Recent approaches in depth-based human activity analysis achieved outstanding performance and proved the effectiveness of 3D representation for classification of action classes. Currently available depth-based and RGB+D-based action recognition benchmarks have a number of limitations, including the lack of training samples, distinct class labels, camera views and variety of subjects. In this paper we introduce a large-scale dataset for RGB+D human action recognition with more than 56 thousand video samples and 4 million frames, collected from 40 distinct subjects. Our dataset contains 60 different action classes including daily, mutual, and health-related actions. In addition, we propose a new recurrent neural network structure to model the long-term temporal correlation of the features for each body part, and utilize them for better action classification. Experimental results show the advantages of applying deep learning methods over state-of-the-art hand-crafted features on the suggested cross-subject and cross-view evaluation criteria for our dataset. The introduction of this large scale dataset will enable the community to apply, develop and adapt various data-hungry learning techniques for the task of depth-based and RGB+D-based human activity analysis.
Nanyang Technological University（南洋理工大学）；Chalmers University of Technology（查尔姆斯理工大学）；Peking University（北京大学）；Peng Cheng Laboratory（鹏城实验室）；Alibaba Group（阿里巴巴集团）
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…
The lack of fine-grained joints (facial joints, hand fingers) is a fundamental performance bottleneck for state of the art skeleton action recognition models. Despite this bottleneck, community's efforts seem to be invested only in coming up with novel architectures. To specifically address this bottleneck, we introduce two new pose based human action datasets - NTU60-X and NTU120-X. Our datasets extend the largest existing action recognition dataset, NTU-RGBD. In addition to the 25 body joints for each skeleton as in NTU-RGBD, NTU60-X and NTU120-X dataset includes finger and facial joints, en…
Research on human action classification has made significant progresses in the past few years. Most deep learning methods focus on improving performance by adding more network components. We propose, however, to better utilize auxiliary mechanisms, including hierarchical classification, network pruning, and skeleton-based preprocessing, to boost the model robustness and performance. We test the effectiveness of our method on four commonly used testing datasets: NTU RGB+D 60, NTU RGB+D 120, Northwestern-UCLA Multiview Action 3D, and UTD Multimodal Human Action Dataset. Our experiments show that…
Human Activity Recognition in RGB-D videos has been an active research topic during the last decade. However, no efforts have been found in the literature, for recognizing human activity in RGB-D videos where several performers are performing simultaneously. In this paper we introduce such a challenging dataset with several performers performing the activities. We present a novel method for recognizing human activities in such videos. The proposed method aims in capturing the motion information of the whole video by producing a dynamic image corresponding to the input video. We use two paralle…
CMD: Self-supervised 3D Action Representation Learning with Cross-modal Mutual Distillation
University of Science and Technology of China（中国科学技术大学）；Institute of Artificial Intelligence, Hefei Comprehensive National Science Center（合肥综合性国家科学中心人工智能研究院）
Istituto Italiano di Tecnologia（意大利技术研究院）；University of Genova（热那亚大学）；University of Verona（维罗纳大学）
Heterogeneous data modalities can provide complementary cues for several tasks, usually leading to more robust algorithms and better performance. However, while training data can be accurately collected to include a variety of sensory modalities, it is often the case that not all of them are available in real life (testing) scenarios, where a model has to be deployed. This raises the challenge of how to extract information from multimodal data in the training stage, in a form that can be exploited at test time, considering limitations such as noisy or missing modalities. This paper presents a …
Multimodal Skeleton-Based Action Representation Learning via Decomposition and Composition
School of Computer Science and Engineering, Southeast University, Nanjing 210096, China（东南大学计算机科学与工程学院，南京210096，中国）；Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education, China（新一代人工智能技术及其交叉应用关键实验室（东南大学），中华人民共和国教育部，中国）；School of Cyber Science and Engineering, Southeast University, Nanjing 210096, China（东南大学网络安全科学与工程学院，南京210096，中国）；Engineering Research Center of Blockchain Application, Supervision And Management (Southeast University), Ministry of Education, China（区块链应用、监督与管理工程研究中心（东南大学），中华人民共和国教育部，中国）；Purple Mountain Laboratories, Nanjing 210000, China（紫金山实验室，南京210000，中国）
The data-driven approach that learns an optimal representation of vision features like skeleton frames or RGB videos is currently a dominant paradigm for activity recognition. While great improvements have been achieved from existing single modal approaches with increasingly larger datasets, the fusion of various data modalities at the feature level has seldom been attempted. In this paper, we propose a multimodal feature fusion model that utilizes both skeleton and RGB modalities to infer human activity. The objective is to improve the activity recognition accuracy by effectively utilizing th…
Occlusion-Aware 3D Motion Interpretation for Abnormal Behavior Detection
University of Science and Technology of China（中国科学技术大学）；Hefei Institutes of Physical Science, Chinese Academy of Sciences（中国科学院合肥物质科学研究院）；University of Lincoln（林肯大学）
SGA-INTERACT: A 3D Skeleton-based Benchmark for Group Activity Understanding in Modern Basketball Tactic
Fudan University（复旦大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；Beihang University（北京航空航天大学）；Zhejiang University（浙江大学）；University of Science and Technology of China（中国科学技术大学）；Shanghai University of Sport（上海体育大学）
Human Activity Recognition using RGB-Event based Sensors: A Multi-modal Heat Conduction Model and A Benchmark Dataset
School of Computer Science and Technology, Anhui University（安徽大学计算机科学与技术学院）；Beijing Institute of Technology（北京理工大学）；University of Chinese Academy of Sciences（中国科学院大学）；Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））；Peng Cheng Laboratory（鹏城实验室）；School of Computer Science, Peking University（北京大学计算机学院）；School of Electronic and Computer Engineering, Shenzhen Graduate School, Peking University（北京大学深圳研究生院电子与计算机工程学院）
Electronics and Telecommunications Research Institute（电子通信研究院）
Deep learning, based on which many modern algorithms operate, is well known to be data-hungry. In particular, the datasets appropriate for the intended application are difficult to obtain. To cope with this situation, we introduce a new dataset called ETRI-Activity3D, focusing on the daily activities of the elderly in robot-view. The major characteristics of the new dataset are as follows: 1) practical action categories that are selected from the close observation of the daily lives of the elderly; 2) realistic data collection, which reflects the robot's working environment and service situati…
Northwestern Polytechnical University（西北工业大学）；The University of Adelaide（阿德莱德大学）
Different from RGB videos, depth data in RGB-D videos provide key complementary information for tristimulus visual data which potentially could achieve accuracy improvement for action recognition. However, most of the existing action recognition models solely using RGB videos limit the performance capacity. Additionally, the state-of-the-art action recognition models, namely 3D convolutional neural networks (3D-CNNs) contain tremendous parameters suffering from computational inefficiency. In this paper, we propose a series of 3D light-weight architectures for action recognition based on RGB-D …
Bosch Center for Artificial Intelligence（博世人工智能中心）
3D skeleton-based motion prediction and activity recognition are two interwoven tasks in human behaviour analysis. In this work, we propose a motion context modeling methodology that provides a new way to combine the advantages of both graph convolutional neural networks and recurrent neural networks for joint human motion prediction and activity recognition. Our approach is based on using an LSTM encoder-decoder and a non-local feature extraction attention mechanism to model the spatial correlation of human skeleton data and temporal correlation among motion frames. The proposed network can e…
University of Chinese Academy of Sciences（中国科学院大学）
The dynamics of human skeletons have significant information for the task of action recognition. The similarity between trajectories of corresponding joints is an indicating feature of the same action, while this similarity may subject to some distortions that can be modeled as the combination of spatial and temporal affine transformations. In this work, we propose a novel feature called spatio-temporal dual affine differential invariant (STDADI). Furthermore, in order to improve the generalization ability of neural networks, a channel augmentation method is proposed. On the large scale action…
In multi-modal action recognition, it is important to consider not only the complementary nature of different modalities but also global action content. In this paper, we propose a novel network, named Modality Mixer (M-Mixer) network, to leverage complementary information across modalities and temporal context of an action for multi-modal action recognition. We also introduce a simple yet effective recurrent unit, called Multi-modal Contextualization Unit (MCU), which is a core component of M-Mixer. Our MCU temporally encodes a sequence of one modality (e.g., RGB) with action content features…
Recently skeleton-based action recognition has made signif-icant progresses in the computer vision community. Most state-of-the-art algorithms are based on Graph Convolutional Networks (GCN), andtarget at improving the network structure of the backbone GCN lay-ers. In this paper, we propose a novel mechanism to learn more robustdiscriminative features in space and time. More specifically, we add aDiscriminative Feature Learning (DFL) branch to the last layers of thenetwork to extract discriminative spatial and temporal features to helpregularize the learning. We also formally advocate the use …
Human Action Recognition (HAR) Using Skeleton-based Spatial Temporal Relative Transformer Network: ST-RTR
Zhengzhou University（郑州大学）；Henan Xintong Intelligent IOT Co., Ltd.（河南信通智能物联网有限公司）；Beijing University of Chemical Technology（北京化工大学）；Prince Sattam bin Abdulaziz University（萨塔姆·本·阿卜杜勒阿齐兹王子大学）
Orange Labs（法国电信Orange实验室）；Université Caen Normandie（卡昂诺曼底大学）；Samsung AI Centre（三星人工智能中心）
We tackle the problem of finding good architectures for multimodal classification problems. We propose a novel and generic search space that spans a large number of possible fusion architectures. In order to find an optimal architecture for a given dataset in the proposed search space, we leverage an efficient sequential model-based exploration approach that is tailored for the problem. We demonstrate the value of posing multimodal fusion as a neural architecture search problem by extensive experimentation on a toy dataset and two other real multimodal datasets. We discover fusion architecture…
Beihang University（北京航空航天大学）；Zhongguancun Laboratory（中关村实验室）；Hangzhou Innovation Institute of Beihang University（北京航空航天大学杭州创新研究院）
Human action recognition aims at classifying the category of human action from a segment of a video. Recently, people have dived into designing GCN-based models to extract features from skeletons for performing this task, because skeleton representations are much more efficient and robust than other modalities such as RGB frames. However, when employing the skeleton data, some important clues like related items are also discarded. It results in some ambiguous actions that are hard to be distinguished and tend to be misclassified. To alleviate this problem, we propose an auxiliary feature refin…
This paper presents a new framework for human action recognition from a 3D skeleton sequence. Previous studies do not fully utilize the temporal relationships between video segments in a human action. Some studies successfully used very deep Convolutional Neural Network (CNN) models but often suffer from the data insufficiency problem. In this study, we first segment a skeleton sequence into distinct temporal segments in order to exploit the correlations between them. The temporal and spatial features of a skeleton sequence are then extracted simultaneously by utilizing a fine-to-coarse (F2C) …
This paper presents an image classification based approach for skeleton-based video action recognition problem. Firstly, A dataset independent translation-scale invariant image mapping method is proposed, which transformes the skeleton videos to colour images, named skeleton-images. Secondly, A multi-scale deep convolutional neural network (CNN) architecture is proposed which could be built and fine-tuned on the powerful pre-trained CNNs, e.g., AlexNet, VGGNet, ResNet etal.. Even though the skeleton-images are very different from natural images, the fine-tune strategy still works well. At last…
Vision-Language Meets the Skeleton: Progressively Distillation with Cross-Modal Knowledge for 3D Action Representation Learning
School of Information and Communication Engineering, University of Electronic Science and Technology of China（电子科技大学信息与通信工程学院）；School of Automation Engineering, University of Electronic Science and Technology of China（电子科技大学自动化工程学院）；The Hong Kong Polytechnic University（香港理工大学）；Hong Kong Polytechnic University Shenzhen Research Institute（香港理工大学深圳研究院）；No.1 Orthopedic Hospital of Chengdu（成都市第一骨科医院）
In this paper, we focus on the spatio-temporal aspect of recognizing Activities of Daily Living (ADL). ADL have two specific properties (i) subtle spatio-temporal patterns and (ii) similar visual patterns varying with time. Therefore, ADL may look very similar and often necessitate to look at their fine-grained details to distinguish them. Because the recent spatio-temporal 3D ConvNets are too rigid to capture the subtle visual patterns across an action, we propose a novel Video-Pose Network: VPN. The 2 key components of this VPN are a spatial embedding and an attention network. The spatial em…
Human action recognition is a quite hugely investigated area where most remarkable action recognition networks usually use large-scale coarse-grained action datasets of daily human actions as inputs to state the superiority of their networks. We intend to recognize our small-scale fine-grained Tai Chi action dataset using neural networks and propose a transfer-learning method using NTU RGB+D dataset to pre-train our network. More specifically, the proposed method first uses a large-scale NTU RGB+D dataset to pre-train the Transformer-based network for action recognition to extract common featu…
SmartMore Corporation（思谋科技）；The Chinese University of Hong Kong (Shenzhen)（香港中文大学（深圳））；South China University of Technology（华南理工大学）
Skeleton-based action recognition has attracted research attentions in recent years. One common drawback in currently popular skeleton-based human action recognition methods is that the sparse skeleton information alone is not sufficient to fully characterize human motion. This limitation makes several existing methods incapable of correctly classifying action categories which exhibit only subtle motion differences. In this paper, we propose a novel framework for employing human pose skeleton and joint-centered light-weight information jointly in a two-stream graph convolutional network, namel…
Traditional action recognition models are constructed around the paradigm of 2D perspective imagery. Though sophisticated time-series models have pushed the field forward, much of the information is still not exploited by confining the domain to 2D. In this work, we introduce a novel representation of motion as a voxelized 3D vector field and demonstrate how it can be used to improve performance of action recognition networks. This volumetric representation is a natural fit for 3D CNNs, and allows out-of-plane data augmentation techniques during training of these networks. Both the constructio…
This paper proposes a human activity recognition method which is based on features learned from 3D video data without incorporating domain knowledge. The experiments on data collected by RGBD cameras produce results outperforming other techniques. Our feature encoding method follows the bag-of-visual-word model, then we use a SVM classifier to recognise the activities. We do not use skeleton or tracking information and the same technique is applied on color and depth data.
Shanghai Jiao Tong University（上海交通大学）；Illinois Institute of Technology（伊利诺伊理工学院）
Action recognition has been a heated topic in computer vision for its wide application in vision systems. Previous approaches achieve improvement by fusing the modalities of the skeleton sequence and RGB video. However, such methods have a dilemma between the accuracy and efficiency for the high complexity of the RGB video network. To solve the problem, we propose a multi-modality feature fusion network to combine the modalities of the skeleton sequence and RGB frame instead of the RGB video, as the key information contained by the combination of skeleton sequence and RGB frame is close to tha…
University of Wollongong（卧龙岗大学）；Motovis Inc（魔视智能科技有限公司）；Chinese Academy of Sciences（中国科学院）；National University of Defense Technology（国防科技大学）
A novel deep neural network training paradigm that exploits the conjoint information in multiple heterogeneous sources is proposed. Specifically, in a RGB-D based action recognition task, it cooperatively trains a single convolutional neural network (named c-ConvNet) on both RGB visual features and depth features, and deeply aggregates the two kinds of features for action recognition. Differently from the conventional ConvNet that learns the deep separable features for homogeneous modality-based classification with only one softmax loss function, the c-ConvNet enhances the discriminative power…
Aparnix；University Carlos III de Madrid（马德里卡洛斯三世大学）；Queen Mary University of London（伦敦玛丽女王大学）
The computer vision community is currently focusing on solving action recognition problems in real videos, which contain thousands of samples with many challenges. In this process, Deep Convolutional Neural Networks (D-CNNs) have played a significant role in advancing the state-of-the-art in various vision-based action recognition systems. Recently, the introduction of residual connections in conjunction with a more traditional CNN model in a single architecture called Residual Network (ResNet) has shown impressive performance and great potential for image recognition tasks. In this paper, we …
Affinity Contrastive Learning for Skeleton-based Human Activity Understanding
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；School of Electronic, Electrical and Communication Engineering, Univeristy of Chinese Academy of Sciences（中国科学院大学电子电气与通信工程学院）；School of Artificial Intelligence, Beijing University of Posts and Telecommunications（北京邮电大学人工智能学院）；Moonshot AI
Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition
State Key Laboratory of General Artificial Intelligence, Peking University（通用人工智能国家重点实验室，北京大学）；Center for Research in Computer Vision, University of Central Florida（中佛罗里达大学计算机视觉研究中心）
Inria（法国国家信息与自动化研究所）；Université Côte d’Azur（蔚蓝海岸大学）；Toyota Motor Europe（丰田汽车欧洲公司）
Action recognition based on skeleton data has recently witnessed increasing attention and progress. State-of-the-art approaches adopting Graph Convolutional networks (GCNs) can effectively extract features on human skeletons relying on the pre-defined human topology. Despite associated progress, GCN-based methods have difficulties to generalize across domains, especially with different human topological structures. In this context, we introduce UNIK, a novel skeleton-based action recognition method that is not only effective to learn spatio-temporal features on human skeleton sequences but als…
Trunk-branch Contrastive Network with Multi-view Deformable Aggregation for Multi-view Action Recognition
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；University of Chinese Academy of Sciences（中国科学院大学）；School of Mechanical Engineering and Automation, Harbin Institute of Technology at Shenzhen（哈尔滨工业大学（深圳）机械工程与自动化学院）
TSkel-Mamba: Temporal Dynamic Modeling via State Space Model for Human Skeleton-based Action Recognition
School of Information Science and Engineering, Yunnan University（信息科学与工程学院，云南大学）；Lancaster University（兰卡斯特大学）；The University of Western Australia（西澳大学）；Monash University（墨尔本大学）
Università Politecnica delle Marche（马尔凯理工大学）；Grottini Lab srl（格罗蒂尼实验室有限公司）
The aim of this paper is to present an integrated system consisted of a RGB-D camera and a software able to monitor shoppers in intelligent retail environments. We propose an innovative low cost smart system that can understand the shoppers' behavior and, in particular, their interactions with the products in the shelves, with the aim to develop an automatic RGB-D technique for video analysis. The system of cameras detects the presence of people and univocally identifies them. Through the depth frames, the system detects the interactions of the shoppers with the products on the shelf and deter…
