In this paper, we propose Two-Stream AMTnet, which leverages recent advances in video-based action representation[1] and incremental action tube generation[2]. Majority of the present action detectors follow a frame-based representation, a late-fusion followed by an offline action tube building steps. These are sub-optimal as: frame-based features barely encode the temporal relations; late-fusion restricts the network to learn robust spatiotemporal features; and finally, an offline action tube generation is not suitable for many real-world problems such as autonomous driving, human-robot interaction to name a few. The key contributions of this work are: (1) combining AMTnet's 3D proposal architecture with an online action tube generation technique which allows the model to learn stronger temporal features needed for accurate action detection and facilitates running inference online; (2) an efficient fusion technique allowing the deep network to learn strong spatiotemporal action representations. This is achieved by augmenting the previous Action Micro-Tube (AMTnet) action detection framework in three distinct ways: by adding a parallel motion stIn this paper, we propose a new deep neural network architecture for online action detection, termed ream to the original appearance one in AMTnet; (2) in opposition to state-of-the-art action detectors which train appearance and motion streams separately, and use a test time late fusion scheme to fuse RGB and flow cues, by jointly training both streams in an end-to-end fashion and merging RGB and optical flow features at training time; (3) by introducing an online action tube generation algorithm which works at video-level, and in real-time (when exploiting only appearance features). Two-Stream AMTnet exhibits superior action detection performance over state-of-the-art approaches on the standard action detection benchmarks.
Dominant approaches to action detection can only provide sub-optimal solutions to the problem, as they rely on seeking frame-level detections, to later compose them into "action tubes" in a post-processing step. With this paper we radically depart from current practice, and take a first step towards the design and implementation of a deep network architecture able to classify and regress whole video subsets, so providing a truly optimal solution of the action detection problem. In this work, in particular, we propose a novel deep net framework able to regress and classify 3D region proposals s…
UniWAM Technical Report: Unified Mobile Manipulation via Mixed-Stream World-Action Modeling and Manipulation Anchor Pose Supervision
Physical Superintelligence Lab, Fysics AI（Fysics AI 物理超级智能实验室）；College of Intelligent Robotics and Advanced Manufacturing, Fudan University（复旦大学智能机器人与先进制造学院）
Institute of Cognitive Intelligence（认知智能研究所）；DeepBlue Academy of Sciences（深蓝科学院）；DeepBlue Technology (Shanghai) Co., Ltd.（深蓝科技（上海）有限公司）
Action recognition is an important research topic in computer vision. It is the basic work for visual understanding and has been applied in many fields. Since human actions can vary in different environments, it is difficult to infer actions in completely different states with a same structural model. For this case, we propose a Cross-Enhancement Transform Two-Stream 3D ConvNets algorithm, which considers the action distribution characteristics on the specific dataset. As a teaching model, stream with better performance in both streams is expected to assist in training another stream. In this …
University of Guelph（圭尔夫大学）；Vector Institute for Artificial Intelligence（向量人工智能研究所）；Canadian Institute for Advanced Research（加拿大高级研究所）
Two-stream networks have been very successful for solving the problem of action detection. However, prior work using two-stream networks train both streams separately, which prevents the network from exploiting regularities between the two streams. Moreover, unlike the visual stream, the dominant forms of optical flow computation typically do not maximally exploit GPU parallelism. We present a real-time end-to-end trainable two-stream network for action detection. First, we integrate the optical flow computation in our framework by using Flownet2. Second, we apply early fusion for the two stre…
We present a 3D Convolutional Neural Networks (CNNs) based single shot detector for spatial-temporal action detection tasks. Our model includes: (1) two short-term appearance and motion streams, with single RGB and optical flow image input separately, in order to capture the spatial and temporal information for the current frame; (2) two long-term 3D ConvNet based stream, working on sequences of continuous RGB and optical flow images to capture the context from past frames. Our model achieves strong performance for action detection in video and can be easily integrated into any current two-str…
We introduce the first benchmark for a new problem --- recognizing human action adverbs (HAA): "Adverbs Describing Human Actions" (ADHA). This is the first step for computer vision to change over from pattern recognition to real AI. We demonstrate some key features of ADHA: a semantically complete set of adverbs describing human actions, a set of common, describable human actions, and an exhaustive labeling of simultaneously emerging actions in each video. We commit an in-depth analysis on the implementation of current effective models in action recognition and image captioning on adverb recog…
The goal of this paper is to detect the spatio-temporal extent of an action. The two-stream detection network based on RGB and flow provides state-of-the-art accuracy at the expense of a large model-size and heavy computation. We propose to embed RGB and optical-flow into a single two-in-one stream network with new layers. A motion condition layer extracts motion information from flow images, which is leveraged by the motion modulation layer to generate transformation parameters for modulating the low-level RGB features. The method is easily embedded in existing appearance- or two-stream actio…
In this paper, several variants of two-stream architectures for temporal action proposal generation in long, untrimmed videos are presented. Inspired by the recent advances in the field of human action recognition utilizing 3D convolutions in combination with two-stream networks and based on the Single-Stream Temporal Action Proposals (SST) architecture, four different two-stream architectures utilizing sequences of images on one stream and sequences of images of optical flow on the other stream are subsequently investigated. The four architectures fuse the two separate streams at different de…
Google（谷歌）；University of Michigan（密歇根大学）；Princeton University（普林斯顿大学）
State-of-the-art methods for video action recognition commonly use an ensemble of two networks: the spatial stream, which takes RGB frames as input, and the temporal stream, which takes optical flow as input. In recent work, both of these streams consist of 3D Convolutional Neural Networks, which apply spatiotemporal filters to the video clip before performing classification. Conceptually, the temporal filters should allow the spatial stream to learn motion representations, making the temporal stream redundant. However, we still see significant benefits in action recognition performance by inc…
Online temporal action localization from an untrimmed video stream is a challenging problem in computer vision. It is challenging because of i) in an untrimmed video stream, more than one action instance may appear, including background scenes, and ii) in online settings, only past and current information is available. Therefore, temporal priors, such as the average action duration of training data, which have been exploited by previous action detection methods, are not suitable for this task because of the high intra-class variation in human actions. We propose a novel online action detection…
We formulate the problem of online temporal action detection in live streaming videos, acknowledging one important property of live streaming videos that there is normally a broadcast delay between the latest captured frame and the actual frame viewed by the audience. The standard setting of the online action detection task requires immediate prediction after a new frame is captured. We illustrate that its lack of consideration of the delay is imposing unnecessary constraints on the models and thus not suitable for this problem. We propose to adopt the problem setting that allows models to mak…
This paper proposes a two-stream flow-guided convolutional attention networks for action recognition in videos. The central idea is that optical flows, when properly compensated for the camera motion, can be used to guide attention to the human foreground. We thus develop cross-link layers from the temporal network (trained on flows) to the spatial network (trained on RGB frames). These cross-link layers guide the spatial-stream to pay more attention to the human foreground areas and be less affected by background clutter. We obtain promising performances with our approach on the UCF101, HMDB5…
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）
For the two-stream style methods in action recognition, fusing the two streams' predictions is always by the weighted averaging scheme. This fusion method with fixed weights lacks of pertinence to different action videos and always needs trial and error on the validation set. In order to enhance the adaptability of two-stream ConvNets and improve its performance, an end-to-end trainable gated fusion method, namely gating ConvNet, for the two-stream ConvNets is proposed in this paper based on the MoE (Mixture of Experts) theory. The gating ConvNet takes the combination of feature maps from the …
Shandong Normal University（山东师范大学）；Deakin University（迪肯大学）
For pursuing accurate skeleton-based action recognition, most prior methods use the strategy of combining Graph Convolution Networks (GCNs) with attention-based methods in a serial way. However, they regard the human skeleton as a complete graph, resulting in less variations between different actions (e.g., the connection between the elbow and head in action ``clapping hands''). For this, we propose a novel Contrastive GCN-Transformer Network (ConGT) which fuses the spatial and temporal modules in a parallel way. The ConGT involves two parallel streams: Spatial-Temporal Graph Convolution strea…
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…
Two-stream networks have achieved great success in video recognition. A two-stream network combines a spatial stream of RGB frames and a temporal stream of Optical Flow to make predictions. However, the temporal redundancy of RGB frames as well as the high-cost of optical flow computation creates challenges for both the performance and efficiency. Recent works instead use modern compressed video modalities as an alternative to the RGB spatial stream and improve the inference speed by orders of magnitudes. Previous works create one stream for each modality which are combined with an additional …
University of Maryland, College Park（马里兰大学帕克分校）；Honda Research Institute, USA（本田美国研究院）
We present a self-supervised approach using spatio-temporal signals between video frames for action recognition. A two-stream architecture is leveraged to tangle spatial and temporal representation learning. Our task is formulated as both a sequence verification and spatio-temporal alignment tasks. The former task requires motion temporal structure understanding while the latter couples the learned motion with the spatial representation. The self-supervised pre-trained weights effectiveness is validated on the action recognition task. Quantitative evaluation shows the self-supervised approach …
Peking University（北京大学）；Beijing Institute of Technology（北京理工大学）
Learning the spatial-temporal representation of motion information is crucial to human action recognition. Nevertheless, most of the existing features or descriptors cannot capture motion information effectively, especially for long-term motion. To address this problem, this paper proposes a long-term motion descriptor called sequential Deep Trajectory Descriptor (sDTD). Specifically, we project dense trajectories into two-dimensional planes, and subsequently a CNN-RNN network is employed to learn an effective representation for long-term motion. Unlike the popular two-stream ConvNets, the sDT…
Egocentric action anticipation is the task of predicting the future actions a camera wearer will likely perform based on past video observations. While in a real-world system it is fundamental to output such predictions before the action begins, past works have not generally paid attention to model runtime during evaluation. Indeed, current evaluation schemes assume that predictions can be made offline, and hence that computational resources are not limited. In contrast, in this paper, we propose a "streaming" egocentric action anticipation evaluation protocol which explicitly considers model …
In this paper, we propose a study on multi-modal (audio and video) action spotting and classification in soccer videos. Action spotting and classification are the tasks that consist in finding the temporal anchors of events in a video and determine which event they are. This is an important application of general activity understanding. Here, we propose an experimental study on combining audio and video information at different stages of deep neural network architectures. We used the SoccerNet benchmark dataset, which contains annotated events for 500 soccer game videos from the Big Five Europ…
CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System（中国科学院地理空间信息处理与应用系统技术重点实验室）；University of Science and Technology of China（中国科学技术大学）
We study the video super-resolution (SR) problem for facilitating video analytics tasks, e.g. action recognition, instead of for visual quality. The popular action recognition methods based on convolutional networks, exemplified by two-stream networks, are not directly applicable on video of low spatial resolution. This can be remedied by performing video SR prior to recognition, which motivates us to improve the SR procedure for recognition accuracy. Tailored for two-stream action recognition networks, we propose two video SR methods for the spatial and temporal streams respectively. On the o…
It remains a challenge to efficiently extract spatialtemporal information from skeleton sequences for 3D human action recognition. Although most recent action recognition methods are based on Recurrent Neural Networks which present outstanding performance, one of the shortcomings of these methods is the tendency to overemphasize the temporal information. Since 3D convolutional neural network(3D CNN) is a powerful tool to simultaneously learn features from both spatial and temporal dimensions through capturing the correlations between three dimensional signals, this paper proposes a novel two-s…
Columbia University（哥伦比亚大学）；Universitat Politecnica de Catalunya（加泰罗尼亚理工大学）；Mitsubishi Electric（三菱电机）
We aim to tackle a novel task in action detection - Online Detection of Action Start (ODAS) in untrimmed, streaming videos. The goal of ODAS is to detect the start of an action instance, with high categorization accuracy and low detection latency. ODAS is important in many applications such as early alert generation to allow timely security or emergency response. We propose three novel methods to specifically address the challenges in training ODAS models: (1) hard negative samples generation based on Generative Adversarial Network (GAN) to distinguish ambiguous background, (2) explicitly mode…
ARN-LSTM: A Multi-Stream Fusion Model for Skeleton-based Action Recognition
Universiti Sains Malaysia（马来西亚理科大学）；College of Technology and Business（科技与商学院）；Shenzhen Polytechnic University（深圳职业技术大学）；Institute of Applied Artificial Intelligence of the Guangdong-Hong Kong-Macao Greater Bay Area（粤港澳大湾区应用人工智能研究院）
Xi’an Jiaotong University（西安交通大学）；University of Illinois at Chicago（伊利诺伊大学芝加哥分校）；HERE Technologies（HERE科技公司）；State University of New York at Buffalo（纽约州立大学布法罗分校）；Wormpex AI Research（沃姆派克斯人工智能研究院）
Weakly-supervised Temporal Action Localization (W-TAL) aims to classify and localize all action instances in an untrimmed video under only video-level supervision. However, without frame-level annotations, it is challenging for W-TAL methods to identify false positive action proposals and generate action proposals with precise temporal boundaries. In this paper, we present a Two-Stream Consensus Network (TSCN) to simultaneously address these challenges. The proposed TSCN features an iterative refinement training method, where a frame-level pseudo ground truth is iteratively updated, and used t…
Indiana University, Bloomington（印第安纳大学伯明顿分校）；University of Central Florida（中佛罗里达大学）；Midea Corporate Research Center（美的企业研究中心）
A major emerging challenge is how to protect people's privacy as cameras and computer vision are increasingly integrated into our daily lives, including in smart devices inside homes. A potential solution is to capture and record just the minimum amount of information needed to perform a task of interest. In this paper, we propose a fully-coupled two-stream spatiotemporal architecture for reliable human action recognition on extremely low resolution (e.g., 12x16 pixel) videos. We provide an efficient method to extract spatial and temporal features and to aggregate them into a robust feature re…
We investigate architectures of discriminatively trained deep Convolutional Networks (ConvNets) for action recognition in video. The challenge is to capture the complementary information on appearance from still frames and motion between frames. We also aim to generalise the best performing hand-crafted features within a data-driven learning framework. Our contribution is three-fold. First, we propose a two-stream ConvNet architecture which incorporates spatial and temporal networks. Second, we demonstrate that a ConvNet trained on multi-frame dense optical flow is able to achieve very good pe…
University of Electronic Science and Technology of China（电子科技大学）
Spatial and temporal stream model has gained great success in video action recognition. Most existing works pay more attention to designing effective features fusion methods, which train the two-stream model in a separate way. However, it's hard to ensure discriminability and explore complementary information between different streams in existing works. In this work, we propose a novel cooperative cross-stream network that investigates the conjoint information in multiple different modalities. The jointly spatial and temporal stream networks feature extraction is accomplished by an end-to-end …
In this work, we introduce a new video representation for action classification that aggregates local convolutional features across the entire spatio-temporal extent of the video. We do so by integrating state-of-the-art two-stream networks with learnable spatio-temporal feature aggregation. The resulting architecture is end-to-end trainable for whole-video classification. We investigate different strategies for pooling across space and time and combining signals from the different streams. We find that: (i) it is important to pool jointly across space and time, but (ii) appearance and motion …
Extended multi-stream temporal-attention module for skeleton-based human action recognition (HAR)
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）；LUT University（拉彭兰塔-拉赫蒂理工大学）；University of Oulu（奥卢大学）；Government College University Faisalabad（费萨拉巴德政府学院大学）
Center for Research on Intelligent Perception and Computing (CRIPAC)（智能感知与计算研究中心）；National Laboratory of Pattern Recognition (NLPR)（模式识别国家重点实验室）；University of Chinese Academy of Sciences (UCAS)（中国科学院大学）；Center for Excellence in Brain Science and Intelligence Technology (CEBSIT)（脑科学与智能技术卓越创新中心）；Institute of Automation, Chinese Academy of Sciences (CASIA)（中国科学院自动化研究所）
Recently, skeleton based action recognition gains more popularity due to cost-effective depth sensors coupled with real-time skeleton estimation algorithms. Traditional approaches based on handcrafted features are limited to represent the complexity of motion patterns. Recent methods that use Recurrent Neural Networks (RNN) to handle raw skeletons only focus on the contextual dependency in the temporal domain and neglect the spatial configurations of articulated skeletons. In this paper, we propose a novel two-stream RNN architecture to model both temporal dynamics and spatial configurations f…
Understanding accurate information on human behaviours is one of the most important tasks in machine intelligence. Human Activity Recognition that aims to understand human activities from a video is a challenging task due to various problems including background, camera motion and dataset variations. This paper proposes two CNN based architectures with three streams which allow the model to exploit the dataset under different settings. The three pathways are differentiated in frame rates. The single pathway, operates at a single frame rate captures spatial information, the slow pathway operate…
Deep convolutional neural networks (ConvNets) have been recently shown to attain state-of-the-art performance for action recognition on standard-resolution videos. However, less attention has been paid to recognition performance at extremely low resolutions (eLR) (e.g., 16 x 12 pixels). Reliable action recognition using eLR cameras would address privacy concerns in various application environments such as private homes, hospitals, nursing/rehabilitation facilities, etc. In this paper, we propose a semi-coupled filter-sharing network that leverages high resolution (HR) videos during training in…
University of Oulu（奥卢大学）；Delft University of Technology（代尔夫特理工大学）
To address the problem of training on small datasets for action recognition tasks, most prior works are either based on a large number of training samples or require pre-trained models transferred from other large datasets to tackle overfitting problems. However, it limits the research within organizations that have strong computational abilities. In this work, we try to propose a data-efficient framework that can train the model from scratch on small datasets while achieving promising results. Specifically, by introducing a 3D central difference convolution operation, we proposed a novel C3D …
Action Recognition with Multi-stream Motion Modeling and Mutual Information Maximization
College of Computer Science and Technology, Jilin University（吉林大学计算机科学与技术学院）；Zhejiang Lab（之江实验室）；School of Cyber Science and Technology, Zhejiang University（浙江大学网络空间安全学院）；Public Computer Education and Research Center, Jilin University（吉林大学公共计算机教育与研究中心）；Black Sesame Technologies（黑芝麻科技）
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）
In skeleton-based action recognition, graph convolutional networks (GCNs), which model the human body skeletons as spatiotemporal graphs, have achieved remarkable performance. However, in existing GCN-based methods, the topology of the graph is set manually, and it is fixed over all layers and input samples. This may not be optimal for the hierarchical GCN and diverse samples in action recognition tasks. In addition, the second-order information (the lengths and directions of bones) of the skeleton data, which is naturally more informative and discriminative for action recognition, is rarely i…
In this paper we address the problem of human action recognition from video sequences. Inspired by the exemplary results obtained via automatic feature learning and deep learning approaches in computer vision, we focus our attention towards learning salient spatial features via a convolutional neural network (CNN) and then map their temporal relationship with the aid of Long-Short-Term-Memory (LSTM) networks. Our contribution in this paper is a deep fusion framework that more effectively exploits spatial features from CNNs with temporal features from LSTM models. We also extensively evaluate t…
Institute of Cognitive Intelligence, DeepBlue Academy of Sciences（深蓝科学院认知智能研究所）；DeepBlue Technology (Shanghai) Co., Ltd.（深蓝科技（上海）有限公司）
With the rapid development of deep learning algorithms, action recognition in video has achieved many important research results. One issue in action recognition, Zero-Shot Action Recognition (ZSAR), has recently attracted considerable attention, which classify new categories without any positive examples. Another difficulty in action recognition is that untrimmed data may seriously affect model performance. We propose a composite two-stream framework with a pre-trained model. Our proposed framework includes a classifier branch and a composite feature branch. The graph network model is adopted…
Graph convolutional networks (GCNs), which generalize CNNs to more generic non-Euclidean structures, have achieved remarkable performance for skeleton-based action recognition. However, there still exist several issues in the previous GCN-based models. First, the topology of the graph is set heuristically and fixed over all the model layers and input data. This may not be suitable for the hierarchy of the GCN model and the diversity of the data in action recognition tasks. Second, the second-order information of the skeleton data, i.e., the length and orientation of the bones, is rarely invest…
The Chinese University of Hong Kong（香港中文大学）；Shenzhen Institutes of Advanced Technology, CAS（中国科学院深圳先进技术研究院）
Deep convolutional networks have achieved great success for object recognition in still images. However, for action recognition in videos, the improvement of deep convolutional networks is not so evident. We argue that there are two reasons that could probably explain this result. First the current network architectures (e.g. Two-stream ConvNets) are relatively shallow compared with those very deep models in image domain (e.g. VGGNet, GoogLeNet), and therefore their modeling capacity is constrained by their depth. Second, probably more importantly, the training dataset of action recognition is…
China University of Geosciences（中国地质大学）；University of Wollongong（卧龙岗大学）
Different from traditional action recognition based on video segments, online action recognition aims to recognize actions from unsegmented streams of data in a continuous manner. One way for online recognition is based on the evidence accumulation over time to make predictions from stream videos. This paper presents a fast yet effective method to recognize actions from stream of noisy skeleton data, and a novel weighted covariance descriptor is adopted to accumulate evidence. In particular, a fast incremental updating method for the weighted covariance descriptor is developed for accumulation…
Graz University of Technology（格拉茨技术大学）；University of Oxford（牛津大学）
Recent applications of Convolutional Neural Networks (ConvNets) for human action recognition in videos have proposed different solutions for incorporating the appearance and motion information. We study a number of ways of fusing ConvNet towers both spatially and temporally in order to best take advantage of this spatio-temporal information. We make the following findings: (i) that rather than fusing at the softmax layer, a spatial and temporal network can be fused at a convolution layer without loss of performance, but with a substantial saving in parameters; (ii) that it is better to fuse su…
Improved dense trajectories (iDT) have shown great performance in action recognition, and their combination with the two-stream approach has achieved state-of-the-art performance. It is, however, difficult for iDT to completely remove background trajectories from video with camera shaking. Trajectories in less discriminative regions should be given modest weights in order to create more discriminative local descriptors for action recognition. In addition, the two-stream approach, which learns appearance and motion information separately, cannot focus on motion in important regions when extract…
