3D hand pose is an underexplored modality for action recognition. Poses are compact yet informative and can greatly benefit applications with limited compute budgets. However, poses alone offer an incomplete understanding of actions, as they cannot fully capture objects and environments with which humans interact. We propose HandFormer, a novel multimodal transformer, to efficiently model hand-object interactions. HandFormer combines 3D hand poses at a high temporal resolution for fine-grained motion modeling with sparsely sampled RGB frames for encoding scene semantics. Observing the unique characteristics of hand poses, we temporally factorize hand modeling and represent each joint by its short-term trajectories. This factorized pose representation combined with sparse RGB samples is remarkably efficient and highly accurate. Unimodal HandFormer with only hand poses outperforms existing skeleton-based methods at 5x fewer FLOPs. With RGB, we achieve new state-of-the-art performance on Assembly101 and H2O with significant improvements in egocentric action recognition.
Sri Lanka Institute of Information Technology（斯里兰卡信息技术学院）；University of Sheffield（谢菲尔德大学）
We present a graph convolutional network with 2D pose estimation for the first time on child action recognition task achieving on par results with an RGB modality based model on a novel benchmark dataset containing unconstrained environment based videos.
Recognizing human actions is a core challenge for autonomous systems as they directly share the same space with humans. Systems must be able to recognize and assess human actions in real-time. In order to train corresponding data-driven algorithms, a significant amount of annotated training data is required. We demonstrated a pipeline to detect humans, estimate their pose, track them over time and recognize their actions in real-time with standard monocular camera sensors. For action recognition, we encode the human pose into a new data format called Encoded Human Pose Image (EHPI) that can th…
Most state-of-the-art methods for action recognition rely only on 2D spatial features encoding appearance, motion or pose. However, 2D data lacks the depth information, which is crucial for recognizing fine-grained actions. In this paper, we propose a depth-aware volumetric descriptor that encodes pose and motion information in a unified representation for action classification in-the-wild. Our framework is robust to many challenges inherent to action recognition, e.g. variation in viewpoint, scene, clothing and body shape. The key component of our method is the Depth-Aware Pose Motion represe…
This paper presents a novel method for learning a pose lexicon comprising semantic poses defined by textual instructions and their associated visual poses defined by visual features. The proposed method simultaneously takes two input streams, semantic poses and visual pose candidates, and statistically learns a mapping between them to construct the lexicon. With the learned lexicon, action recognition can be cast as the problem of finding the maximum translation probability of a sequence of semantic poses given a stream of visual pose candidates. Experiments evaluating pre-trained and zero-sho…
Politecnico di Torino（都灵理工大学）；PIC4SeR, Politecnico di Torino Interdepartmental Centre for Service Robotics（都灵理工大学跨部门服务机器人中心 PIC4SeR）；Newcastle University（纽卡斯尔大学）
Deep neural networks based purely on attention have been successful across several domains, relying on minimal architectural priors from the designer. In Human Action Recognition (HAR), attention mechanisms have been primarily adopted on top of standard convolutional or recurrent layers, improving the overall generalization capability. In this work, we introduce Action Transformer (AcT), a simple, fully self-attentional architecture that consistently outperforms more elaborated networks that mix convolutional, recurrent and attentive layers. In order to limit computational and energy requests,…
This work targets human action recognition in video. While recent methods typically represent actions by statistics of local video features, here we argue for the importance of a representation derived from human pose. To this end we propose a new Pose-based Convolutional Neural Network descriptor (P-CNN) for action recognition. The descriptor aggregates motion and appearance information along tracks of human body parts. We investigate different schemes of temporal aggregation and experiment with P-CNN features obtained both for automatically estimated and manually annotated human poses. We ev…
Tsinghua University（清华大学）；University of Waterloo（滑铁卢大学）
Recognizing actions in ice hockey using computer vision poses challenges due to bulky equipment and inadequate image quality. A novel two-stream framework has been designed to improve action recognition accuracy for hockey using three main components. First, pose is estimated via the Part Affinity Fields model to extract meaningful cues from the player. Second, optical flow (using LiteFlowNet) is used to extract temporal features. Third, pose and optical flow streams are fused and passed to fully-connected layers to estimate the hockey player's action. A novel publicly available dataset named …
Human pose is a useful feature for fine-grained sports action understanding. However, pose estimators are often unreliable when run on sports video due to domain shift and factors such as motion blur and occlusions. This leads to poor accuracy when downstream tasks, such as action recognition, depend on pose. End-to-end learning circumvents pose, but requires more labels to generalize. We introduce Video Pose Distillation (VPD), a weakly-supervised technique to learn features for new video domains, such as individual sports that challenge pose estimation. Under VPD, a student network learns to…
How does one represent an action? How does one describe an action that we have never seen before? Such questions are addressed by the Zero Shot Learning paradigm, where a model is trained on only a subset of classes and is evaluated on its ability to correctly classify an example from a class it has never seen before. In this work, we present a body pose based zero shot action recognition network and demonstrate its performance on the NTU RGB-D dataset. Our model learns to jointly encapsulate visual similarities based on pose features of the action performer as well as similarities in the natu…
Center for Research on Intelligent Perception and Computing（智能感知与计算研究中心）；National Laboratory of Pattern Recognition（模式识别国家重点实验室）；Center for Excellence in Brain Science and Intelligence Technology（脑科学与智能技术卓越创新中心）；Institute of Automation Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）
Recently, pose-based action recognition has gained more and more attention due to the better performance compared with traditional appearance-based methods. However, there still exist two problems to be further solved. First, existing pose-based methods generally recognize human actions with captured 3D human poses which are very difficult to obtain in real scenarios. Second, few pose-based methods model the action-related objects in recognizing human-object interaction actions in which objects play an important role. To solve the problems above, we propose a pose-based two-stream relational n…
Cerema Research Center（Cerema研究中心）；Aparnix；Cortexica Vision Systems Ltd.（Cortexica视觉系统有限公司）；Vingroup Big Data Institute (VinBDI)（Vingroup大数据研究所（VinBDI））
We present a deep learning-based multitask framework for joint 3D human pose estimation and action recognition from RGB video sequences. Our approach proceeds along two stages. In the first, we run a real-time 2D pose detector to determine the precise pixel location of important keypoints of the body. A two-stream neural network is then designed and trained to map detected 2D keypoints into 3D poses. In the second, we deploy the Efficient Neural Architecture Search (ENAS) algorithm to find an optimal network architecture that is used for modeling the spatio-temporal evolution of the estimated …
Bioinformatics Institute, A*STAR（新加坡科技研究局生物信息学研究所）
Pose estimation, tracking, and action recognition of articulated objects from depth images are important and challenging problems, which are normally considered separately. In this paper, a unified paradigm based on Lie group theory is proposed, which enables us to collectively address these related problems. Our approach is also applicable to a wide range of articulated objects. Empirically it is evaluated on lab animals including mouse and fish, as well as on human hand. On these applications, it is shown to deliver competitive results compared to the state-of-the-arts, and non-trivial basel…
Grounding Foundational Vision Models with 3D Human Poses for Robust Action Recognition
Arizona State University（亚利桑那州立大学）；Emory University（埃默里大学）；University of California, Berkeley（加州大学伯克利分校）；Delft University of Technology（代尔夫特理工大学）；Algoverse AI Research（Algoverse AI 研究）
ETIS UMR 8051（ETIS联合研究单位8051）；Paris Seine University（巴黎塞纳大学）；ENSEA（法国国立高等电子及应用学院）；CNRS（法国国家科学研究中心）；Sorbonne Université（索邦大学）；Laboratoire d’Informatique de Paris 6, LIP6（巴黎第六大学计算机实验室）
Action recognition and human pose estimation are closely related but both problems are generally handled as distinct tasks in the literature. In this work, we propose a multitask framework for jointly 2D and 3D pose estimation from still images and human action recognition from video sequences. We show that a single architecture can be used to solve the two problems in an efficient way and still achieves state-of-the-art results. Additionally, we demonstrate that optimization from end-to-end leads to significantly higher accuracy than separated learning. The proposed architecture can be traine…
Prediction with high accuracy is essential for various applications such as autonomous driving. Existing prediction models are easily prone to errors in real-world settings where observations (e.g. human poses and locations) are often noisy. To address this problem, we introduce GPRAR, a graph convolutional network based pose reconstruction and action recognition for human trajectory prediction. The key idea of GPRAR is to generate robust features: human poses and actions, under noisy scenarios. To this end, we design GPRAR using two novel sub-networks: PRAR (Pose Reconstruction and Action Rec…
Human Action Recognition is an important task of Human Robot Interaction as cooperation between robots and humans requires that artificial agents recognise complex cues from the environment. A promising approach is using trained classifiers to recognise human actions through sequences of skeleton poses extracted from images or RGB-D data from a sensor. However, with many different data-sets focused on slightly different sets of actions and different algorithms it is not clear which strategy produces highest accuracy for indoor activities performed in a home environment. This work discussed, te…
Classifying the behavior of humans or animals from videos is important in biomedical fields for understanding brain function and response to stimuli. Action recognition, classifying activities performed by one or more subjects in a trimmed video, forms the basis of many of these techniques. Deep learning models for human action recognition have progressed significantly over the last decade. Recently, there is an increased interest in research that incorporates deep learning-based action recognition for animal behavior classification. However, human action recognition methods are more developed…
Privacy-Preserving Action Recognition: Taxonomy, Methods, and Privacy-Utility Trade-offs
Chung-Ang University（中央大学）；Ulsan National Institute of Science and Technology (UNIST)（蔚山科学技术院）；College of Art and Technology, Chung-Ang University（中央大学艺术与技术学院）
Most current action recognition methods heavily rely on appearance information by taking an RGB sequence of entire image regions as input. While being effective in exploiting contextual information around humans, e.g., human appearance and scene category, they are easily fooled by out-of-context action videos where the contexts do not exactly match with target actions. In contrast, pose-based methods, which take a sequence of human skeletons only as input, suffer from inaccurate pose estimation or ambiguity of human pose per se. Integrating these two approaches has turned out to be non-trivial…
North University of China（中北大学）；Shandong University（山东大学）；University of Electronic Science and Technology of China（电子科技大学）；University of Wollongong（伍伦贡大学）
Pose based hand gesture recognition has been widely studied in the recent years. Compared with full body action recognition, hand gesture involves joints that are more spatially closely distributed with stronger collaboration. This nature requires a different approach from action recognition to capturing the complex spatial features. Many gesture categories, such as "Grab" and "Pinch", have very similar motion or temporal patterns posing a challenge on temporal processing. To address these challenges, this paper proposes a two-stream neural network with one stream being a self-attention based …
We propose Human Pose Models that represent RGB and depth images of human poses independent of clothing textures, backgrounds, lighting conditions, body shapes and camera viewpoints. Learning such universal models requires training images where all factors are varied for every human pose. Capturing such data is prohibitively expensive. Therefore, we develop a framework for synthesizing the training data. First, we learn representative human poses from a large corpus of real motion captured human skeleton data. Next, we fit synthetic 3D humans with different body shapes to each pose and render …
Johns Hopkins University（约翰斯·霍普金斯大学）；University of Maryland, College Park（马里兰大学帕克分校）；Research Center for Information Technology Innovation, Academia Sinica（中央研究院资讯科技创新研究中心）
Recent progress on action recognition has mainly focused on RGB and optical flow features. In this paper, we approach the problem of joint-based action recognition. Unlike other modalities, constellation of joints and their motion generate models with succinct human motion information for activity recognition. We present a new model for joint-based action recognition, which first extracts motion features from each joint separately through a shared motion encoder before performing collective reasoning. Our joint selector module re-weights the joint information to select the most discriminative …
Human action recognition (HAR) in videos is one of the core tasks of video understanding. Based on video sequences, the goal is to recognize actions performed by humans. While HAR has received much attention in the visible spectrum, action recognition in infrared videos is little studied. Accurate recognition of human actions in the infrared domain is a highly challenging task because of the redundant and indistinguishable texture features present in the sequence. Furthermore, in some cases, challenges arise from the irrelevant information induced by the presence of multiple active persons not…
University of Salerno（萨莱诺大学）；University of Groningen（格罗宁根大学）
Pose detection is one of the fundamental steps for the recognition of human actions. In this paper we propose a novel trainable detector for recognizing human poses based on the analysis of the skeleton. The main idea is that a skeleton pose can be described by the spatial arrangements of its joints. Starting from this consideration, we propose a trainable pose detector, that can be configured on a prototype skeleton in an automatic configuration process. The result of the configuration is a model of the position of the joints in the concerned skeleton. In the application phase, the joint posi…
Zhejiang University – University of Illinois at Urbana-Champaign Institute, ZJUI（浙江大学伊利诺伊大学厄巴纳香槟校区联合学院（ZJUI））
Action recognition and pose estimation from videos are closely related to understand human motions, but more literature focuses on how to solve pose estimation tasks alone from action recognition. This research shows a faster and more flexible training method for VideoPose3D which is based on action recognition. This model is fed with the same type of action as the type that will be estimated, and different types of actions can be trained separately. Evidence has shown that, for common pose-estimation tasks, this model requires a relatively small amount of data to carry out similar results wit…
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）；CAS Center for Excellence in Brain Science and Intelligence Technology（中国科学院脑科学与智能技术卓越创新中心）
Pose-based action recognition has drawn considerable attention recently. Existing methods exploit the joint positions to extract the body-part features from the activation map of the convolutional networks to assist human action recognition. However, these features are simply concatenated or max-pooled in previous works. The structured correlations among the body parts, which are essential for understanding complex human actions, are not fully exploited. To address the problem, we propose a pose-based graph convolutional network (PGCN), which encodes the body-part features into a human-based s…
NVIDIA（英伟达）；University of Central Florida（中佛罗里达大学）
We propose DeepGRU, a novel end-to-end deep network model informed by recent developments in deep learning for gesture and action recognition, that is streamlined and device-agnostic. DeepGRU, which uses only raw skeleton, pose or vector data is quickly understood, implemented, and trained, and yet achieves state-of-the-art results on challenging datasets. At the heart of our method lies a set of stacked gated recurrent units (GRU), two fully-connected layers and a novel global attention model. We evaluate our method on seven publicly available datasets, containing various number of samples an…
Graph convolutional networks (GCNs), which can model the human body skeletons as spatial and temporal graphs, have shown remarkable potential in skeleton-based action recognition. However, in the existing GCN-based methods, graph-structured representation of the human skeleton makes it difficult to be fused with other modalities, especially in the early stages. This may limit their scalability and performance in action recognition tasks. In addition, the pose information, which naturally contains informative and discriminative clues for action recognition, is rarely explored together with skel…
University of Rochester（罗切斯特大学）；University of Rochester Medical Center（罗切斯特大学医学中心）；Google Inc.（谷歌公司）
Inspired by the human ability to infer emotions from body language, we propose an automated framework for body language based emotion recognition starting from regular RGB videos. In collaboration with psychologists, we further extend the framework for psychiatric symptom prediction. Because a specific application domain of the proposed framework may only supply a limited amount of data, the framework is designed to work on a small training set and possess a good transferability. The proposed system in the first stage generates sequences of body language predictions based on human poses estima…
Institute of Automation, Chinese Academy of Sciences (CASIA)（中国科学院自动化研究所）；University of Chinese Academy of Sciences (UCAS)（中国科学院大学）；Horizon Robotics, Inc.（地平线机器人公司）；Xiamen University（厦门大学）
Existing methods in video action recognition mostly do not distinguish human body from the environment and easily overfit the scenes and objects. In this work, we present a conceptually simple, general and high-performance framework for action recognition in trimmed videos, aiming at person-centric modeling. The method, called Action Machine, takes as inputs the videos cropped by person bounding boxes. It extends the Inflated 3D ConvNet (I3D) by adding a branch for human pose estimation and a 2D CNN for pose-based action recognition, being fast to train and test. Action Machine can benefit fro…
The University of Hong Kong（香港大学）；Microsoft Research Asia（微软亚洲研究院）；TransGP；Texas A&M University（德克萨斯农工大学）
Understanding dynamic hand motions and actions from egocentric RGB videos is a fundamental yet challenging task due to self-occlusion and ambiguity. To address occlusion and ambiguity, we develop a transformer-based framework to exploit temporal information for robust estimation. Noticing the different temporal granularity of and the semantic correlation between hand pose estimation and action recognition, we build a network hierarchy with two cascaded transformer encoders, where the first one exploits the short-term temporal cue for hand pose estimation, and the latter aggregates per-frame po…
With the advances in capturing 2D or 3D skeleton data, skeleton-based action recognition has received an increasing interest over the last years. As skeleton data is commonly represented by graphs, graph convolutional networks have been proposed for this task. While current graph convolutional networks accurately recognize actions, they are too expensive for robotics applications where limited computational resources are available. In this paper, we therefore propose a highly efficient graph convolutional network that addresses the limitations of previous works. This is achieved by a parallel …
We present ActionXPose, a novel 2D pose-based algorithm for posture-level Human Action Recognition (HAR). The proposed approach exploits 2D human poses provided by OpenPose detector from RGB videos. ActionXPose aims to process poses data to be provided to a Long Short-Term Memory Neural Network and to a 1D Convolutional Neural Network, which solve the classification problem. ActionXPose is one of the first algorithms that exploits 2D human poses for HAR. The algorithm has real-time performance and it is robust to camera movings, subject proximity changes, viewpoint changes, subject appearance …
The Chinese University of HongKong（香港中文大学）；Shanghai AI Laboratory（上海人工智能实验室）；The University of Texas at Austin（德克萨斯大学奥斯汀分校）；SenseTime Research（商汤科技研究院）；Nanyang Technological University（南洋理工大学）
Human skeleton, as a compact representation of human action, has received increasing attention in recent years. Many skeleton-based action recognition methods adopt graph convolutional networks (GCN) to extract features on top of human skeletons. Despite the positive results shown in previous works, GCN-based methods are subject to limitations in robustness, interoperability, and scalability. In this work, we propose PoseC3D, a new approach to skeleton-based action recognition, which relies on a 3D heatmap stack instead of a graph sequence as the base representation of human skeletons. Compare…
Univ Lyon, INSA-Lyon, CNRS, LIRIS（里昂大学，里昂国立应用科学学院，法国国家科学研究中心，里昂信息科学与技术实验室）；Laboratoire d’Informatique de l’Université de Tours (EA 6300), INSA Centre Val de Loire（图尔大学信息学实验室，卢瓦尔河谷国立应用科学学院）
We address human action recognition from multi-modal video data involving articulated pose and RGB frames and propose a two-stream approach. The pose stream is processed with a convolutional model taking as input a 3D tensor holding data from a sub-sequence. A specific joint ordering, which respects the topology of the human body, ensures that different convolutional layers correspond to meaningful levels of abstraction. The raw RGB stream is handled by a spatio-temporal soft-attention mechanism conditioned on features from the pose network. An LSTM network receives input from a set of image l…
mmEgoHand: Egocentric Hand Pose Estimation and Gesture Recognition with Head-mounted Millimeter-wave Radar and IMU
School of Software Engineering, Xi’an Jiaotong University（软件工程学院，西安交通大学）；School of Cyber Science and Engineering, Xi’an Jiaotong University（网络科学与工程学院，西安交通大学）；School of Computer Science and Technology, Xi’an Jiaotong University（计算机科学与技术学院，西安交通大学）；College of Computer Science and Technology, Zhejiang University（计算机科学与技术学院，浙江大学）
Robert Bosch GmbH（罗伯特·博世有限公司）；TU Dortmund（多特蒙德工业大学）
Human action recognition in video is an active yet challenging research topic due to high variation and complexity of data. In this paper, a novel video based action recognition framework utilizing complementary cues is proposed to handle this complex problem. Inspired by the successful two stream networks for action classification, additional pose features are studied and fused to enhance understanding of human action in a more abstract and semantic way. Towards practices, not only ground truth poses but also noisy estimated poses are incorporated in the framework with our proposed pre-proces…
Univ Lyon, INSA-Lyon, CNRS, LIRIS（里昂大学，里昂国立应用科学学院，法国国家科学研究中心，里昂信息科学与技术实验室）；Laboratoire d’Informatique de l’Université de Tours (EA 6300), INSA Centre Val de Loire（图尔大学计算机科学实验室，中央卢瓦尔河谷国立应用科学学院）
We propose a new spatio-temporal attention based mechanism for human action recognition able to automatically attend to the hands most involved into the studied action and detect the most discriminative moments in an action. Attention is handled in a recurrent manner employing Recurrent Neural Network (RNN) and is fully-differentiable. In contrast to standard soft-attention based mechanisms, our approach does not use the hidden RNN state as input to the attention model. Instead, attention distributions are extracted using external information: human articulated pose. We performed an extensive …
Centre for Visual Information Technology（视觉信息技术中心）
Pose-based action recognition is predominantly tackled by approaches which treat the input skeleton in a monolithic fashion, i.e. joints in the pose tree are processed as a whole. However, such approaches ignore the fact that action categories are often characterized by localized action dynamics involving only small subsets of part joint groups involving hands (e.g. `Thumbs up') or legs (e.g. `Kicking'). Although part-grouping based approaches exist, each part group is not considered within the global pose frame, causing such methods to fall short. Further, conventional approaches employ indep…
FunFace: Feature Utility and Norm Estimation for Face Recognition
University of Ljubljana（卢布尔雅纳大学）；Fraunhofer Institute for Computer Graphics Research IGD（弗劳恩霍夫计算机图形研究机构IGD）；Department of Computer Science, TU Darmstadt（图腾斯大学计算机科学系）；Dalian University of Technology（大连理工大学）
With a growing interest in autonomous vehicles' operation, there is an equally increasing need for efficient anticipatory gesture recognition systems for human-vehicle interaction. Existing gesture-recognition algorithms have been primarily restricted to historical data. In this paper, we propose a novel context and gap aware pose prediction framework(CGAP2), which predicts future pose data for anticipatory recognition of gestures in an online fashion. CGAP2 implements an encoder-decoder architecture paired with a pose prediction module to anticipate future frames followed by a shallow classif…
Indian Institute of Technology (ISM) Dhanbad（印度理工学院（印度矿业学院）丹巴德分校）；Queensland University of Technology (QUT)（昆士兰科技大学）
Visual Place Recognition (VPR) approaches have typically attempted to match places by identifying visual cues, image regions or landmarks that have high ``utility'' in identifying a specific place. But this concept of utility is not singular - rather it can take a range of forms. In this paper, we present a novel approach to deduce two key types of utility for VPR: the utility of visual cues `specific' to an environment, and to a particular place. We employ contrastive learning principles to estimate both the environment- and place-specific utility of Vector of Locally Aggregated Descriptors (…
This paper presents a multi-pose face recognition approach using hybrid face features descriptors (HFFD). The HFFD is a face descriptor containing of rich discriminant information that is created by fusing some frequency-based features extracted using both wavelet and DCT analysis of several different poses of 2D face images. The main aim of this method is to represent the multi-pose face images using a dominant frequency component with still having reasonable achievement compared to the recent multi-pose face recognition methods. The HFFD based face recognition tends to achieve better perform…
Demand of hand pose recognition systems are growing in the last years in technologies like human-machine interfaces. This work suggests an approach for hand pose recognition in embedded computers using hand tracking and CNNs. Results show a fast time response with an accuracy of 94.50% and low power consumption.
