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 framework that considers actions as a set of temporally ordered subclasses and leverages a future frame generation network to cope with the limited information issue associated with the problem outlined above. Additionally, we augment our data by varying the lengths of videos to allow the proposed method to learn about the high intra-class variation in human actions. We evaluate our method using two benchmark datasets, THUMOS'14 and ActivityNet, for an online temporal action localization scenario and demonstrate that the performance is comparable to state-of-the-art methods that have been proposed for offline settings.
Online action detection in untrimmed videos aims to identify an action as it happens, which makes it very important for real-time applications. Previous methods rely on tedious annotations of temporal action boundaries for training, which hinders the scalability of online action detection systems. We propose WOAD, a weakly supervised framework that can be trained using only video-class labels. WOAD contains two jointly-trained modules, i.e., temporal proposal generator (TPG) and online action recognizer (OAR). Supervised by video-class labels, TPG works offline and targets at accurately mining…
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…
Detecting actions in videos have been widely applied in on-device applications. Practical on-device videos are always untrimmed with both action and background. It is desirable for a model to both recognize the class of action and localize the temporal position where the action happens. Such a task is called temporal action location (TAL), which is always trained on the cloud where multiple untrimmed videos are collected and labeled. It is desirable for a TAL model to continuously and locally learn from new data, which can directly improve the action detection precision while protecting custom…
Columbia University（哥伦比亚大学）；Mitsubishi Electric（三菱电机）
Temporal action localization is an important yet challenging problem. Given a long, untrimmed video consisting of multiple action instances and complex background contents, we need not only to recognize their action categories, but also to localize the start time and end time of each instance. Many state-of-the-art systems use segment-level classifiers to select and rank proposal segments of pre-determined boundaries. However, a desirable model should move beyond segment-level and make dense predictions at a fine granularity in time to determine precise temporal boundaries. To this end, we des…
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…
University of Alcalá（阿尔卡拉大学）；Adobe Research（Adobe研究院）；Delft University of Technology（代尔夫特理工大学）
The problem of Online Human Behaviour Recognition in untrimmed videos, aka Online Action Detection (OAD), needs to be revisited. Unlike traditional offline action detection approaches, where the evaluation metrics are clear and well established, in the OAD setting we find few works and no consensus on the evaluation protocols to be used. In this paper we introduce a novel online metric, the Instantaneous Accuracy ($IA$), that exhibits an \emph{online} nature, solving most of the limitations of the previous (offline) metrics. We conduct a thorough experimental evaluation on TVSeries dataset, co…
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…
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…
School of Electrical and Electronic Engineering（电气与电子工程学院）
Online Temporal Action Localization (On-TAL) aims to immediately provide action instances from untrimmed streaming videos. The model is not allowed to utilize future frames and any processing techniques to modify past predictions, making On-TAL much more challenging. In this paper, we propose a simple yet effective framework, termed SimOn, that learns to predict action instances using the popular Transformer architecture in an end-to-end manner. Specifically, the model takes the current frame feature as a query and a set of past context information as keys and values of the Transformer. Differ…
University of Maryland（马里兰大学）；Indiana University（印第安纳大学）；Salesforce Research（Salesforce研究院）
We propose StartNet to address Online Detection of Action Start (ODAS) where action starts and their associated categories are detected in untrimmed, streaming videos. Previous methods aim to localize action starts by learning feature representations that can directly separate the start point from its preceding background. It is challenging due to the subtle appearance difference near the action starts and the lack of training data. Instead, StartNet decomposes ODAS into two stages: action classification (using ClsNet) and start point localization (using LocNet). ClsNet focuses on per-frame la…
State University of New York at Buffalo（纽约州立大学布法罗分校）
This technical report presents our solution to the HACS Temporal Action Localization Challenge 2021, Weakly-Supervised Learning Track. The goal of weakly-supervised temporal action localization is to temporally locate and classify action of interest in untrimmed videos given only video-level labels. We adopt the two-stream consensus network (TSCN) as the main framework in this challenge. The TSCN consists of a two-stream base model training procedure and a pseudo ground truth learning procedure. The base model training encourages the model to predict reliable predictions based on single modali…
Adobe Research（Adobe研究院）；Delft University of Technology（代尔夫特理工大学）
The Online Action Detection (OAD) problem needs to be revisited. Unlike traditional offline action detection approaches, where the evaluation metrics are clear and well established, in the OAD setting we find very few works and no consensus on the evaluation protocols to be used. In this work we propose to rethink the OAD scenario, clearly defining the problem itself and the main characteristics that the models which are considered online must comply with. We also introduce a novel metric: the Instantaneous Accuracy ($IA$). This new metric exhibits an \emph{online} nature and solves most of th…
School of Cyber Science and Engineering, Southeast University（东南大学信息科学与工程学院）；Engineering Research Center of Blockchain Application, Supervision and Management (Southeast University), Ministry of Education（教育部区块链应用、监督与管理工程研究中心（东南大学））；Purple Mountain Laboratories, Nanjing（紫金山实验室（南京））；School of Computer Science and Engineering, Southeast University（东南大学计算机科学与工程学院）
Peking University（北京大学）；Microsoft Research Asia（微软亚洲研究院）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）
Human action recognition from well-segmented 3D skeleton data has been intensively studied and has been attracting an increasing attention. Online action detection goes one step further and is more challenging, which identifies the action type and localizes the action positions on the fly from the untrimmed stream data. In this paper, we study the problem of online action detection from streaming skeleton data. We propose a multi-task end-to-end Joint Classification-Regression Recurrent Neural Network to better explore the action type and temporal localization information. By employing a joint…
LiveVLM: Efficient Online Video Understanding via Streaming-Oriented KV Cache and Retrieval
School of Computer Science, Shanghai Jiao Tong University（上海交通大学计算机科学学院）；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）；Guizhou Provincial Laboratory of Big Data, College of Computer Science and Technology, Guizhou University（贵州大数据省实验室，贵州大学计算机科学与技术学院）
MacJEPA: Missingness-Robust Audio-Visual Recognition from Untrimmed Egocentric Videos
Peter L. Reichertz Institute for Medical Informatics, Hannover Medical School（汉诺威医学院彼得·L·赖歇茨医学信息学研究所）；Lower Saxony Center for Artificial Intelligence and Causal Methods in Medicine (CAIMed)（下萨克森州医学人工智能与因果方法中心（CAIMed））
Universidad de los Andes（安第斯大学）；Adobe Research（Adobe研究院）；King Abdullah University of Science and Technology（阿卜杜拉国王科技大学）
Humans are arguably one of the most important subjects in video streams, many real-world applications such as video summarization or video editing workflows often require the automatic search and retrieval of a person of interest. Despite tremendous efforts in the person reidentification and retrieval domains, few works have developed audiovisual search strategies. In this paper, we present the Audiovisual Person Search dataset (APES), a new dataset composed of untrimmed videos whose audio (voices) and visual (faces) streams are densely annotated. APES contains over 1.9K identities labeled alo…
Center for Research in Computer Vision（计算机视觉研究中心）；University of Central Florida（中佛罗里达大学）
Activity detection in security videos is a difficult problem due to multiple factors such as large field of view, presence of multiple activities, varying scales and viewpoints, and its untrimmed nature. The existing research in activity detection is mainly focused on datasets, such as UCF-101, JHMDB, THUMOS, and AVA, which partially address these issues. The requirement of processing the security videos in real-time makes this even more challenging. In this work we propose Gabriella, a real-time online system to perform activity detection on untrimmed security videos. The proposed method cons…
LiveStar: Live Streaming Assistant for Real-World Online 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）；ShanghaiTech University（上海科技大学）；Kuaishou Technology（快手科技）；Peng Cheng Laboratory（鹏城实验室）
Color When It Counts: Grayscale-Guided Online Triggering for Always-On Streaming Video Sensing
Queen Mary University of London（伦敦皇后玛丽大学）；Independent Researcher（独立研究者）；Durham University（杜伦大学）；Imperial College London（伦敦帝国学院）；Huawei Noah’s Ark Lab（华为诺亚实验室）
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…
IBM Almaden Research Center（IBM阿尔马登研究中心）；Arizona State University（亚利桑那州立大学）
Many applications benefit from sampling algorithms where a small number of well chosen samples are used to generalize different properties of a large dataset. In this paper, we use diverse sampling for streaming video summarization. Several emerging applications support streaming video, but existing summarization algorithms need access to the entire video which requires a lot of memory and computational power. We propose a memory efficient and computationally fast, online algorithm that uses competitive learning for diverse sampling. Our algorithm is a generalization of online K-means such tha…
MICC – Media Integration and Communcation Center（MICC – 媒体整合与通信中心）；University Of Florence（佛罗伦萨大学）
We present a novel online unsupervised method for face identity learning from video streams. The method exploits deep face descriptors together with a memory based learning mechanism that takes advantage of the temporal coherence of visual data. Specifically, we introduce a discriminative feature matching solution based on Reverse Nearest Neighbour and a feature forgetting strategy that detect redundant features and discard them appropriately while time progresses. It is shown that the proposed learning procedure is asymptotically stable and can be effectively used in relevant applications lik…
Oxford Brookes University（牛津布鲁克斯大学）；University of Oxford（牛津大学）；Samsung Research America（三星美国研究院）
We present a deep-learning framework for real-time multiple spatio-temporal (S/T) action localisation, classification and early prediction. Current state-of-the-art approaches work offline and are too slow to be useful in real- world settings. To overcome their limitations we introduce two major developments. Firstly, we adopt real-time SSD (Single Shot MultiBox Detector) convolutional neural networks to regress and classify detection boxes in each video frame potentially containing an action of interest. Secondly, we design an original and efficient online algorithm to incrementally construct…
University of California, Irvine（加利福尼亚大学尔湾分校）；Carnegie Mellon University（卡内基梅隆大学）
We formulate tracking as an online decision-making process, where a tracking agent must follow an object despite ambiguous image frames and a limited computational budget. Crucially, the agent must decide where to look in the upcoming frames, when to reinitialize because it believes the target has been lost, and when to update its appearance model for the tracked object. Such decisions are typically made heuristically. Instead, we propose to learn an optimal decision-making policy by formulating tracking as a partially observable decision-making process (POMDP). We learn policies with deep rei…
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…
Label-Efficient Online Continual Object Detection in Streaming Video
Show Lab（Show实验室）；National University of Singapore（新加坡国立大学）；Nanyang Technological University（南洋理工大学）；Agency for Science, Technology and Research（科学技术研究局）
Spatial-Temporal Decoupled Adapter for Micro-gesture Online Recognition
Hefei University of Technology（合肥工业大学）；United Arab Emirates University（阿联酋大学）；Institute of Artificial Intelligence, Hefei Comprehensive National Science Center（人工智能研究院，合肥国家综合科学中心）；Anhui Evolution Technology Co., Ltd.（安徽进化科技有限公司）
Activity detection is one of the attractive computer vision tasks to exploit the video streams captured by widely installed cameras. Although achieving impressive performance, conventional activity detection algorithms are usually designed under certain constraints, such as using trimmed and/or object-centered video clips as inputs. Therefore, they failed to deal with the multi-scale multi-instance cases in real-world unconstrained video streams, which are untrimmed and have large field-of-views. Real-time requirements for streaming analysis also mark brute force expansion of them unfeasible. …
IRIT, CNRS（法国国家科学研究中心图卢兹计算机科学研究所）；University of Toulouse（图卢兹大学）
Temporal segmentation of untrimmed videos and photo-streams is currently an active area of research in computer vision and image processing. This paper proposes a new approach to improve the temporal segmentation of photo-streams. The method consists in enhancing image representations by encoding long-range temporal dependencies. Our key contribution is to take advantage of the temporal stationarity assumption of photostreams for modeling each frame by its nonlocal self-similarity function. The proposed approach is put to test on the EDUB-Seg dataset, a standard benchmark for egocentric photos…
Online Streaming Video Super-Resolution with Convolutional Look-Up Table
Zhejiang University（浙江大学）；Tongji University（同济大学）；University of Science and Technology of China（中国科学技术大学）；Shanghai Jiao Tong University（上海交通大学）；Microsoft Research Asia（微软亚洲研究院）
StreamSplat: Towards Online Dynamic 3D Reconstruction from Uncalibrated Video Streams
University of British Columbia（不列颠哥伦比亚大学）；Vector Institute for AI（人工智能向量研究所）；Canada CIFAR AI Chair（加拿大CIFAR人工智能主席）；Nanyang Technological University（南洋理工大学）
Attaining prototypical features to represent class distributions is well established in representation learning. However, learning prototypes online from streaming data proves a challenging endeavor as they rapidly become outdated, caused by an ever-changing parameter space during the learning process. Additionally, continual learning does not assume the data stream to be stationary, typically resulting in catastrophic forgetting of previous knowledge. As a first, we introduce a system addressing both problems, where prototypes evolve continually in a shared latent space, enabling learning and…
Recognising human activities from streaming videos poses unique challenges to learning algorithms: predictive models need to be scalable, incrementally trainable, and must remain bounded in size even when the data stream is arbitrarily long. Furthermore, as parameter tuning is problematic in a streaming setting, suitable approaches should be parameterless, and make no assumptions on what class labels may occur in the stream. We present here an approach to the recognition of human actions from streaming data which meets all these requirements by: (1) incrementally learning a model which adaptiv…
NAVER CLOVA；NAVER AI Lab（NAVER人工智能实验室）；GIST（光州科学技术院）；Seoul National University（首尔国立大学）；Yonsei University（延世大学）
Learning under a continuously changing data distribution with incorrect labels is a desirable real-world problem yet challenging. A large body of continual learning (CL) methods, however, assumes data streams with clean labels, and online learning scenarios under noisy data streams are yet underexplored. We consider a more practical CL task setup of an online learning from blurry data stream with corrupted labels, where existing CL methods struggle. To address the task, we first argue the importance of both diversity and purity of examples in the episodic memory of continual learning models. T…
