Search

In recent years, 3D parametric animal models have been developed to aid in estimating 3D shape and pose from images and video. While progress has been made for humans, it's more challenging for animals due to limited annotated data. To address this, we introduce the first method using synthetic data generation and disentanglement to learn to regress 3D shape and pose. Focusing on horses, we use text-based texture generation and a synthetic data pipeline to create varied shapes, poses, and appearances, learning disentangled spaces. Our method, Dessie, surpasses existing 3D horse reconstruction methods and generalizes to other large animals like zebras, cows, and deer. See the project website at: \url{https://celiali.github.io/Dessie/}., Comment: ACCV2024

In the monocular setting, predicting 3D pose and shape of animals typically relies solely on visual information, which is highly under-constrained. In this work, we explore using audio to enhance 3D shape and motion recovery of horses from monocular video. We test our approach on two datasets: an indoor treadmill dataset for 3D evaluation and an outdoor dataset capturing diverse horse movements, the latter being a contribution to this study. Our results show that incorporating sound with visual data leads to more accurate and robust motion regression. This study is the first to investigate audio's role in 3D animal motion recovery., Comment: CVPR CV4Animals Workshop 2024

Tabular synthesis models remain ineffective at capturing complex dependencies, and the quality of synthetic data is still insufficient for comprehensive downstream tasks, such as prediction under distribution shifts, automated decision-making, and cross-table understanding. A major challenge is the lack of prior knowledge about underlying structures and high-order relationships in tabular data. We argue that a systematic evaluation on high-order structural information for tabular data synthesis is the first step towards solving the problem. In this paper, we introduce high-order structural causal information as natural prior knowledge and provide a benchmark framework for the evaluation of tabular synthesis models. The framework allows us to generate benchmark datasets with a flexible range of data generation processes and to train tabular synthesis models using these datasets for further evaluation. We propose multiple benchmark tasks, high-order metrics, and causal inference tasks as downstream tasks for evaluating the quality of synthetic data generated by the trained models. Our experiments demonstrate to leverage the benchmark framework for evaluating the model capability of capturing high-order structural causal information. Furthermore, our benchmarking results provide an initial assessment of state-of-the-art tabular synthesis models. They have clearly revealed significant gaps between ideal and actual performance and how baseline methods differ. Our benchmark framework is available at URL https://github.com/TURuibo/CauTabBench.

The goal of Online Domain Adaptation for semantic segmentation is to handle unforeseeable domain changes that occur during deployment, like sudden weather events. However, the high computational costs associated with brute-force adaptation make this paradigm unfeasible for real-world applications. In this paper we propose HAMLET, a Hardware-Aware Modular Least Expensive Training framework for real-time domain adaptation. Our approach includes a hardware-aware back-propagation orchestration agent (HAMT) and a dedicated domain-shift detector that enables active control over when and how the model is adapted (LT). Thanks to these advancements, our approach is capable of performing semantic segmentation while simultaneously adapting at more than 29FPS on a single consumer-grade GPU. Our framework's encouraging accuracy and speed trade-off is demonstrated on OnDA and SHIFT benchmarks through experimental results., Comment: ICCV 2023. The first two authors contributed equally. Project page: https://marcbotet.github.io/hamlet-web/

In this work, we present a pipeline to reconstruct the 3D pose of a horse from 4 simultaneous surveillance camera recordings. Our environment poses interesting challenges to tackle, such as limited field view of the cameras and a relatively closed and small environment. The pipeline consists of training a 2D markerless pose estimation model to work on every viewpoint, then applying it to the videos and performing triangulation. We present numerical evaluation of the results (error analysis), as well as show the utility of the achieved poses in downstream tasks of selected behavioral predictions. Our analysis of the predictive model for equine behavior showed a bias towards pain-induced horses, which aligns with our understanding of how behavior varies across painful and healthy subjects., Comment: 3rd Workshop on CV4Animals: Computer Vision for Animal Behavior Tracking and Modeling (in conjunction with CVPR 2023) [POSTER]

Data-driven and controllable human motion synthesis and prediction are active research areas with various applications in interactive media and social robotics. Challenges remain in these fields for generating diverse motions given past observations and dealing with imperfect poses. This paper introduces MoDiff, an autoregressive probabilistic diffusion model over motion sequences conditioned on control contexts of other modalities. Our model integrates a cross-modal Transformer encoder and a Transformer-based decoder, which are found effective in capturing temporal correlations in motion and control modalities. We also introduce a new data dropout method based on the diffusion forward process to provide richer data representations and robust generation. We demonstrate the superior performance of MoDiff in controllable motion synthesis for locomotion with respect to two baselines and show the benefits of diffusion data dropout for robust synthesis and reconstruction of high-fidelity motion close to recorded data.

Replay methods are known to be successful at mitigating catastrophic forgetting in continual learning scenarios despite having limited access to historical data. However, storing historical data is cheap in many real-world settings, yet replaying all historical data is often prohibited due to processing time constraints. In such settings, we propose that continual learning systems should learn the time to learn and schedule which tasks to replay at different time steps. We first demonstrate the benefits of our proposal by using Monte Carlo tree search to find a proper replay schedule, and show that the found replay schedules can outperform fixed scheduling policies when combined with various replay methods in different continual learning settings. Additionally, we propose a framework for learning replay scheduling policies with reinforcement learning. We show that the learned policies can generalize better in new continual learning scenarios compared to equally replaying all seen tasks, without added computational cost. Our study reveals the importance of learning the time to learn in continual learning, which brings current research closer to real-world needs., Comment: Published in TMLR (2023)

Advances in animal motion tracking and pose recognition have been a game changer in the study of animal behavior. Recently, an increasing number of works go 'deeper' than tracking, and address automated recognition of animals' internal states such as emotions and pain with the aim of improving animal welfare, making this a timely moment for a systematization of the field. This paper provides a comprehensive survey of computer vision-based research on recognition of affective states and pain in animals, addressing both facial and bodily behavior analysis. We summarize the efforts that have been presented so far within this topic -- classifying them across different dimensions, highlight challenges and research gaps, and provide best practice recommendations for advancing the field, and some future directions for research.

To determine causal relationships between two variables, approaches based on Functional Causal Models (FCMs) have been proposed by properly restricting model classes; however, the performance is sensitive to the model assumptions, which makes it difficult to use. In this paper, we provide a novel dynamical-system view of FCMs and propose a new framework for identifying causal direction in the bivariate case. We first show the connection between FCMs and optimal transport, and then study optimal transport under the constraints of FCMs. Furthermore, by exploiting the dynamical interpretation of optimal transport under the FCM constraints, we determine the corresponding underlying dynamical process of the static cause-effect pair data. It provides a new dimension for describing static causal discovery tasks while enjoying more freedom for modeling the quantitative causal influences. In particular, we show that Additive Noise Models (ANMs) correspond to volume-preserving pressureless flows. Consequently, based on their velocity field divergence, we introduce a criterion for determining causal direction. With this criterion, we propose a novel optimal transport-based algorithm for ANMs which is robust to the choice of models and extend it to post-nonlinear models. Our method demonstrated state-of-the-art results on both synthetic and causal discovery benchmark datasets.

Most action recognition models today are highly parameterized, and evaluated on datasets with appearance-wise distinct classes. It has also been shown that 2D Convolutional Neural Networks (CNNs) tend to be biased toward texture rather than shape in still image recognition tasks, in contrast to humans. Taken together, this raises suspicion that large video models partly learn spurious spatial texture correlations rather than to track relevant shapes over time to infer generalizable semantics from their movement. A natural way to avoid parameter explosion when learning visual patterns over time is to make use of recurrence. Biological vision consists of abundant recurrent circuitry, and is superior to computer vision in terms of domain shift generalization. In this article, we empirically study whether the choice of low-level temporal modeling has consequences for texture bias and cross-domain robustness. In order to enable a light-weight and systematic assessment of the ability to capture temporal structure, not revealed from single frames, we provide the Temporal Shape (TS) dataset, as well as modified domains of Diving48 allowing for the investigation of spatial texture bias in video models. The combined results of our experiments indicate that sound physical inductive bias such as recurrence in temporal modeling may be advantageous when robustness to domain shift is important for the task.

Multi-task learning requires accurate identification of the correlations between tasks. In real-world time-series, tasks are rarely perfectly temporally aligned; traditional multi-task models do not account for this and subsequent errors in correlation estimation will result in poor predictive performance and uncertainty quantification. We introduce a method that automatically accounts for temporal misalignment in a unified generative model that improves predictive performance. Our method uses Gaussian processes (GPs) to model the correlations both within and between the tasks. Building on the previous work by Kazlauskaiteet al. [2019], we include a separate monotonic warp of the input data to model temporal misalignment. In contrast to previous work, we formulate a lower bound that accounts for uncertainty in both the estimates of the warping process and the underlying functions. Also, our new take on a monotonic stochastic process, with efficient path-wise sampling for the warp functions, allows us to perform full Bayesian inference in the model rather than MAP estimates. Missing data experiments, on synthetic and real time-series, demonstrate the advantages of accounting for misalignments (vs standard unaligned method) as well as modelling the uncertainty in the warping process(vs baseline MAP alignment approach).

We study approximation methods for a large class of mixed models with a probit link function that includes mixed versions of the binomial model, the multinomial model, and generalized survival models. The class of models is special because the marginal likelihood can be expressed as Gaussian weighted integrals or as multivariate Gaussian cumulative density functions. The latter approach is unique to the probit link function models and has been proposed for parameter estimation in complex, mixed effects models. However, it has not been investigated in which scenarios either form is preferable. Our simulations and data example show that neither form is preferable in general and give guidance on when to approximate the cumulative density functions and when to approximate the Gaussian weighted integrals and, in the case of the latter, which general purpose method to use among a large list of methods., Comment: 33 pages, 2 figures, and 9 tables

Timely detection of horse pain is important for equine welfare. Horses express pain through their facial and body behavior, but may hide signs of pain from unfamiliar human observers. In addition, collecting visual data with detailed annotation of horse behavior and pain state is both cumbersome and not scalable. Consequently, a pragmatic equine pain classification system would use video of the unobserved horse and weak labels. This paper proposes such a method for equine pain classification by using multi-view surveillance video footage of unobserved horses with induced orthopaedic pain, with temporally sparse video level pain labels. To ensure that pain is learned from horse body language alone, we first train a self-supervised generative model to disentangle horse pose from its appearance and background before using the disentangled horse pose latent representation for pain classification. To make best use of the pain labels, we develop a novel loss that formulates pain classification as a multi-instance learning problem. Our method achieves pain classification accuracy better than human expert performance with 60% accuracy. The learned latent horse pose representation is shown to be viewpoint covariant, and disentangled from horse appearance. Qualitative analysis of pain classified segments shows correspondence between the pain symptoms identified by our model, and equine pain scales used in veterinary practice.

Embodied conversational agents benefit from being able to accompany their speech with gestures. Although many data-driven approaches to gesture generation have been proposed in recent years, it is still unclear whether such systems can consistently generate gestures that convey meaning. We investigate which gesture properties (phase, category, and semantics) can be predicted from speech text and/or audio using contemporary deep learning. In extensive experiments, we show that gesture properties related to gesture meaning (semantics and category) are predictable from text features (time-aligned FastText embeddings) alone, but not from prosodic audio features, while rhythm-related gesture properties (phase) on the other hand can be predicted from audio features better than from text. These results are encouraging as they indicate that it is possible to equip an embodied agent with content-wise meaningful co-speech gestures using a machine-learning model., Comment: Accepted at the International Conference on Autonomous Agents and Multiagent Systems (AAMAS) 2022

We propose a new framework for gesture generation, aiming to allow data-driven approaches to produce more semantically rich gestures. Our approach first predicts whether to gesture, followed by a prediction of the gesture properties. Those properties are then used as conditioning for a modern probabilistic gesture-generation model capable of high-quality output. This empowers the approach to generate gestures that are both diverse and representational. Follow-ups and more information can be found on the project page: https://svito-zar.github.io/speech2properties2gestures/ ., Comment: Accepted for publication at the ACM International Conference on Intelligent Virtual Agents (IVA 2021)

In this paper we present our preliminary work on model-based behavioral analysis of horse motion. Our approach is based on the SMAL model, a 3D articulated statistical model of animal shape. We define a novel SMAL model for horses based on a new template, skeleton and shape space learned from $37$ horse toys. We test the accuracy of our hSMAL model in reconstructing a horse from 3D mocap data and images. We apply the hSMAL model to the problem of lameness detection from video, where we fit the model to images to recover 3D pose and train an ST-GCN network on pose data. A comparison with the same network trained on mocap points illustrates the benefit of our approach., Comment: CV4Animals Workshop in CVPR 2021

Orthopedic disorders are common among horses, often leading to euthanasia, which often could have been avoided with earlier detection. These conditions often create varying degrees of subtle long-term pain. It is challenging to train a visual pain recognition method with video data depicting such pain, since the resulting pain behavior also is subtle, sparsely appearing, and varying, making it challenging for even an expert human labeller to provide accurate ground-truth for the data. We show that a model trained solely on a dataset of horses with acute experimental pain (where labeling is less ambiguous) can aid recognition of the more subtle displays of orthopedic pain. Moreover, we present a human expert baseline for the problem, as well as an extensive empirical study of various domain transfer methods and of what is detected by the pain recognition method trained on clean experimental pain in the orthopedic dataset. Finally, this is accompanied with a discussion around the challenges posed by real-world animal behavior datasets and how best practices can be established for similar fine-grained action recognition tasks. Our code is available at https://github.com/sofiabroome/painface-recognition.

Embodied conversational agents (ECAs) benefit from non-verbal behavior for natural and efficient interaction with users. Gesticulation - hand and arm movements accompanying speech - is an essential part of non-verbal behavior. Gesture generation models have been developed for several decades: starting with rule-based and ending with mainly data-driven methods. To date, recent end-to-end gesture generation methods have not been evaluated in a real-time interaction with users. We present a proof-of-concept framework, which is intended to facilitate evaluation of modern gesture generation models in interaction. We demonstrate an extensible open-source framework that contains three components: 1) a 3D interactive agent; 2) a chatbot backend; 3) a gesticulating system. Each component can be replaced, making the proposed framework applicable for investigating the effect of different gesturing models in real-time interactions with different communication modalities, chatbot backends, or different agent appearances. The code and video are available at the project page https://nagyrajmund.github.io/project/gesturebot., Comment: Rajmund Nagy and Taras Kucherenko contributed equally to this work. To be published in the Proceedings of the 20th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2021), Online, May 3-7, 2021, IFAA-MAS, 3 pages, 1 figure

The recently developed Equine Facial Action Coding System (EquiFACS) provides a precise and exhaustive, but laborious, manual labelling method of facial action units of the horse. To automate parts of this process, we propose a Deep Learning-based method to detect EquiFACS units automatically from images. We use a cascade framework; we firstly train several object detectors to detect the predefined Region-of-Interest (ROI), and secondly apply binary classifiers for each action unit in related regions. We experiment with both regular CNNs and a more tailored model transferred from human facial action unit recognition. Promising initial results are presented for nine action units in the eye and lower face regions. Code for the project is publicly available.

Missing values with mixed data types is a common problem in a large number of machine learning applications such as processing of surveys and in different medical applications. Recently, Gaussian copula models have been suggested as a means of performing imputation of missing values using a probabilistic framework. While the present Gaussian copula models have shown to yield state of the art performance, they have two limitations: they are based on an approximation that is fast but may be imprecise and they do not support unordered multinomial variables. We address the first limitation using direct and arbitrarily precise approximations both for model estimation and imputation by using randomized quasi-Monte Carlo procedures. The method we provide has lower errors for the estimated model parameters and the imputed values, compared to previously proposed methods. We also extend the previous Gaussian copula models to include unordered multinomial variables in addition to the present support of ordinal, binary, and continuous variables., Comment: 20 pages, 1 figures, and 4 tables

Computer modeling of human decision making is of large importance for, e.g., sustainable transport, urban development, and online recommendation systems. In this paper we present a model for predicting the behavior of an individual during a binary game under different amounts of risk, gain, and time pressure. The model is based on Quantum Decision Theory (QDT), which has been shown to enable modeling of the irrational and subjective aspects of the decision making, not accounted for by the classical Cumulative Prospect Theory (CPT). Experiments on two different datasets show that our QDT-based approach outperforms both a CPT-based approach and data driven approaches such as feed-forward neural networks and random forests.

Autonomous agents, such as driverless cars, require large amounts of labeled visual data for their training. A viable approach for acquiring such data is training a generative model with collected real data, and then augmenting the collected real dataset with synthetic images from the model, generated with control of the scene layout and ground truth labeling. In this paper we propose Full-Glow, a fully conditional Glow-based architecture for generating plausible and realistic images of novel street scenes given a semantic segmentation map indicating the scene layout. Benchmark comparisons show our model to outperform recent works in terms of the semantic segmentation performance of a pretrained PSPNet. This indicates that images from our model are, to a higher degree than from other models, similar to real images of the same kinds of scenes and objects, making them suitable as training data for a visual semantic segmentation or object recognition system., Comment: Accepted to DAGM GCPR 2021

Although many fairness criteria have been proposed for decision making, their long-term impact on the well-being of a population remains unclear. In this work, we study the dynamics of population qualification and algorithmic decisions under a partially observed Markov decision problem setting. By characterizing the equilibrium of such dynamics, we analyze the long-term impact of static fairness constraints on the equality and improvement of group well-being. Our results show that static fairness constraints can either promote equality or exacerbate disparity depending on the driving factor of qualification transitions and the effect of sensitive attributes on feature distributions. We also consider possible interventions that can effectively improve group qualification or promote equality of group qualification. Our theoretical results and experiments on static real-world datasets with simulated dynamics show that our framework can be used to facilitate social science studies., Comment: Accepted to the 34th Conference on Neural Information Processing Systems (NeurIPS)

This paper presents a novel framework for speech-driven gesture production, applicable to virtual agents to enhance human-computer interaction. Specifically, we extend recent deep-learning-based, data-driven methods for speech-driven gesture generation by incorporating representation learning. Our model takes speech as input and produces gestures as output, in the form of a sequence of 3D coordinates. We provide an analysis of different representations for the input (speech) and the output (motion) of the network by both objective and subjective evaluations. We also analyse the importance of smoothing of the produced motion. Our results indicated that the proposed method improved on our baseline in terms of objective measures. For example, it better captured the motion dynamics and better matched the motion-speed distribution. Moreover, we performed user studies on two different datasets. The studies confirmed that our proposed method is perceived as more natural than the baseline, although the difference in the studies was eliminated by appropriate post-processing: hip-centering and smoothing. We conclude that it is important to take both motion representation and post-processing into account when designing an automatic gesture-production method., Comment: Extension of our IVA'19 paper. Accepted at the International Journal of Human-Computer Interaction. See more at https://svito-zar.github.io/audio2gestures/. arXiv admin note: substantial text overlap with arXiv:1903.03369

We present a method for weakly-supervised action localization based on graph convolutions. In order to find and classify video time segments that correspond to relevant action classes, a system must be able to both identify discriminative time segments in each video, and identify the full extent of each action. Achieving this with weak video level labels requires the system to use similarity and dissimilarity between moments across videos in the training data to understand both how an action appears, as well as the sub-actions that comprise the action's full extent. However, current methods do not make explicit use of similarity between video moments to inform the localization and classification predictions. We present a novel method that uses graph convolutions to explicitly model similarity between video moments. Our method utilizes similarity graphs that encode appearance and motion, and pushes the state of the art on THUMOS '14, ActivityNet 1.2, and Charades for weakly supervised action localization., Comment: Accepted at WACV 2020

A number of techniques for interpretability have been presented for deep learning in computer vision, typically with the goal of understanding what the networks have based their classification on. However, interpretability for deep video architectures is still in its infancy and we do not yet have a clear concept of how to decode spatiotemporal features. In this paper, we present a study comparing how 3D convolutional networks and convolutional LSTM networks learn features across temporally dependent frames. This is the first comparison of two video models that both convolve to learn spatial features but have principally different methods of modeling time. Additionally, we extend the concept of meaningful perturbation introduced by \cite{MeaningFulPert} to the temporal dimension, to identify the temporal part of a sequence most meaningful to the network for a classification decision. Our findings indicate that the 3D convolutional model concentrates on shorter events in the input sequence, and places its spatial focus on fewer, contiguous areas.

In this paper, we introduce a method for segmenting time series data using tools from Bayesian nonparametrics. We consider the task of temporal segmentation of a set of time series data into representative stationary segments. We use Gaussian process (GP) priors to impose our knowledge about the characteristics of the underlying stationary segments, and use a nonparametric distribution to partition the sequences into such segments, formulated in terms of a prior distribution on segment length. Given the segmentation, the model can be viewed as a variant of a Gaussian mixture model where the mixture components are described using the covariance function of a GP. We demonstrate the effectiveness of our model on synthetic data as well as on real time-series data of heartbeats where the task is to segment the indicative types of beats and to classify the heartbeat recordings into classes that correspond to healthy and abnormal heart sounds.

During speech, people spontaneously gesticulate, which plays a key role in conveying information. Similarly, realistic co-speech gestures are crucial to enable natural and smooth interactions with social agents. Current end-to-end co-speech gesture generation systems use a single modality for representing speech: either audio or text. These systems are therefore confined to producing either acoustically-linked beat gestures or semantically-linked gesticulation (e.g., raising a hand when saying "high"): they cannot appropriately learn to generate both gesture types. We present a model designed to produce arbitrary beat and semantic gestures together. Our deep-learning based model takes both acoustic and semantic representations of speech as input, and generates gestures as a sequence of joint angle rotations as output. The resulting gestures can be applied to both virtual agents and humanoid robots. Subjective and objective evaluations confirm the success of our approach. The code and video are available at the project page https://svito-zar.github.io/gesticulator ., Comment: ICMI 2020 Best Paper Award. Code is available. 9 pages, 6 figures

Scene understanding is paramount in robotics, self-navigation, augmented reality, and many other fields. To fully accomplish this task, an autonomous agent has to infer the 3D structure of the sensed scene (to know where it looks at) and its content (to know what it sees). To tackle the two tasks, deep neural networks trained to infer semantic segmentation and depth from stereo images are often the preferred choices. Specifically, Semantic Stereo Matching can be tackled by either standalone models trained for the two tasks independently or joint end-to-end architectures. Nonetheless, as proposed so far, both solutions are inefficient because requiring two forward passes in the former case or due to the complexity of a single network in the latter, although jointly tackling both tasks is usually beneficial in terms of accuracy. In this paper, we propose a single compact and lightweight architecture for real-time semantic stereo matching. Our framework relies on coarse-to-fine estimations in a multi-stage fashion, allowing: i) very fast inference even on embedded devices, with marginal drops in accuracy, compared to state-of-the-art networks, ii) trade accuracy for speed, according to the specific application requirements. Experimental results on high-end GPUs as well as on an embedded Jetson TX2 confirm the superiority of semantic stereo matching compared to standalone tasks and highlight the versatility of our framework on any hardware and for any application., Comment: 8 pages, 3 figures. Accepted to ICRA 2020

Many applications of classification methods not only require high accuracy but also reliable estimation of predictive uncertainty. However, while many current classification frameworks, in particular deep neural networks, achieve high accuracy, they tend to incorrectly estimate uncertainty. In this paper, we propose a method that adjusts the confidence estimates of a general classifier such that they approach the probability of classifying correctly. In contrast to existing approaches, our calibration method employs a non-parametric representation using a latent Gaussian process, and is specifically designed for multi-class classification. It can be applied to any classifier that outputs confidence estimates and is not limited to neural networks. We also provide a theoretical analysis regarding the over- and underconfidence of a classifier and its relationship to calibration, as well as an empirical outlook for calibrated active learning. In experiments we show the universally strong performance of our method across different classifiers and benchmark data sets, in particular for state-of-the art neural network architectures.

Discovery of causal relations from observational data is essential for many disciplines of science and real-world applications. However, unlike other machine learning algorithms, whose development has been greatly fostered by a large amount of available benchmark datasets, causal discovery algorithms are notoriously difficult to be systematically evaluated because few datasets with known ground-truth causal relations are available. In this work, we handle the problem of evaluating causal discovery algorithms by building a flexible simulator in the medical setting. We develop a neuropathic pain diagnosis simulator, inspired by the fact that the biological processes of neuropathic pathophysiology are well studied with well-understood causal influences. Our simulator exploits the causal graph of the neuropathic pain pathology and its parameters in the generator are estimated from real-life patient cases. We show that the data generated from our simulator have similar statistics as real-world data. As a clear advantage, the simulator can produce infinite samples without jeopardizing the privacy of real-world patients. Our simulator provides a natural tool for evaluating various types of causal discovery algorithms, including those to deal with practical issues in causal discovery, such as unknown confounders, selection bias, and missing data. Using our simulator, we have evaluated extensively causal discovery algorithms under various settings., Comment: Accepted by NeurIPS 2019, 6 figures, 10 tables

This paper presents a novel framework for automatic speech-driven gesture generation, applicable to human-agent interaction including both virtual agents and robots. Specifically, we extend recent deep-learning-based, data-driven methods for speech-driven gesture generation by incorporating representation learning. Our model takes speech as input and produces gestures as output, in the form of a sequence of 3D coordinates. Our approach consists of two steps. First, we learn a lower-dimensional representation of human motion using a denoising autoencoder neural network, consisting of a motion encoder MotionE and a motion decoder MotionD. The learned representation preserves the most important aspects of the human pose variation while removing less relevant variation. Second, we train a novel encoder network SpeechE to map from speech to a corresponding motion representation with reduced dimensionality. At test time, the speech encoder and the motion decoder networks are combined: SpeechE predicts motion representations based on a given speech signal and MotionD then decodes these representations to produce motion sequences. We evaluate different representation sizes in order to find the most effective dimensionality for the representation. We also evaluate the effects of using different speech features as input to the model. We find that mel-frequency cepstral coefficients (MFCCs), alone or combined with prosodic features, perform the best. The results of a subsequent user study confirm the benefits of the representation learning., Comment: Accepted at IVA '19. Shorter version published at AAMAS '19. The code is available at https://github.com/GestureGeneration/Speech_driven_gesture_generation_with_autoencoder

A prerequisite to successfully alleviate pain in animals is to recognize it, which is a great challenge in non-verbal species. Furthermore, prey animals such as horses tend to hide their pain. In this study, we propose a deep recurrent two-stream architecture for the task of distinguishing pain from non-pain in videos of horses. Different models are evaluated on a unique dataset showing horses under controlled trials with moderate pain induction, which has been presented in earlier work. Sequential models are experimentally compared to single-frame models, showing the importance of the temporal dimension of the data, and are benchmarked against a veterinary expert classification of the data. We additionally perform baseline comparisons with generalized versions of state-of-the-art human pain recognition methods. While equine pain detection in machine learning is a novel field, our results surpass veterinary expert performance and outperform pain detection results reported for other larger non-human species., Comment: CVPR 2019: IEEE Conference on Computer Vision and Pattern Recognition

Image classification models built into visual support systems and other assistive devices need to provide accurate predictions about their environment. We focus on an application of assistive technology for people with visual impairments, for daily activities such as shopping or cooking. In this paper, we provide a new benchmark dataset for a challenging task in this application - classification of fruits, vegetables, and refrigerated products, e.g. milk packages and juice cartons, in grocery stores. To enable the learning process to utilize multiple sources of structured information, this dataset not only contains a large volume of natural images but also includes the corresponding information of the product from an online shopping website. Such information encompasses the hierarchical structure of the object classes, as well as an iconic image of each type of object. This dataset can be used to train and evaluate image classification models for helping visually impaired people in natural environments. Additionally, we provide benchmark results evaluated on pretrained convolutional neural networks often used for image understanding purposes, and also a multi-view variational autoencoder, which is capable of utilizing the rich product information in the dataset., Comment: To appear in IEEE Winter Conference on Applications of Computer Vision (WACV) 2019

We present the Mixed Likelihood Gaussian process latent variable model (GP-LVM), capable of modeling data with attributes of different types. The standard formulation of GP-LVM assumes that each observation is drawn from a Gaussian distribution, which makes the model unsuited for data with e.g. categorical or nominal attributes. Our model, for which we use a sampling based variational inference, instead assumes a separate likelihood for each observed dimension. This formulation results in more meaningful latent representations, and give better predictive performance for real world data with dimensions of different types.

Human behavior is a continuous stochastic spatio-temporal process which is governed by semantic actions and affordances as well as latent factors. Therefore, video-based human activity modeling is concerned with a number of tasks such as inferring current and future semantic labels, predicting future continuous observations as well as imagining possible future label and feature sequences. In this paper we present a semi-supervised probabilistic deep latent variable model that can represent both discrete labels and continuous observations as well as latent dynamics over time. This allows the model to solve several tasks at once without explicit fine-tuning. We focus here on the tasks of action classification, detection, prediction and anticipation as well as motion prediction and synthesis based on 3D human activity data recorded with Kinect. We further extend the model to capture hierarchical label structure and to model the dependencies between multiple entities, such as a human and objects. Our experiments demonstrate that our principled approach to human activity modeling can be used to detect current and anticipate future semantic labels and to predict and synthesize future label and feature sequences. When comparing our model to state-of-the-art approaches, which are specifically designed for e.g. action classification, we find that our probabilistic formulation outperforms or is comparable to these task specific models.

Achilles Tendon Rupture (ATR) is one of the typical soft tissue injuries. Rehabilitation after such a musculoskeletal injury remains a prolonged process with a very variable outcome. Accurately predicting rehabilitation outcome is crucial for treatment decision support. However, it is challenging to train an automatic method for predicting the ATR rehabilitation outcome from treatment data, due to a massive amount of missing entries in the data recorded from ATR patients, as well as complex nonlinear relations between measurements and outcomes. In this work, we design an end-to-end probabilistic framework to impute missing data entries and predict rehabilitation outcomes simultaneously. We evaluate our model on a real-life ATR clinical cohort, comparing with various baselines. The proposed method demonstrates its clear superiority over traditional methods which typically perform imputation and prediction in two separate stages.

Missing data are ubiquitous in many domains including healthcare. When these data entries are not missing completely at random, the (conditional) independence relations in the observed data may be different from those in the complete data generated by the underlying causal process. Consequently, simply applying existing causal discovery methods to the observed data may lead to wrong conclusions. In this paper, we aim at developing a causal discovery method to recover the underlying causal structure from observed data that follow different missingness mechanisms, including missing completely at random (MCAR), missing at random (MAR), and missing not at random (MNAR). With missingness mechanisms represented by missingness graphs, we analyse conditions under which additional correction is needed to derive conditional independence/dependence relations in the complete data. Based on our analysis, we propose the Missing Value PC (MVPC) algorithm for both continuous and binary variables, which extends the PC algorithm to incorporate additional corrections. Our proposed MVPC is shown in theory to give asymptotically correct results even on data that are MAR or MNAR. Experimental results on synthetic data show that the proposed algorithm is able to find correct causal relations even in the general case of MNAR. Moreover, we create a neuropathic pain diagnostic simulator for evaluating causal discovery methods. Evaluated on such simulated neuropathic pain diagnosis records and the other two real world applications, MVPC outperforms the other benchmark methods.

Optical motion capture systems have become a widely used technology in various fields, such as augmented reality, robotics, movie production, etc. Such systems use a large number of cameras to triangulate the position of optical markers.The marker positions are estimated with high accuracy. However, especially when tracking articulated bodies, a fraction of the markers in each timestep is missing from the reconstruction. In this paper, we propose to use a neural network approach to learn how human motion is temporally and spatially correlated, and reconstruct missing markers positions through this model. We experiment with two different models, one LSTM-based and one time-window-based. Both methods produce state-of-the-art results, while working online, as opposed to most of the alternative methods, which require the complete sequence to be known. The implementation is publicly available at https://github.com/Svito-zar/NN-for-Missing-Marker-Reconstruction ., Comment: 7 pages, 6 figures

Exploring and modeling heterogeneous elastic surfaces requires multiple interactions with the environment and a complex selection of physical material parameters. The most common approaches model deformable properties from sets of offline observations using computationally expensive force-based simulators. In this work we present an online probabilistic framework for autonomous estimation of a deformability distribution map of heterogeneous elastic surfaces from few physical interactions. The method takes advantage of Gaussian Processes for constructing a model of the environment geometry surrounding a robot. A fast Position-based Dynamics simulator uses focused environmental observations in order to model the elastic behavior of portions of the environment. Gaussian Process Regression maps the local deformability on the whole environment in order to generate a deformability distribution map. We show experimental results using a PrimeSense camera, a Kinova Jaco2 robotic arm and an Optoforce sensor on different deformable surfaces., Comment: 8 pages, video of an experiment available at https://youtu.be/mDNSDZz7Qzs

Applying machine learning in the health care domain has shown promising results in recent years. Interpretable outputs from learning algorithms are desirable for decision making by health care personnel. In this work, we explore the possibility of utilizing causal relationships to refine diagnostic prediction. We focus on the task of diagnostic prediction using discomfort drawings, and explore two ways to employ causal identification to improve the diagnostic results. Firstly, we use causal identification to infer the causal relationships among diagnostic labels which, by itself, provides interpretable results to aid the decision making and training of health care personnel. Secondly, we suggest a post-processing approach where the inferred causal relationships are used to refine the prediction accuracy of a multi-view probabilistic model. Experimental results show firstly that causal identification is capable of detecting the causal relationships among diagnostic labels correctly, and secondly that there is potential for improving pain diagnostics prediction accuracy using the causal relationships., Comment: NIPS 2017 Workshop on Machine Learning for Health (ML4H)

Fluent and safe interactions of humans and robots require both partners to anticipate the others' actions. A common approach to human intention inference is to model specific trajectories towards known goals with supervised classifiers. However, these approaches do not take possible future movements into account nor do they make use of kinematic cues, such as legible and predictable motion. The bottleneck of these methods is the lack of an accurate model of general human motion. In this work, we present a conditional variational autoencoder that is trained to predict a window of future human motion given a window of past frames. Using skeletal data obtained from RGB depth images, we show how this unsupervised approach can be used for online motion prediction for up to 1660 ms. Additionally, we demonstrate online target prediction within the first 300-500 ms after motion onset without the use of target specific training data. The advantage of our probabilistic approach is the possibility to draw samples of possible future motions. Finally, we investigate how movements and kinematic cues are represented on the learned low dimensional manifold.

Generative models of 3D human motion are often restricted to a small number of activities and can therefore not generalize well to novel movements or applications. In this work we propose a deep learning framework for human motion capture data that learns a generic representation from a large corpus of motion capture data and generalizes well to new, unseen, motions. Using an encoding-decoding network that learns to predict future 3D poses from the most recent past, we extract a feature representation of human motion. Most work on deep learning for sequence prediction focuses on video and speech. Since skeletal data has a different structure, we present and evaluate different network architectures that make different assumptions about time dependencies and limb correlations. To quantify the learned features, we use the output of different layers for action classification and visualize the receptive fields of the network units. Our method outperforms the recent state of the art in skeletal motion prediction even though these use action specific training data. Our results show that deep feedforward networks, trained from a generic mocap database, can successfully be used for feature extraction from human motion data and that this representation can be used as a foundation for classification and prediction., Comment: This paper is published at the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017

Imputing incomplete medical tests and predicting patient outcomes are crucial for guiding the decision making for therapy, such as after an Achilles Tendon Rupture (ATR). We formulate the problem of data imputation and prediction for ATR relevant medical measurements into a recommender system framework. By applying MatchBox, which is a collaborative filtering approach, on a real dataset collected from 374 ATR patients, we aim at offering personalized medical data imputation and prediction. In this work, we show the feasibility of this approach and discuss potential research directions by conducting initial qualitative evaluations., Comment: Workshop on Machine Learning for Healthcare, NIPS 2016, Barcelona, Spain

Automatic forensic image analysis assists criminal investigation experts in the search for suspicious persons, abnormal behaviors detection and identity matching in images. In this paper we propose a person retrieval system that uses textual queries (e.g., "black trousers and green shirt") as descriptions and a one-class generative color model with outlier filtering to represent the images both to train the models and to perform the search. The method is evaluated in terms of its efficiency in fulfilling the needs of a forensic retrieval system: limited annotation, robustness, extensibility, adaptability and computational cost. The proposed generative method is compared to a corresponding discriminative approach. Experiments are carried out using a range of queries in three different databases. The experiments show that the two evaluated algorithms provide average retrieval performance and adaptable to new datasets. The proposed generative algorithm has some advantages over the discriminative one, specifically its capability to work with very few training samples and its much lower computational requirements when the number of training examples increases.