Temporal Action Detection with Multi-level Supervision
Peking University（北京大学）；Microsoft Research Asia（微软亚洲研究院）；Georgia Tech（佐治亚理工学院）；Boston University（波士顿大学）；MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）；UC Berkeley（加州大学伯克利分校）
Training temporal action detection in videos requires large amounts of labeled data, yet such annotation is expensive to collect. Incorporating unlabeled or weakly-labeled data to train action detection model could help reduce annotation cost. In this work, we first introduce the Semi-supervised Action Detection (SSAD) task with a mixture of labeled and unlabeled data and analyze different types of errors in the proposed SSAD baselines which are directly adapted from the semi-supervised classification task. To alleviate the main error of action incompleteness (i.e., missing parts of actions) in SSAD baselines, we further design an unsupervised foreground attention (UFA) module utilizing the "independence" between foreground and background motion. Then we incorporate weakly-labeled data into SSAD and propose Omni-supervised Action Detection (OSAD) with three levels of supervision. An information bottleneck (IB) suppressing the scene information in non-action frames while preserving the action information is designed to help overcome the accompanying action-context confusion problem in OSAD baselines. We extensively benchmark against the baselines for SSAD and OSAD on our created data splits in THUMOS14 and ActivityNet1.2, and demonstrate the effectiveness of the proposed UFA and IB methods. Lastly, the benefit of our full OSAD-IB model under limited annotation budgets is shown by exploring the optimal annotation strategy for labeled, unlabeled and weakly-labeled data.
Arizona State University（亚利桑那州立大学）；Carnegie Mellon University（卡内基梅隆大学）；Beihang University（北京航空航天大学）；University of California, Irvine（加利福尼亚大学尔湾分校）
A system capturing the association between video frames and textual queries offer great potential for better video analysis. However, training such a system in a fully supervised way inevitably demands a meticulously curated video dataset with temporal-textual annotations. Therefore we provide a Weak-Supervised alternative with our proposed Referring Attention mechanism to learn temporal-textual association (dubbed WSRA). The weak supervision is simply a textual expression (e.g., short phrases or sentences) at video level, indicating this video contains relevant frames. The referring attention…
We propose a novel domain adaptive action detection approach and a new adaptation protocol that leverages the recent advancements in image-level unsupervised domain adaptation (UDA) techniques and handle vagaries of instance-level video data. Self-training combined with cross-domain mixed sampling has shown remarkable performance gain in semantic segmentation in UDA (unsupervised domain adaptation) context. Motivated by this fact, we propose an approach for human action detection in videos that transfers knowledge from the source domain (annotated dataset) to the target domain (unannotated dat…
University of California, Berkeley（加州大学伯克利分校）；Boston University（波士顿大学）
Spatio-temporal action detection in videos requires localizing the action both spatially and temporally in the form of an "action tube". Nowadays, most spatio-temporal action detection datasets (e.g. UCF101-24, AVA, DALY) are annotated with action tubes that contain a single person performing the action, thus the predominant action detection models simply employ a person detection and tracking pipeline for localization. However, when the action is defined as an interaction between multiple objects, such methods may fail since each bounding box in the action tube contains multiple objects inste…
University of Electronic Science and Technology of China（电子科技大学）；Northeastern University（东北大学）
Temporal action detection aims at not only recognizing action category but also detecting start time and end time for each action instance in an untrimmed video. The key challenge of this task is to accurately classify the action and determine the temporal boundaries of each action instance. In temporal action detection benchmark: THUMOS 2014, large variations exist in the same action category while many similarities exist in different action categories, which always limit the performance of temporal action detection. To address this problem, we propose to use joint Identification-Verification…
We present a semi-supervised learning approach to the temporal action segmentation task. The goal of the task is to temporally detect and segment actions in long, untrimmed procedural videos, where only a small set of videos are densely labelled, and a large collection of videos are unlabelled. To this end, we propose two novel loss functions for the unlabelled data: an action affinity loss and an action continuity loss. The action affinity loss guides the unlabelled samples learning by imposing the action priors induced from the labelled set. Action continuity loss enforces the temporal conti…
Technische Universität München（慕尼黑工业大学）；Google（谷歌）
The video action segmentation task is regularly explored under weaker forms of supervision, such as transcript supervision, where a list of actions is easier to obtain than dense frame-wise labels. In this formulation, the task presents various challenges for sequence modeling approaches due to the emphasis on action transition points, long sequence lengths, and frame contextualization, making the task well-posed for transformers. Given developments enabling transformers to scale linearly, we demonstrate through our architecture how they can be applied to improve action alignment accuracy over…
The goal of this work is spatio-temporal action localization in videos, using only the supervision from video-level class labels. The state-of-the-art casts this weakly-supervised action localization regime as a Multiple Instance Learning problem, where instances are a priori computed spatio-temporal proposals. Rather than disconnecting the spatio-temporal learning from the training, we propose Spatio-Temporal Instance Learning, which enables action localization directly from box proposals in video frames. We outline the assumptions of our model and propose a max-margin objective and optimizat…
Adobe Research（Adobe研究院）；University of Surrey（萨里大学）
We propose a self-supervised learning approach for videos that learns representations of both the RGB frames and the accompanying audio without human supervision. In contrast to images that capture the static scene appearance, videos also contain sound and temporal scene dynamics. To leverage the temporal and aural dimension inherent to videos, our method extends temporal self-supervision to the audio-visual setting and integrates it with multi-modal contrastive objectives. As temporal self-supervision, we pose playback speed and direction recognition in both modalities and propose intra- and …
Information Engineering College, Capital Normal University（首都师范大学信息工程学院）；State Key Lab of Software Development Environment, School of Computer Science and Engineering, Beihang University（北京航空航天大学计算机学院软件开发环境国家重点实验室）；Computer Vision Perception Department of ZongMu Technology（纵目科技计算机视觉感知部）
In recent years, 2D Convolutional Networks-based video action recognition has encouragingly gained wide popularity; However, constrained by the lack of long-range non-linear temporal relation modeling and reverse motion information modeling, the performance of existing models is, therefore, undercut seriously. To address this urgent problem, we introduce a startling Temporal Transformer Network with Self-supervision (TTSN). Our high-performance TTSN mainly consists of a temporal transformer module and a temporal sequence self-supervision module. Concisely speaking, we utilize the efficient tem…
University of Bonn（波恩大学）；Microsoft（微软）；Birzeit University（比尔宰特大学）；Toyota Motor Europe（丰田汽车欧洲公司）
Action segmentation is the task of predicting an action label for each frame of an untrimmed video. As obtaining annotations to train an approach for action segmentation in a fully supervised way is expensive, various approaches have been proposed to train action segmentation models using different forms of weak supervision, e.g., action transcripts, action sets, or more recently timestamps. Timestamp supervision is a promising type of weak supervision as obtaining one timestamp per action is less expensive than annotating all frames, but it provides more information than other forms of weak s…
In temporal action segmentation, Timestamp supervision requires only a handful of labelled frames per video sequence. For unlabelled frames, previous works rely on assigning hard labels, and performance rapidly collapses under subtle violations of the annotation assumptions. We propose a novel Expectation-Maximization (EM) based approach that leverages the label uncertainty of unlabelled frames and is robust enough to accommodate possible annotation errors. With accurate timestamp annotations, our proposed method produces SOTA results and even exceeds the fully-supervised setup in several metr…
University of Bristol（布里斯托大学）；University of Toronto（多伦多大学）；NVIDIA（英伟达）；Vector Institute（向量研究所）
Recognising actions in videos relies on labelled supervision during training, typically the start and end times of each action instance. This supervision is not only subjective, but also expensive to acquire. Weak video-level supervision has been successfully exploited for recognition in untrimmed videos, however it is challenged when the number of different actions in training videos increases. We propose a method that is supervised by single timestamps located around each action instance, in untrimmed videos. We replace expensive action bounds with sampling distributions initialised from the…
Xerox Research Centre Europe（施乐欧洲研究中心）；Inria（法国国家信息与自动化研究所）
We introduce an approach for spatio-temporal human action localization using sparse spatial supervision. Our method leverages the large amount of annotated humans available today and extracts human tubes by combining a state-of-the-art human detector with a tracking-by-detection approach. Given these high-quality human tubes and temporal supervision, we select positive and negative tubes with very sparse spatial supervision, i.e., only one spatially annotated frame per instance. The selected tubes allow us to effectively learn a spatio-temporal action detector based on dense trajectories or CN…
Modern self-supervised learning algorithms typically enforce persistency of instance representations across views. While being very effective on learning holistic image and video representations, such an objective becomes sub-optimal for learning spatio-temporally fine-grained features in videos, where scenes and instances evolve through space and time. In this paper, we present Contextualized Spatio-Temporal Contrastive Learning (ConST-CL) to effectively learn spatio-temporally fine-grained video representations via self-supervision. We first design a region-based pretext task which requires …
Temporal action segmentation approaches have been very successful recently. However, annotating videos with frame-wise labels to train such models is very expensive and time consuming. While weakly supervised methods trained using only ordered action lists require less annotation effort, the performance is still worse than fully supervised approaches. In this paper, we propose to use timestamp supervision for the temporal action segmentation task. Timestamps require a comparable annotation effort to weakly supervised approaches, and yet provide a more supervisory signal. To demonstrate the eff…
Is it possible to guess human action from dialogue alone? In this work we investigate the link between spoken words and actions in movies. We note that movie screenplays describe actions, as well as contain the speech of characters and hence can be used to learn this correlation with no additional supervision. We train a BERT-based Speech2Action classifier on over a thousand movie screenplays, to predict action labels from transcribed speech segments. We then apply this model to the speech segments of a large unlabelled movie corpus (188M speech segments from 288K movies). Using the prediction…
Weakly supervised temporal action localization aims at learning the instance-level action pattern from the video-level labels, where a significant challenge is action-context confusion. To overcome this challenge, one recent work builds an action-click supervision framework. It requires similar annotation costs but can steadily improve the localization performance when compared to the conventional weakly supervised methods. In this paper, by revealing that the performance bottleneck of the existing approaches mainly comes from the background errors, we find that a stronger action localizer can…
Nanyang Technological University（南洋理工大学）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）
Video semantic segmentation has achieved great progress under the supervision of large amounts of labelled training data. However, domain adaptive video segmentation, which can mitigate data labelling constraints by adapting from a labelled source domain toward an unlabelled target domain, is largely neglected. We design temporal pseudo supervision (TPS), a simple and effective method that explores the idea of consistency training for learning effective representations from unlabelled target videos. Unlike traditional consistency training that builds consistency in spatial space, we explore co…
Inria（法国国家信息与自动化研究所）；École normale supérieure（巴黎高等师范学院）；CNRS（法国国家科学研究中心）；PSL Research University（巴黎文理研究大学）；University Grenoble Alpes（格勒诺布尔阿尔卑斯大学）；Grenoble INP（格勒诺布尔国立高等物理、数学与信息学院）
Spatio-temporal action detection in videos is typically addressed in a fully-supervised setup with manual annotation of training videos required at every frame. Since such annotation is extremely tedious and prohibits scalability, there is a clear need to minimize the amount of manual supervision. In this work we propose a unifying framework that can handle and combine varying types of less-demanding weak supervision. Our model is based on discriminative clustering and integrates different types of supervision as constraints on the optimization. We investigate applications of such a model to t…
KAUST（沙特阿拉伯阿卜杜拉国王科技大学）；University of Amsterdam（阿姆斯特丹大学）；Qualcomm Technologies Inc（高通技术公司）
This paper addresses the problem of spatiotemporal localization of actions in videos. Compared to leading approaches, which all learn to localize based on carefully annotated boxes on training video frames, we adhere to a weakly-supervised solution that only requires a video class label. We introduce an actor-supervised architecture that exploits the inherent compositionality of actions in terms of actor transformations, to localize actions. We make two contributions. First, we propose actor proposals derived from a detector for human and non-human actors intended for images, which is linked o…
Multi-modal video question answering aims to predict correct answer and localize the temporal boundary relevant to the question. The temporal annotations of questions improve QA performance and interpretability of recent works, but they are usually empirical and costly. To avoid the temporal annotations, we devise a weakly supervised question grounding (WSQG) setting, where only QA annotations are used and the relevant temporal boundaries are generated according to the temporal attention scores. To substitute the temporal annotations, we transform the correspondence between frames and subtitle…
IIT Delhi（德里印度理工学院）；Florida Institute of Technology（佛罗里达理工学院）
Diagnostic and intervention methodologies for skill assessment of autism typically requires a clinician repetitively initiating several stimuli and recording the child's response. In this paper, we propose to automate the response measurement through video recording of the scene following the use of Deep Neural models for human action recognition from videos. However, supervised learning of neural networks demand large amounts of annotated data that are hard to come by. This issue is addressed by leveraging the `similarities' between the action categories in publicly available large-scale vide…
Huazhong University of Science and Technology（华中科技大学）；MEGVII Technology（旷视科技）
The great progress of 3D object detectors relies on large-scale data and 3D annotations. The annotation cost for 3D bounding boxes is extremely expensive while the 2D ones are easier and cheaper to collect. In this paper, we introduce a hybrid training framework, enabling us to learn a visual 3D object detector with massive 2D (pseudo) labels, even without 3D annotations. To break through the information bottleneck of 2D clues, we explore a new perspective: Temporal 2D Supervision. We propose a temporal 2D transformation to bridge the 3D predictions with temporal 2D labels. Two steps, includin…
College of Electronics and Information Engineering, Shenzhen University（深圳大学电子与信息工程学院）；Guangdong Key Laboratory of Intelligent Information Processing（广东省智能信息处理重点实验室）；Department of Computer and Information Science, University of Macau（澳门大学计算机与信息科学系）；State Key Laboratory of Internet of Things for Smart City（物联网与智慧城市国家重点实验室）
Predicting human motion behavior in a crowd is important for many applications, ranging from the natural navigation of autonomous vehicles to intelligent security systems of video surveillance. All the previous works model and predict the trajectory with a single resolution, which is rather inefficient and difficult to simultaneously exploit the long-range information (e.g., the destination of the trajectory), and the short-range information (e.g., the walking direction and speed at a certain time) of the motion behavior. In this paper, we propose a temporal pyramid network for pedestrian traj…
Action detection and temporal segmentation of actions in videos are topics of increasing interest. While fully supervised systems have gained much attention lately, full annotation of each action within the video is costly and impractical for large amounts of video data. Thus, weakly supervised action detection and temporal segmentation methods are of great importance. While most works in this area assume an ordered sequence of occurring actions to be given, our approach only uses a set of actions. Such action sets provide much less supervision since neither action ordering nor the number of a…
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…
Weakly-supervised temporal action localization aims to localize actions in untrimmed videos with only video-level action category labels. Most of previous methods ignore the incompleteness issue of Class Activation Sequences (CAS), suffering from trivial localization results. To solve this issue, we introduce an adaptive mutual supervision framework (AMS) with two branches, where the base branch adopts CAS to localize the most discriminative action regions, while the supplementary branch localizes the less discriminative action regions through a novel adaptive sampler. The adaptive sampler dyn…
Contrastive Learning under Noisy Temporal Self-Supervision for Colonoscopy Videos
Department of Mathematics, University of Padova, Padova, Italy（帕多瓦大学数学系）；LTCI, Telecom Paris, Institut Polytechnique de Paris, Palaiseau, France（巴黎电信学院）；Cosmo Intelligent Medical Devices, Dublin, Ireland（都柏林智能医疗设备公司）
In this paper, we study an intermediate form of supervision, i.e., single-frame supervision, for temporal action localization (TAL). To obtain the single-frame supervision, the annotators are asked to identify only a single frame within the temporal window of an action. This can significantly reduce the labor cost of obtaining full supervision which requires annotating the action boundary. Compared to the weak supervision that only annotates the video-level label, the single-frame supervision introduces extra temporal action signals while maintaining low annotation overhead. To make full use o…
ARTEMIS: Agent-guided Reliability-aware Temporal Mask Evolution for Imperfectly Supervised Video Polyp Segmentation
Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications, Southeast University, Ministry of Education（东南大学教育部新一代人工智能技术及其跨学科应用重点实验室）；Mohamed bin Zayed University of Artificial Intelligence (MBZUAI)（穆罕默德·本·扎耶德人工智能大学）；School of Medicine, Case Western Reserve University（凯斯西储大学医学院）
University of Amsterdam（阿姆斯特丹大学）；Columbia University（哥伦比亚大学）
The goal of this paper is to determine the spatio-temporal location of actions in video. Where training from hard to obtain box annotations is the norm, we propose an intuitive and effective algorithm that localizes actions from their class label only. We are inspired by recent work showing that unsupervised action proposals selected with human point-supervision perform as well as using expensive box annotations. Rather than asking users to provide point supervision, we propose fully automatic visual cues that replace manual point annotations. We call the cues pseudo-annotations, introduce fiv…
The temporal action segmentation task segments videos temporally and predicts action labels for all frames. Fully supervising such a segmentation model requires dense frame-wise action annotations, which are expensive and tedious to collect. This work is the first to propose a Constituent Action Discovery (CAD) framework that only requires the video-wise high-level complex activity label as supervision for temporal action segmentation. The proposed approach automatically discovers constituent video actions using an activity classification task. Specifically, we define a finite number of latent…
Our work explores temporal self-supervision for GAN-based video generation tasks. While adversarial training successfully yields generative models for a variety of areas, temporal relationships in the generated data are much less explored. Natural temporal changes are crucial for sequential generation tasks, e.g. video super-resolution and unpaired video translation. For the former, state-of-the-art methods often favor simpler norm losses such as $L^2$ over adversarial training. However, their averaging nature easily leads to temporally smooth results with an undesirable lack of spatial detail…
Action QFormer: Structured Representation Shaping under Action Supervision in Vision-Language-Action Models
Shanghai Qizhi Institute（上海期智研究院）；The Chinese University of Hong Kong（香港中文大学）；Hong Kong Embodied AI Lab（香港具身人工智能实验室）；Tsinghua University（清华大学）；University of California, Berkeley（加州大学伯克利分校）
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络空间安全学院）；Youedata Co., Ltd.（优数数据有限公司）；University of Electronic Science and Technology of China（电子科技大学）；University of Science and Technology Beijing（北京科技大学）
Action recognition in videos has attracted a lot of attention in the past decade. In order to learn robust models, previous methods usually assume videos are trimmed as short sequences and require ground-truth annotations of each video frame/sequence, which is quite costly and time-consuming. In this paper, given only video-level annotations, we propose a novel weakly supervised framework to simultaneously locate action frames as well as recognize actions in untrimmed videos. Our proposed framework consists of two major components. First, for action frame localization, we take advantage of the…
Action-Agnostic Point-Level Supervision for Temporal Action Detection
Visual Intelligence Research Laboratories, NEC Corporation（日本电气公司视觉智能研究所）；Graduate School of Information Sciences, Tohoku University（东北大学信息科学研究科）；RIKEN Center for Advanced Intelligence Project（理化学研究所先进智能研究中心）；Graduate School of Frontier Sciences, The University of Tokyo（东京大学前沿科学研究科）
Self-supervised learning has shown great potentials in improving the deep learning model in an unsupervised manner by constructing surrogate supervision signals directly from the unlabeled data. Different from existing works, we present a novel way to obtain the surrogate supervision signal based on high-level feature maps under consistency regularization. In this paper, we propose a Spatio-Temporal Consistency Regularization between different output features generated from a siamese network including a clean path fed with original video and a noise path fed with the corresponding augmented vi…
Understanding temporal dynamics of video is an essential aspect of learning better video representations. Recently, transformer-based architectural designs have been extensively explored for video tasks due to their capability to capture long-term dependency of input sequences. However, we found that these Video Transformers are still biased to learn spatial dynamics rather than temporal ones, and debiasing the spurious correlation is critical for their performance. Based on the observations, we design simple yet effective self-supervised tasks for video models to learn temporal dynamics bette…
Oxford Robotics Institute（牛津机器人研究所）；University of Oxford（牛津大学）
This work explores scene graphs as a distilled representation of high-level information for autonomous driving, applied to future driver-action prediction. Given the scarcity and strong imbalance of data samples, we propose a self-supervision pipeline to infer representative and well-separated embeddings. Key aspects are interpretability and explainability; as such, we embed in our architecture attention mechanisms that can create spatial and temporal heatmaps on the scene graphs. We evaluate our system on the ROAD dataset against a fully-supervised approach, showing the superiority of our tra…
Temporally Consistent Label Interpolation for Robust Surgical Multi-Task Learning under Challenging Conditions
Center for Humanoid Research, Korea Institute of Science and Technology（韩国科学技术研究院仿人机器人研究中心）；School of Electrical and Electronic Engineering, Yonsei University（延世大学电气与电子工程学院）
Inception Institute of Artificial Intelligence（Inception人工智能研究院）
Temporal action localization is a challenging computer vision problem with numerous real-world applications. Most existing methods require laborious frame-level supervision to train action localization models. In this work, we propose a framework, called 3C-Net, which only requires video-level supervision (weak supervision) in the form of action category labels and the corresponding count. We introduce a novel formulation to learn discriminative action features with enhanced localization capabilities. Our joint formulation has three terms: a classification term to ensure the separability of le…
In this paper, we show how to use audio to supervise the learning of active speaker detection in video. Voice Activity Detection (VAD) guides the learning of the vision-based classifier in a weakly supervised manner. The classifier uses spatio-temporal features to encode upper body motion - facial expressions and gesticulations associated with speaking. We further improve a generic model for active speaker detection by learning person specific models. Finally, we demonstrate the online adaptation of generic models learnt on one dataset, to previously unseen people in a new dataset, again using…
Temporal relational modeling in video is essential for human action understanding, such as action recognition and action segmentation. Although Graph Convolution Networks (GCNs) have shown promising advantages in relation reasoning on many tasks, it is still a challenge to apply graph convolution networks on long video sequences effectively. The main reason is that large number of nodes (i.e., video frames) makes GCNs hard to capture and model temporal relations in videos. To tackle this problem, in this paper, we introduce an effective GCN module, Dilated Temporal Graph Reasoning Module (DTGR…
We address weakly supervised action alignment and segmentation in videos, where only the order of occurring actions is available during training. We propose Discriminative Differentiable Dynamic Time Warping (D3TW), the first discriminative model using weak ordering supervision. The key technical challenge for discriminative modeling with weak supervision is that the loss function of the ordering supervision is usually formulated using dynamic programming and is thus not differentiable. We address this challenge with a continuous relaxation of the min-operator in dynamic programming and extend…
