. In this paper, we improve the network generalization ability by modeling domain shifts with uncertainty (DSU), i.e., characterizing the feature statistics as uncertain distributions during training. Specifically, we hypothesize that the feature statistic, after considering the potential uncertainties, follows a multivariate Gaussian distribution. During inference, we propose an instance-wise adaptation strategy that can adaptively deal with the unforeseeable shift and further enhance the generalization ability of the trained model with negligible additional cost. We also conduct theoretical analysis on the aspects of generalization error bound and the implicit regularization effect, showing the efficacy of our method. Extensive experiments demonstrate that our method consistently improves the network generalization ability on multiple vision tasks, including image classification, semantic segmentation, instance retrieval, and pose estimation. Our methods are simple yet effective and can be readily integrated into networks without additional trainable parameters or loss constraints. Code will be released in https://github.com/lixiaotong97/DSU., Comment: This work is an extension of our ICLR 2022 paper [arXiv:2202.03958] https://openreview.net/forum?id=6HN7LHyzGgC

Image BERT pre-training with masked image modeling (MIM) becomes a popular practice to cope with self-supervised representation learning. A seminal work, BEiT, casts MIM as a classification task with a visual vocabulary, tokenizing the continuous visual signals into discrete vision tokens using a pre-learned dVAE. Despite a feasible solution, the improper discretization hinders further improvements of image pre-training. Since image discretization has no ground-truth answers, we believe that the masked patch should not be assigned with a unique token id even if a better tokenizer can be obtained. In this work, we introduce an improved BERT-style image pre-training method, namely mc-BEiT, which performs MIM proxy tasks towards eased and refined multi-choice training objectives. Specifically, the multi-choice supervision for the masked image patches is formed by the soft probability vectors of the discrete token ids, which are predicted by the off-the-shelf image tokenizer and further refined by high-level inter-patch perceptions resorting to the observation that similar patches should share their choices. Extensive experiments on classification, segmentation, and detection tasks demonstrate the superiority of our method, e.g., the pre-trained ViT-B achieves 84.1% top-1 fine-tuning accuracy on ImageNet-1K classification, 49.2% AP^b and 44.0% AP^m of object detection and instance segmentation on COCO, 50.8% mIOU on ADE20K semantic segmentation, outperforming the competitive counterparts. The code will be available at https://github.com/lixiaotong97/mc-BEiT., Comment: Accepted by ECCV 2022

Federated Learning (FL) is an emerging distributed learning paradigm under privacy constraint. Data heterogeneity is one of the main challenges in FL, which results in slow convergence and degraded performance. Most existing approaches only tackle the heterogeneity challenge by restricting the local model update in client, ignoring the performance drop caused by direct global model aggregation. Instead, we propose a data-free knowledge distillation method to fine-tune the global model in the server (FedFTG), which relieves the issue of direct model aggregation. Concretely, FedFTG explores the input space of local models through a generator, and uses it to transfer the knowledge from local models to the global model. Besides, we propose a hard sample mining scheme to achieve effective knowledge distillation throughout the training. In addition, we develop customized label sampling and class-level ensemble to derive maximum utilization of knowledge, which implicitly mitigates the distribution discrepancy across clients. Extensive experiments show that our FedFTG significantly outperforms the state-of-the-art (SOTA) FL algorithms and can serve as a strong plugin for enhancing FedAvg, FedProx, FedDyn, and SCAFFOLD., Comment: This paper is accepted by CVPR2022

Cross-domain person re-identification (re-ID), such as unsupervised domain adaptive (UDA) re-ID, aims to transfer the identity-discriminative knowledge from the source to the target domain. Existing methods commonly consider the source and target domains are isolated from each other, i.e., no intermediate status is modeled between both domains. Directly transferring the knowledge between two isolated domains can be very difficult, especially when the domain gap is large. From a novel perspective, we assume these two domains are not completely isolated, but can be connected through intermediate domains. Instead of directly aligning the source and target domains against each other, we propose to align the source and target domains against their intermediate domains for a smooth knowledge transfer. To discover and utilize these intermediate domains, we propose an Intermediate Domain Module (IDM) and a Mirrors Generation Module (MGM). IDM has two functions: 1) it generates multiple intermediate domains by mixing the hidden-layer features from source and target domains and 2) it dynamically reduces the domain gap between the source / target domain features and the intermediate domain features. While IDM achieves good domain alignment, it introduces a side effect, i.e., the mix-up operation may mix the identities into a new identity and lose the original identities. To compensate this, MGM is introduced by mapping the features into the IDM-generated intermediate domains without changing their original identity. It allows to focus on minimizing domain variations to promote the alignment between the source / target domain and intermediate domains, which reinforces IDM into IDM++. We extensively evaluate our method under both the UDA and domain generalization (DG) scenarios and observe that IDM++ yields consistent performance improvement for cross-domain re-ID, achieving new state of the art., Comment: This work is a journal extension of our ICCV 2021 Oral paper https://openaccess.thecvf.com/content/ICCV2021/html/Dai_IDM_An_Intermediate_Domain_Module_for_Domain_Adaptive_Person_Re-ID_ICCV_2021_paper.html

Though remarkable progress has been achieved in various vision tasks, deep neural networks still suffer obvious performance degradation when tested in out-of-distribution scenarios. We argue that the feature statistics (mean and standard deviation), which carry the domain characteristics of the training data, can be properly manipulated to improve the generalization ability of deep learning models. Common methods often consider the feature statistics as deterministic values measured from the learned features and do not explicitly consider the uncertain statistics discrepancy caused by potential domain shifts during testing. In this paper, we improve the network generalization ability by modeling the uncertainty of domain shifts with synthesized feature statistics during training. Specifically, we hypothesize that the feature statistic, after considering the potential uncertainties, follows a multivariate Gaussian distribution. Hence, each feature statistic is no longer a deterministic value, but a probabilistic point with diverse distribution possibilities. With the uncertain feature statistics, the models can be trained to alleviate the domain perturbations and achieve better robustness against potential domain shifts. Our method can be readily integrated into networks without additional parameters. Extensive experiments demonstrate that our proposed method consistently improves the network generalization ability on multiple vision tasks, including image classification, semantic segmentation, and instance retrieval. The code can be available at https://github.com/lixiaotong97/DSU., Comment: Accepted by ICLR 2022

In this paper, we make the first benchmark effort to elaborate on the superiority of using RAW images in the low light enhancement and develop a novel alternative route to utilize RAW images in a more flexible and practical way. Inspired by a full consideration on the typical image processing pipeline, we are inspired to develop a new evaluation framework, Factorized Enhancement Model (FEM), which decomposes the properties of RAW images into measurable factors and provides a tool for exploring how properties of RAW images affect the enhancement performance empirically. The empirical benchmark results show that the Linearity of data and Exposure Time recorded in meta-data play the most critical role, which brings distinct performance gains in various measures over the approaches taking the sRGB images as input. With the insights obtained from the benchmark results in mind, a RAW-guiding Exposure Enhancement Network (REENet) is developed, which makes trade-offs between the advantages and inaccessibility of RAW images in real applications in a way of using RAW images only in the training phase. REENet projects sRGB images into linear RAW domains to apply constraints with corresponding RAW images to reduce the difficulty of modeling training. After that, in the testing phase, our REENet does not rely on RAW images. Experimental results demonstrate not only the superiority of REENet to state-of-the-art sRGB-based methods and but also the effectiveness of the RAW guidance and all components.

Video Coding for Machines (VCM) is committed to bridging to an extent separate research tracks of video/image compression and feature compression, and attempts to optimize compactness and efficiency jointly from a unified perspective of high accuracy machine vision and full fidelity human vision. In this paper, we summarize VCM methodology and philosophy based on existing academia and industrial efforts. The development of VCM follows a general rate-distortion optimization, and the categorization of key modules or techniques is established. From previous works, it is demonstrated that, although existing works attempt to reveal the nature of scalable representation in bits when dealing with machine and human vision tasks, there remains a rare study in the generality of low bit rate representation, and accordingly how to support a variety of visual analytic tasks. Therefore, we investigate a novel visual information compression for the analytics taxonomy problem to strengthen the capability of compact visual representations extracted from multiple tasks for visual analytics. A new perspective of task relationships versus compression is revisited. By keeping in mind the transferability among different machine vision tasks (e.g. high-level semantic and mid-level geometry-related), we aim to support multiple tasks jointly at low bit rates. In particular, to narrow the dimensionality gap between neural network generated features extracted from pixels and a variety of machine vision features/labels (e.g. scene class, segmentation labels), a codebook hyperprior is designed to compress the neural network-generated features. As demonstrated in our experiments, this new hyperprior model is expected to improve feature compression efficiency by estimating the signal entropy more accurately, which enables further investigation of the granularity of abstracting compact features among different tasks., Comment: The first three authors had equal contribution. arXiv admin note: text overlap with arXiv:2106.08512

Visual retrieval system faces frequent model update and deployment. It is a heavy workload to re-extract features of the whole database every time.Feature compatibility enables the learned new visual features to be directly compared with the old features stored in the database. In this way, when updating the deployed model, we can bypass the inflexible and time-consuming feature re-extraction process. However, the old feature space that needs to be compatible is not ideal and faces the distribution discrepancy problem with the new space caused by different supervision losses. In this work, we propose a global optimization Dual-Tuning method to obtain feature compatibility against different networks and losses. A feature-level prototype loss is proposed to explicitly align two types of embedding features, by transferring global prototype information. Furthermore, we design a component-level mutual structural regularization to implicitly optimize the feature intrinsic structure. Experimental results on million-scale datasets demonstrate that our Dual-Tuning is able to obtain feature compatibility without sacrificing performance. (Our code will be avaliable at https://github.com/yanbai1993/Dual-Tuning)

Unsupervised domain adaptive person re-identification (UDA re-ID) aims at transferring the labeled source domain's knowledge to improve the model's discriminability on the unlabeled target domain. From a novel perspective, we argue that the bridging between the source and target domains can be utilized to tackle the UDA re-ID task, and we focus on explicitly modeling appropriate intermediate domains to characterize this bridging. Specifically, we propose an Intermediate Domain Module (IDM) to generate intermediate domains' representations on-the-fly by mixing the source and target domains' hidden representations using two domain factors. Based on the "shortest geodesic path" definition, i.e., the intermediate domains along the shortest geodesic path between the two extreme domains can play a better bridging role, we propose two properties that these intermediate domains should satisfy. To ensure these two properties to better characterize appropriate intermediate domains, we enforce the bridge losses on intermediate domains' prediction space and feature space, and enforce a diversity loss on the two domain factors. The bridge losses aim at guiding the distribution of appropriate intermediate domains to keep the right distance to the source and target domains. The diversity loss serves as a regularization to prevent the generated intermediate domains from being over-fitting to either of the source and target domains. Our proposed method outperforms the state-of-the-arts by a large margin in all the common UDA re-ID tasks, and the mAP gain is up to 7.7% on the challenging MSMT17 benchmark. Code is available at https://github.com/SikaStar/IDM., Comment: Accepted by ICCV 2021 (Oral)

Domain generalizable (DG) person re-identification (ReID) is a challenging problem because we cannot access any unseen target domain data during training. Almost all the existing DG ReID methods follow the same pipeline where they use a hybrid dataset from multiple source domains for training, and then directly apply the trained model to the unseen target domains for testing. These methods often neglect individual source domains' discriminative characteristics and their relevances w.r.t. the unseen target domains, though both of which can be leveraged to help the model's generalization. To handle the above two issues, we propose a novel method called the relevance-aware mixture of experts (RaMoE), using an effective voting-based mixture mechanism to dynamically leverage source domains' diverse characteristics to improve the model's generalization. Specifically, we propose a decorrelation loss to make the source domain networks (experts) keep the diversity and discriminability of individual domains' characteristics. Besides, we design a voting network to adaptively integrate all the experts' features into the more generalizable aggregated features with domain relevance. Considering the target domains' invisibility during training, we propose a novel learning-to-learn algorithm combined with our relation alignment loss to update the voting network. Extensive experiments demonstrate that our proposed RaMoE outperforms the state-of-the-art methods., Comment: Accepted to CVPR 2021

Unsupervised domain adaptive (UDA) person re-identification (re-ID) is a challenging task due to the missing of labels for the target domain data. To handle this problem, some recent works adopt clustering algorithms to off-line generate pseudo labels, which can then be used as the supervision signal for on-line feature learning in the target domain. However, the off-line generated labels often contain lots of noise that significantly hinders the discriminability of the on-line learned features, and thus limits the final UDA re-ID performance. To this end, we propose a novel approach, called Dual-Refinement, that jointly refines pseudo labels at the off-line clustering phase and features at the on-line training phase, to alternatively boost the label purity and feature discriminability in the target domain for more reliable re-ID. Specifically, at the off-line phase, a new hierarchical clustering scheme is proposed, which selects representative prototypes for every coarse cluster. Thus, labels can be effectively refined by using the inherent hierarchical information of person images. Besides, at the on-line phase, we propose an instant memory spread-out (IM-spread-out) regularization, that takes advantage of the proposed instant memory bank to store sample features of the entire dataset and enable spread-out feature learning over the entire training data instantly. Our Dual-Refinement method reduces the influence of noisy labels and refines the learned features within the alternative training process. Experiments demonstrate that our method outperforms the state-of-the-art methods by a large margin., Comment: 14 pages, 5 figures

Video coding, which targets to compress and reconstruct the whole frame, and feature compression, which only preserves and transmits the most critical information, stand at two ends of the scale. That is, one is with compactness and efficiency to serve for machine vision, and the other is with full fidelity, bowing to human perception. The recent endeavors in imminent trends of video compression, e.g. deep learning based coding tools and end-to-end image/video coding, and MPEG-7 compact feature descriptor standards, i.e. Compact Descriptors for Visual Search and Compact Descriptors for Video Analysis, promote the sustainable and fast development in their own directions, respectively. In this paper, thanks to booming AI technology, e.g. prediction and generation models, we carry out exploration in the new area, Video Coding for Machines (VCM), arising from the emerging MPEG standardization efforts1. Towards collaborative compression and intelligent analytics, VCM attempts to bridge the gap between feature coding for machine vision and video coding for human vision. Aligning with the rising Analyze then Compress instance Digital Retina, the definition, formulation, and paradigm of VCM are given first. Meanwhile, we systematically review state-of-the-art techniques in video compression and feature compression from the unique perspective of MPEG standardization, which provides the academic and industrial evidence to realize the collaborative compression of video and feature streams in a broad range of AI applications. Finally, we come up with potential VCM solutions, and the preliminary results have demonstrated the performance and efficiency gains. Further direction is discussed as well.

In this paper, we study a new problem arising from the emerging MPEG standardization effort Video Coding for Machine (VCM), which aims to bridge the gap between visual feature compression and classical video coding. VCM is committed to address the requirement of compact signal representation for both machine and human vision in a more or less scalable way. To this end, we make endeavors in leveraging the strength of predictive and generative models to support advanced compression techniques for both machine and human vision tasks simultaneously, in which visual features serve as a bridge to connect signal-level and task-level compact representations in a scalable manner. Specifically, we employ a conditional deep generation network to reconstruct video frames with the guidance of learned motion pattern. By learning to extract sparse motion pattern via a predictive model, the network elegantly leverages the feature representation to generate the appearance of to-be-coded frames via a generative model, relying on the appearance of the coded key frames. Meanwhile, the sparse motion pattern is compact and highly effective for high-level vision tasks, e.g. action recognition. Experimental results demonstrate that our method yields much better reconstruction quality compared with the traditional video codecs (0.0063 gain in SSIM), as well as state-of-the-art action recognition performance over highly compressed videos (9.4% gain in recognition accuracy), which showcases a promising paradigm of coding signal for both human and machine vision.

The past decades have witnessed the rapid development of image and video coding techniques in the era of big data. However, the signal fidelity-driven coding pipeline design limits the capability of the existing image/video coding frameworks to fulfill the needs of both machine and human vision. In this paper, we come up with a novel image coding framework by leveraging both the compressive and the generative models, to support machine vision and human perception tasks jointly. Given an input image, the feature analysis is first applied, and then the generative model is employed to perform image reconstruction with features and additional reference pixels, in which compact edge maps are extracted in this work to connect both kinds of vision in a scalable way. The compact edge map serves as the basic layer for machine vision tasks, and the reference pixels act as a sort of enhanced layer to guarantee signal fidelity for human vision. By introducing advanced generative models, we train a flexible network to reconstruct images from compact feature representations and the reference pixels. Experimental results demonstrate the superiority of our framework in both human visual quality and facial landmark detection, which provide useful evidence on the emerging standardization efforts on MPEG VCM (Video Coding for Machine)., Comment: Project page: https://williamyang1991.github.io/projects/VCM-Face/

The digital retina in smart cities is to select what the City Eye tells the City Brain, and convert the acquired visual data from front-end visual sensors to features in an intelligent sensing manner. By deploying deep learning and/or handcrafted models in front-end devices, the compact features can be extracted and subsequently delivered to back-end cloud for search and advanced analytics. In this context, we propose a model generation, utilization, and communication paradigm, aiming to address a set of unique challenges for better artificial intelligence services in smart cities. In particular, we present an integrated multiple deep learning models reuse and prediction strategy, which greatly increases the feasibility of the digital retina in processing and analyzing the large-scale visual data in smart cities. The promise of the proposed paradigm is demonstrated through a set of experiments., Comment: 6 pages, 6 figures

Research on depth-based human activity analysis achieved outstanding performance and demonstrated the effectiveness of 3D representation for action recognition. The existing depth-based and RGB+D-based action recognition benchmarks have a number of limitations, including the lack of large-scale training samples, realistic number of distinct class categories, diversity in camera views, varied environmental conditions, and variety of human subjects. In this work, we introduce a large-scale dataset for RGB+D human action recognition, which is collected from 106 distinct subjects and contains more than 114 thousand video samples and 8 million frames. This dataset contains 120 different action classes including daily, mutual, and health-related activities. We evaluate the performance of a series of existing 3D activity analysis methods on this dataset, and show the advantage of applying deep learning methods for 3D-based human action recognition. Furthermore, we investigate a novel one-shot 3D activity recognition problem on our dataset, and a simple yet effective Action-Part Semantic Relevance-aware (APSR) framework is proposed for this task, which yields promising results for recognition of the novel action classes. We believe the introduction of this large-scale dataset will enable the community to apply, adapt, and develop various data-hungry learning techniques for depth-based and RGB+D-based human activity understanding. [The dataset is available at: http://rose1.ntu.edu.sg/Datasets/actionRecognition.asp], Comment: IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)

This paper solves the Sparse Photometric stereo through Lighting Interpolation and Normal Estimation using a generative Network (SPLINE-Net). SPLINE-Net contains a lighting interpolation network to generate dense lighting observations given a sparse set of lights as inputs followed by a normal estimation network to estimate surface normals. Both networks are jointly constrained by the proposed symmetric and asymmetric loss functions to enforce isotropic constrain and perform outlier rejection of global illumination effects. SPLINE-Net is verified to outperform existing methods for photometric stereo of general BRDFs by using only ten images of different lights instead of using nearly one hundred images., Comment: Accepted to ICCV 2019

Face images captured through the glass are usually contaminated by reflections. The non-transmitted reflections make the reflection removal more challenging than for general scenes, because important facial features are completely occluded. In this paper, we propose and solve the face image reflection removal problem. We remove non-transmitted reflections by incorporating inpainting ideas into a guided reflection removal framework and recover facial features by considering various face-specific priors. We use a newly collected face reflection image dataset to train our model and compare with state-of-the-art methods. The proposed method shows advantages in estimating reflection-free face images for improving face recognition.

Action prediction is to recognize the class label of an ongoing activity when only a part of it is observed. In this paper, we focus on online action prediction in streaming 3D skeleton sequences. A dilated convolutional network is introduced to model the motion dynamics in temporal dimension via a sliding window over the temporal axis. Since there are significant temporal scale variations in the observed part of the ongoing action at different time steps, a novel window scale selection method is proposed to make our network focus on the performed part of the ongoing action and try to suppress the possible incoming interference from the previous actions at each step. An activation sharing scheme is also proposed to handle the overlapping computations among the adjacent time steps, which enables our framework to run more efficiently. Moreover, to enhance the performance of our framework for action prediction with the skeletal input data, a hierarchy of dilated tree convolutions are also designed to learn the multi-level structured semantic representations over the skeleton joints at each frame. Our proposed approach is evaluated on four challenging datasets. The extensive experiments demonstrate the effectiveness of our method for skeleton-based online action prediction., Comment: This paper has been accepted by T-PAMI. DOI: 10.1109/TPAMI.2019.2898954

In this paper, a feature boosting network is proposed for estimating 3D hand pose and 3D body pose from a single RGB image. In this method, the features learned by the convolutional layers are boosted with a new long short-term dependence-aware (LSTD) module, which enables the intermediate convolutional feature maps to perceive the graphical long short-term dependency among different hand (or body) parts using the designed Graphical ConvLSTM. Learning a set of features that are reliable and discriminatively representative of the pose of a hand (or body) part is difficult due to the ambiguities, texture and illumination variation, and self-occlusion in the real application of 3D pose estimation. To improve the reliability of the features for representing each body part and enhance the LSTD module, we further introduce a context consistency gate (CCG) in this paper, with which the convolutional feature maps are modulated according to their consistency with the context representations. We evaluate the proposed method on challenging benchmark datasets for 3D hand pose estimation and 3D full body pose estimation. Experimental results show the effectiveness of our method that achieves state-of-the-art performance on both of the tasks., Comment: Accepted to T-PAMI. DOI: 10.1109/TPAMI.2019.2894422

Removing the undesired reflections from images taken through the glass is of broad application to various computer vision tasks. Non-learning based methods utilize different handcrafted priors such as the separable sparse gradients caused by different levels of blurs, which often fail due to their limited description capability to the properties of real-world reflections. In this paper, we propose the Concurrent Reflection Removal Network (CRRN) to tackle this problem in a unified framework. Our proposed network integrates image appearance information and multi-scale gradient information with human perception inspired loss function, and is trained on a new dataset with 3250 reflection images taken under diverse real-world scenes. Extensive experiments on a public benchmark dataset show that the proposed method performs favorably against state-of-the-art methods., Comment: Accepted by CVPR 2018

Human action recognition in 3D skeleton sequences has attracted a lot of research attention. Recently, Long Short-Term Memory (LSTM) networks have shown promising performance in this task due to their strengths in modeling the dependencies and dynamics in sequential data. As not all skeletal joints are informative for action recognition, and the irrelevant joints often bring noise which can degrade the performance, we need to pay more attention to the informative ones. However, the original LSTM network does not have explicit attention ability. In this paper, we propose a new class of LSTM network, Global Context-Aware Attention LSTM (GCA-LSTM), for skeleton based action recognition. This network is capable of selectively focusing on the informative joints in each frame of each skeleton sequence by using a global context memory cell. To further improve the attention capability of our network, we also introduce a recurrent attention mechanism, with which the attention performance of the network can be enhanced progressively. Moreover, we propose a stepwise training scheme in order to train our network effectively. Our approach achieves state-of-the-art performance on five challenging benchmark datasets for skeleton based action recognition.

This paper provides an overview of the on-going compact descriptors for video analysis standard (CDVA) from the ISO/IEC moving pictures experts group (MPEG). MPEG-CDVA targets at defining a standardized bitstream syntax to enable interoperability in the context of video analysis applications. During the developments of MPEGCDVA, a series of techniques aiming to reduce the descriptor size and improve the video representation ability have been proposed. This article describes the new standard that is being developed and reports the performance of these key technical contributions., Comment: 4 figures, 4 tables

Object detection aims to identify instances of semantic objects of a certain class in images or videos. The success of state-of-the-art approaches is attributed to the significant progress of object proposal and convolutional neural networks (CNNs). Most promising detectors involve multi-task learning with an optimization objective of softmax loss and regression loss. The first is for multi-class categorization, while the latter is for improving localization accuracy. However, few of them attempt to further investigate the hardness of distinguishing different sorts of distracting background regions (i.e., negatives) from true object regions (i.e., positives). To improve the performance of classifying positive object regions vs. a variety of negative background regions, we propose to incorporate triplet embedding into learning objective. The triplet units are formed by assigning each negative region to a meaningful object class and establishing class- specific negatives, followed by triplets construction. Over the benchmark PASCAL VOC 2007, the proposed triplet em- bedding has improved the performance of well-known FastRCNN model with a mAP gain of 2.1%. In particular, the state-of-the-art approach OHEM can benefit from the triplet embedding and has achieved a mAP improvement of 1.2%., Comment: 6 pages, 5 figures

Fine-grained visual recognition aims to capture discriminative characteristics amongst visually similar categories. The state-of-the-art research work has significantly improved the fine-grained recognition performance by deep metric learning using triplet network. However, the impact of intra-category variance on the performance of recognition and robust feature representation has not been well studied. In this paper, we propose to leverage intra-class variance in metric learning of triplet network to improve the performance of fine-grained recognition. Through partitioning training images within each category into a few groups, we form the triplet samples across different categories as well as different groups, which is called Group Sensitive TRiplet Sampling (GS-TRS). Accordingly, the triplet loss function is strengthened by incorporating intra-class variance with GS-TRS, which may contribute to the optimization objective of triplet network. Extensive experiments over benchmark datasets CompCar and VehicleID show that the proposed GS-TRS has significantly outperformed state-of-the-art approaches in both classification and retrieval tasks., Comment: 6 pages, 5 figures