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-stream action detection methods. We report a frame-mAP of 71.30% on the challenging UCF101-24 actions dataset, achieving the state-of-the-art result of the one-stage methods. To the best of our knowledge, our work is the first system that combined 3D CNN and SSD in action detection tasks.
Beijing University of Posts and Telecommunications（北京邮电大学）
Fusion is critical for a two-stream network. In this paper, we propose a novel temporal fusion (TF) module to fuse the two-stream joints' information to predict human motion, including a temporal concatenation and a reinforcement trajectory spatial-temporal (TST) block, specifically designed to keep prediction temporal consistency. In particular, the temporal concatenation keeps the temporal consistency of preliminary predictions from two streams. Meanwhile, the TST block improves the spatial-temporal feature coupling. However, the TF module can increase the temporal continuities between the f…
In this paper we propose a novel Temporal Attentive Relation Network (TARN) for the problems of few-shot and zero-shot action recognition. At the heart of our network is a meta-learning approach that learns to compare representations of variable temporal length, that is, either two videos of different length (in the case of few-shot action recognition) or a video and a semantic representation such as word vector (in the case of zero-shot action recognition). By contrast to other works in few-shot and zero-shot action recognition, we a) utilise attention mechanisms so as to perform temporal ali…
U.S. Army Research Lab（美国陆军研究实验室）；Booz Allen Hamilton（博思艾伦汉密尔顿）
We present a novel deep zero-shot learning (ZSL) model for inferencing human-object-interaction with verb-object (VO) query. While the previous two-stream ZSL approaches only use the semantic/textual information to be fed into the query stream, we seek to incorporate and embed the semantics into the visual representation stream as well. Our approach is powered by Semantics-to-Space (S2S) architecture where semantics derived from the residing objects are embedded into a spatial space of the visual stream. This architecture allows the co-capturing of the semantic attributes of the human and the …
Few-shot action recognition has attracted increasing attention due to the difficulty in acquiring the properly labelled training samples. Current works have shown that preserving spatial information and comparing video descriptors are crucial for few-shot action recognition. However, the importance of preserving temporal information is not well discussed. In this paper, we propose a Contents and Length-based Temporal Attention (CLTA) model, which learns customized temporal attention for the individual video to tackle the few-shot action recognition problem. CLTA utilizes the Gaussian likelihoo…
OriginAI；Technion（以色列理工学院）；IBM Research AI（IBM研究院人工智能部门）
Classification of new class entities requires collecting and annotating hundreds or thousands of samples that is often prohibitively costly. Few-shot learning suggests learning to classify new classes using just a few examples. Only a small number of studies address the challenge of few-shot learning on spatio-temporal patterns such as videos. In this paper, we present the Temporal Aware Embedding Network (TAEN) for few-shot action recognition, that learns to represent actions, in a metric space as a trajectory, conveying both short term semantics and longer term connectivity between action pa…
University of California, Berkeley（加利福尼亚大学伯克利分校）；National University of Singapore（新加坡国立大学）；Boston University（波士顿大学）
Many activities of interest are rare events, with only a few labeled examples available. Therefore models for temporal activity detection which are able to learn from a few examples are desirable. In this paper, we present a conceptually simple and general yet novel framework for few-shot temporal activity detection which detects the start and end time of the few-shot input activities in an untrimmed video. Our model is end-to-end trainable and can benefit from more few-shot examples. At test time, each proposal is assigned the label of the few-shot activity class corresponding to the maximum …
The Zero-Shot Sketch-based Image Retrieval (ZS-SBIR) is a challenging task because of the large domain gap between sketches and natural images as well as the semantic inconsistency between seen and unseen categories. Previous literature bridges seen and unseen categories by semantic embedding, which requires prior knowledge of the exact class names and additional extraction efforts. And most works reduce domain gap by mapping sketches and natural images into a common high-level space using constructed sketch-image pairs, which ignore the unpaired information between images and sketches. To add…
There is a growing interest in learning a model which could recognize novel classes with only a few labeled examples. In this paper, we propose Temporal Alignment Module (TAM), a novel few-shot learning framework that can learn to classify a previous unseen video. While most previous works neglect long-term temporal ordering information, our proposed model explicitly leverages the temporal ordering information in video data through temporal alignment. This leads to strong data-efficiency for few-shot learning. In concrete, TAM calculates the distance value of query video with respect to novel …
The temporal component of videos provides an important clue for activity recognition, as a number of activities can be reliably recognized based on the motion information. In view of that, this work proposes a novel temporal stream for two-stream convolutional networks based on images computed from the optical flow magnitude and orientation, named Magnitude-Orientation Stream (MOS), to learn the motion in a better and richer manner. Our method applies simple nonlinear transformations on the vertical and horizontal components of the optical flow to generate input images for the temporal stream.…
We propose a novel approach to few-shot action recognition, finding temporally-corresponding frame tuples between the query and videos in the support set. Distinct from previous few-shot works, we construct class prototypes using the CrossTransformer attention mechanism to observe relevant sub-sequences of all support videos, rather than using class averages or single best matches. Video representations are formed from ordered tuples of varying numbers of frames, which allows sub-sequences of actions at different speeds and temporal offsets to be compared. Our proposed Temporal-Relational Cros…
We present a novel method for few-shot video classification, which performs appearance and temporal alignments. In particular, given a pair of query and support videos, we conduct appearance alignment via frame-level feature matching to achieve the appearance similarity score between the videos, while utilizing temporal order-preserving priors for obtaining the temporal similarity score between the videos. Moreover, we introduce a few-shot video classification framework that leverages the above appearance and temporal similarity scores across multiple steps, namely prototype-based training and…
National Key Lab for Novel Software Technology（新型软件技术国家重点实验室）；Nanjing University（南京大学）
The goal of few-shot video classification is to learn a classification model with good generalization ability when trained with only a few labeled videos. However, it is difficult to learn discriminative feature representations for videos in such a setting. In this paper, we propose Temporal Alignment Prediction (TAP) based on sequence similarity learning for few-shot video classification. In order to obtain the similarity of a pair of videos, we predict the alignment scores between all pairs of temporal positions in the two videos with the temporal alignment prediction function. Besides, the …
Huazhong University of Science and Technology（华中科技大学）；Alibaba Group（阿里巴巴集团）；University of Oxford（牛津大学）
Current developments in temporal event or action localization usually target actions captured by a single camera. However, extensive events or actions in the wild may be captured as a sequence of shots by multiple cameras at different positions. In this paper, we propose a new and challenging task called multi-shot temporal event localization, and accordingly, collect a large scale dataset called MUlti-Shot EventS (MUSES). MUSES has 31,477 event instances for a total of 716 video hours. The core nature of MUSES is the frequent shot cuts, for an average of 19 shots per instance and 176 shots pe…
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…
How to effectively and efficiently deal with spatio-temporal event streams, where the events are generally sparse and non-uniform and have the microsecond temporal resolution, is of great value and has various real-life applications. Spiking neural network (SNN), as one of the brain-inspired event-triggered computing models, has the potential to extract effective spatio-temporal features from the event streams. However, when aggregating individual events into frames with a new higher temporal resolution, existing SNN models do not attach importance to that the serial frames have different sign…
University of Tübingen（图宾根大学）；MPI for Informatics（马克斯·普朗克信息学研究所）；MPI for Intelligent Systems（马克斯·普朗克智能系统研究所）
Audio-visual generalised zero-shot learning for video classification requires understanding the relations between the audio and visual information in order to be able to recognise samples from novel, previously unseen classes at test time. The natural semantic and temporal alignment between audio and visual data in video data can be exploited to learn powerful representations that generalise to unseen classes at test time. We propose a multi-modal and Temporal Cross-attention Framework (\modelName) for audio-visual generalised zero-shot learning. Its inputs are temporally aligned audio and vis…
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…
3D Human body pose and shape estimation within a temporal sequence can be quite critical for understanding human behavior. Despite the significant progress in human pose estimation in the recent years, which are often based on single images or videos, human motion estimation on live stream videos is still a rarely-touched area considering its special requirements for real-time output and temporal consistency. To address this problem, we present a temporally embedded 3D human body pose and shape estimation (TePose) method to improve the accuracy and temporal consistency of pose estimation in li…
Temporal action segmentation (TAS) aims to classify and locate actions in the long untrimmed action sequence. With the success of deep learning, many deep models for action segmentation have emerged. However, few-shot TAS is still a challenging problem. This study proposes an efficient framework for the few-shot skeleton-based TAS, including a data augmentation method and an improved model. The data augmentation approach based on motion interpolation is presented here to solve the problem of insufficient data, and can increase the number of samples significantly by synthesizing action sequence…
Czech Technical University in Prague（捷克布拉格技术大学）；NAVER LABS Europe（NAVER欧洲实验室）
Few-shot action recognition, i.e. recognizing new action classes given only a few examples, benefits from incorporating temporal information. Prior work either encodes such information in the representation itself and learns classifiers at test time, or obtains frame-level features and performs pairwise temporal matching. We first evaluate a number of matching-based approaches using features from spatio-temporal backbones, a comparison missing from the literature, and show that the gap in performance between simple baselines and more complicated methods is significantly reduced. Inspired by th…
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 …
In this paper, we consider the problem of temporal action localization under low-shot (zero-shot & few-shot) scenario, with the goal of detecting and classifying the action instances from arbitrary categories within some untrimmed videos, even not seen at training time. We adopt a Transformer-based two-stage action localization architecture with class-agnostic action proposal, followed by open-vocabulary classification. We make the following contributions. First, to compensate image-text foundation models with temporal motions, we improve category-agnostic action proposal by explicitly alignin…
We address the problem of temporal activity detection in continuous, untrimmed video streams. This is a difficult task that requires extracting meaningful spatio-temporal features to capture activities, accurately localizing the start and end times of each activity. We introduce a new model, Region Convolutional 3D Network (R-C3D), which encodes the video streams using a three-dimensional fully convolutional network, then generates candidate temporal regions containing activities and finally classifies selected regions into specific activities. Computation is saved due to the sharing of convol…
Learning Causal Domain-Invariant Temporal Dynamics for Few-Shot Action Recognition
Boston College（波士顿学院）；Carnegie Mellon University（卡内基梅隆大学）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；Tulane University（杜兰大学）
SVBench: A Benchmark with Temporal Multi-Turn Dialogues for Streaming Video Understanding
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）；Kuaishou Technology（快手科技）；Zhengzhou University（郑州大学）；ShanghaiTech University（上海科技大学）；Peng Cheng Laboratory（鹏城实验室）
UC Santa Barbara（加州大学圣巴巴拉分校）；University of Maryland（马里兰大学）
In this paper, we present a novel Single Shot multi-Span Detector for temporal activity detection in long, untrimmed videos using a simple end-to-end fully three-dimensional convolutional (Conv3D) network. Our architecture, named S3D, encodes the entire video stream and discretizes the output space of temporal activity spans into a set of default spans over different temporal locations and scales. At prediction time, S3D predicts scores for the presence of activity categories in each default span and produces temporal adjustments relative to the span location to predict the precise activity du…
Few-shot learning aims to recognize instances from novel classes with few labeled samples, which has great value in research and application. Although there has been a lot of work in this area recently, most of the existing work is based on image classification tasks. Video-based few-shot action recognition has not been explored well and remains challenging: 1) the differences of implementation details among different papers make a fair comparison difficult; 2) the wide variations and misalignment of temporal sequences make the video-level similarity comparison difficult; 3) the scarcity of la…
While supervised techniques in re-identification are extremely effective, the need for large amounts of annotations makes them impractical for large camera networks. One-shot re-identification, which uses a singular labeled tracklet for each identity along with a pool of unlabeled tracklets, is a potential candidate towards reducing this labeling effort. Current one-shot re-identification methods function by modeling the inter-relationships amongst the labeled and the unlabeled data, but fail to fully exploit such relationships that exist within the pool of unlabeled data itself. In this paper…
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 …
This paper proposes a two-stream convolution network to extract spatial and temporal cues for video based person Re-Identification (ReID). A temporal stream in this network is constructed by inserting several Multi-scale 3D (M3D) convolution layers into a 2D CNN network. The resulting M3D convolution network introduces a fraction of parameters into the 2D CNN, but gains the ability of multi-scale temporal feature learning. With this compact architecture, M3D convolution network is also more efficient and easier to optimize than existing 3D convolution networks. The temporal stream further invo…
Single-Stream Multi-Feature Fusion with Temporal Robustness for Gait Emotion Recognition
College of Computer and Information Science, Southwest University（西南大学计算机与信息科学学院）；College of Physical Science and Technology, Southwest University（西南大学物理科学与技术学院）；Wisesoft Inc.（四川川大智胜软件股份有限公司）
Alibaba Group（阿里巴巴集团）；Twitter（推特）；Huazhong University of Science and Technology（华中科技大学）
Recent attempts mainly focus on learning deep representations for each video individually under the episodic meta-learning regime and then performing temporal alignment to match query and support videos. However, they still suffer from two drawbacks: (i) learning individual features without considering the entire task may result in limited representation capability, and (ii) existing alignment strategies are sensitive to noises and misaligned instances. To handle the two limitations, we propose a novel Hybrid Relation guided temporal Set Matching (HyRSM++) approach for few-shot action recognit…
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）
Recognizing the phases of a laparoscopic surgery (LS) operation form its video constitutes a fundamental step for efficient content representation, indexing and retrieval in surgical video databases. In the literature, most techniques focus on phase segmentation of the entire LS video using hand-crafted visual features, instrument usage signals, and recently convolutional neural networks (CNNs). In this paper we address the problem of phase recognition of short video shots (10s) of the operation, without utilizing information about the preceding/forthcoming video frames, their phase labels or …
Xi’an Jiaotong University（西安交通大学）；Monash University（莫纳什大学）；The University of Queensland（昆士兰大学）；Carnegie Mellon University（卡内基梅隆大学）
An integral part of video analysis and surveillance is temporal activity detection, which means to simultaneously recognize and localize activities in long untrimmed videos. Currently, the most effective methods of temporal activity detection are based on deep learning, and they typically perform very well with large scale annotated videos for training. However, these methods are limited in real applications due to the unavailable videos about certain activity classes and the time-consuming data annotation. To solve this challenging problem, we propose a novel task setting called zero-shot tem…
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…
