Video-based visual relation detection tasks, such as video scene graph generation, play important roles in fine-grained video understanding. However, current video visual relation detection datasets have two main limitations that hinder the progress of research in this area. First, they do not explore complex human-human interactions in multi-person scenarios. Second, the relation types of existing datasets have relatively low-level semantics and can be often recognized by appearance or simple prior information, without the need for detailed spatio-temporal context reasoning. Nevertheless, comprehending high-level interactions between humans is crucial for understanding complex multi-person videos, such as sports and surveillance videos. To address this issue, we propose a new video visual relation detection task: video human-human interaction detection, and build a dataset named SportsHHI for it. SportsHHI contains 34 high-level interaction classes from basketball and volleyball sports. 118,075 human bounding boxes and 50,649 interaction instances are annotated on 11,398 keyframes. To benchmark this, we propose a two-stage baseline method and conduct extensive experiments to reveal the key factors for a successful human-human interaction detector. We hope that SportsHHI can stimulate research on human interaction understanding in videos and promote the development of spatio-temporal context modeling techniques in video visual relation detection.
Beihang University（北京航空航天大学）；Hangzhou Innovation Institute, Beihang University（北京航空航天大学杭州创新研究院）；National Computer Network Emergency Response Technical Team/Coordination Center of China（国家计算机网络应急技术处理协调中心）
Tracking multiple athletes in sports videos is a very challenging Multi-Object Tracking (MOT) task, since athletes often have the same appearance and are intimately covered with each other, making a common occlusion problem becomes an abhorrent duplicate detection. In this paper, the duplicate detection is newly and precisely defined as occlusion misreporting on the same athlete by multiple detection boxes in one frame. To address this problem, we meticulously design a novel transformer-based Duplicate Detection Decontaminator (D$^3$) for training, and a specific algorithm Rally-Hungarian (RH)…
ShanghaiTech University（上海科技大学）；Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences（中国科学院上海微系统与信息技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Huazhong University of Science and Technology（华中科技大学）
Markerless motion capture and understanding of professional non-daily human movements is an important yet unsolved task, which suffers from complex motion patterns and severe self-occlusion, especially for the monocular setting. In this paper, we propose SportsCap -- the first approach for simultaneously capturing 3D human motions and understanding fine-grained actions from monocular challenging sports video input. Our approach utilizes the semantic and temporally structured sub-motion prior in the embedding space for motion capture and understanding in a data-driven multi-task manner. To enab…
State Key Laboratory for Novel Software Technology, Nanjing University（南京大学计算机软件新技术国家重点实验室）
Spatio-temporal action detection is an important and challenging problem in video understanding. The existing action detection benchmarks are limited in aspects of small numbers of instances in a trimmed video or low-level atomic actions. This paper aims to present a new multi-person dataset of spatio-temporal localized sports actions, coined as MultiSports. We first analyze the important ingredients of constructing a realistic and challenging dataset for spatio-temporal action detection by proposing three criteria: (1) multi-person scenes and motion dependent identification, (2) with well-def…
This paper targets at learning to score the figure skating sports videos. To address this task, we propose a deep architecture that includes two complementary components, i.e., Self-Attentive LSTM and Multi-scale Convolutional Skip LSTM. These two components can efficiently learn the local and global sequential information in each video. Furthermore, we present a large-scale figure skating sports video dataset -- FisV dataset. This dataset includes 500 figure skating videos with the average length of 2 minutes and 50 seconds. Each video is annotated by two scores of nine different referees, i.…
DeepSport: A Multimodal Large Language Model for Comprehensive Sports Video Reasoning via Agentic Reinforcement Learning
Georgia Institute of Technology（佐治亚理工学院）；Rice University（Rice大学）；Johns Hopkins University（约翰霍普金斯大学）；University of California, Irvine（加州大学 Irvine分校）；University of California, Santa Barbara（加州大学圣巴巴拉分校）
Biomechanical-phase based Temporal Segmentation in Sports Videos: a Demonstration on Javelin-Throw
Department of Physics Indian Institute of Technology Gandhinagar Gandhinagar, India（物理系 印度理工学院加尔各答分校 加尔各答, 印度）；Department of Electrical Engineering Indian Institute of Technology Gandhinagar Gandhinagar, India（电气工程系 印度理工学院加尔各答分校 加尔各答, 印度）；Department of Mathematics IISER Berhampur Brahmapur, India（数学系 印度国家科学研究院伯哈马普尔 布拉哈马普尔, 印度）
Max Planck Institute for Evolutionary Anthropology（马克斯·普朗克进化人类学研究所）；La Rochelle University（拉罗谢尔大学）；University of Bordeaux（波尔多大学）；CNRS（法国国家科学研究中心）；Bordeaux INP（波尔多国立理工学院）
Sports video analysis is a widespread research topic. Its applications are very diverse, like events detection during a match, video summary, or fine-grained movement analysis of athletes. As part of the MediaEval 2022 benchmarking initiative, this task aims at detecting and classifying subtle movements from sport videos. We focus on recordings of table tennis matches. Conducted since 2019, this task provides a classification challenge from untrimmed videos recorded under natural conditions with known temporal boundaries for each stroke. Since 2021, the task also provides a stroke detection ch…
Max Planck Institute for Evolutionary Anthropology（马克斯·普朗克进化人类学研究所）
This paper presents the baseline method proposed for the Sports Video task part of the MediaEval 2021 benchmark. This task proposes a stroke detection and a stroke classification subtasks. This baseline addresses both subtasks. The spatio-temporal CNN architecture and the training process of the model are tailored according to the addressed subtask. The method has the purpose of helping the participants to solve the task and is not meant to reach stateof-the-art performance. Still, for the detection task, the baseline is performing better than the other participants, which stresses the difficu…
Athlete performance measurement in sports videos requires modeling long sequences since the entire spatio-temporal progression contributes dominantly to the performance. It is crucial to comprehend local discriminative spatial dependencies and global semantics for accurate evaluation. However, existing benchmark datasets mainly incorporate sports where the performance lasts only a few seconds. Consequently, state-ofthe-art sports quality assessment methods specifically focus on spatial structure. Although they achieve high performance in short-term sports, they are unable to model prolonged vi…
National Tsing Hua University（台湾清华大学）；NVIDIA research（英伟达研究院）；National Chiao Tung University（台湾交通大学）
Watching a 360° sports video requires a viewer to continuously select a viewing angle, either through a sequence of mouse clicks or head movements. To relieve the viewer from this "360 piloting" task, we propose "deep 360 pilot" -- a deep learning-based agent for piloting through 360° sports videos automatically. At each frame, the agent observes a panoramic image and has the knowledge of previously selected viewing angles. The task of the agent is to shift the current viewing angle (i.e. action) to the next preferred one (i.e., goal). We propose to directly learn an online policy of the agent…
Dalian University of Technology（大连理工大学）；Tsinghua University of Technology（清华大学理工学院）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）
Action recognition is an important and challenging problem in video analysis. Although the past decade has witnessed progress in action recognition with the development of deep learning, such process has been slow in competitive sports content analysis. To promote the research on action recognition from competitive sports video clips, we introduce a Figure Skating Dataset (FSD-10) for finegrained sports content analysis. To this end, we collect 1484 clips from the worldwide figure skating championships in 2017-2018, which consist of 10 different actions in men/ladies programs. Each clip is at …
National Institute of Technology, Warangal（瓦朗加尔国家理工学院）；Aarhus University（奥胡斯大学）
Recent developments in video analysis of sports and computer vision techniques have achieved significant improvements to enable a variety of critical operations. To provide enhanced information, such as detailed complex analysis in sports like soccer, basketball, cricket, badminton, etc., studies have focused mainly on computer vision techniques employed to carry out different tasks. This paper presents a comprehensive review of sports video analysis for various applications high-level analysis such as detection and classification of players, tracking player or ball in sports and predicting th…
Kalyani Government Engineering College（卡里亚尼政府工程学院）；University of Malaya（马来亚大学）；Indian Statistical Institute（印度统计研究所）；Nanjing University（南京大学）；University of Technology Sydney（悉尼科技大学）
Detecting text located on the torsos of marathon runners and sports players in video is a challenging issue due to poor quality and adverse effects caused by flexible/colorful clothing, and different structures of human bodies or actions. This paper presents a new unified method for tackling the above challenges. The proposed method fuses gradient magnitude and direction coherence of text pixels in a new way for detecting candidate regions. Candidate regions are used for determining the number of temporal frame clusters obtained by K-means clustering on frame differences. This process in turn …
SwimXYZ: A large-scale dataset of synthetic swimming motions and videos
CentraleSupélec（巴黎中央理工-高等电力学院）；IETR UMR CNRS 6164（法国国家科学研究中心雷恩电子与电信研究所（UMR 6164））；Centrale Nantes（南特中央理工学院）；Université Technologique de Compiègne（贡比涅技术大学）
Alibaba Business School, Hangzhou Normal University（杭州师范大学阿里巴巴商学院）；Keep Inc.（Keep公司）；Beihang University（北京航空航天大学）
Human pose estimation has made significant advancement in recent years. However, the existing datasets are limited in their coverage of pose variety. In this paper, we introduce a novel benchmark FollowMeUp Sports that makes an important advance in terms of specific postures, self-occlusion and class balance, a contribution that we feel is required for future development in human body models. This comprehensive dataset was collected using an established taxonomy of over 200 standard workout activities with three different shot angles. The collected videos cover a wider variety of specific work…
Group activity detection in soccer can be done by using either video data or player and ball trajectory data. In current soccer activity datasets, activities are labelled as atomic events without a duration. Given that the state-of-the-art activity detection methods are not well-defined for atomic actions, these methods cannot be used. In this work, we evaluated the effectiveness of activity recognition models for detecting such events, by using an intuitive non-maximum suppression process and evaluation metrics. We also considered the problem of explicitly modeling interactions between player…
With the recent development of Deep Learning applied to Computer Vision, sport video understanding has gained a lot of attention, providing much richer information for both sport consumers and leagues. This paper introduces DeepSportradar-v1, a suite of computer vision tasks, datasets and benchmarks for automated sport understanding. The main purpose of this framework is to close the gap between academic research and real world settings. To this end, the datasets provide high-resolution raw images, camera parameters and high quality annotations. DeepSportradar currently supports four challengi…
FineQuest: Adaptive Knowledge-Assisted Sports Video Understanding via Agent-of-Thoughts Reasoning
School of Automation, Northwestern Polytechnical University（自动化学院，西北工业大学）；The University of Hong Kong（香港大学）；School of Software, Northwestern Polytechnical University（软件学院，西北工业大学）；Unmanned System Research Institute, Northwestern Polytechnical University（无人系统研究院，西北工业大学）
Human pose is a useful feature for fine-grained sports action understanding. However, pose estimators are often unreliable when run on sports video due to domain shift and factors such as motion blur and occlusions. This leads to poor accuracy when downstream tasks, such as action recognition, depend on pose. End-to-end learning circumvents pose, but requires more labels to generalize. We introduce Video Pose Distillation (VPD), a weakly-supervised technique to learn features for new video domains, such as individual sports that challenge pose estimation. Under VPD, a student network learns to…
Nara Institute of Science and Technology（奈良先端科学技术大学院大学）；University of Oulu（奥卢大学）；Tampere University of Technology（坦佩雷理工大学）
Automatically generating a summary of sports video poses the challenge of detecting interesting moments, or highlights, of a game. Traditional sports video summarization methods leverage editing conventions of broadcast sports video that facilitate the extraction of high-level semantics. However, user-generated videos are not edited, and thus traditional methods are not suitable to generate a summary. In order to solve this problem, this work proposes a novel video summarization method that uses players' actions as a cue to determine the highlights of the original video. A deep neural network-…
Towards Temporal Compositional Reasoning in Long-Form Sports Videos
School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；MAIS, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所MAIS）
University of Pittsburgh（匹兹堡大学）；York University（约克大学）；École Polytechnique Fédérale de Lausanne (EPFL)（洛桑联邦理工学院）
This paper investigates the modeling of automated machine description on sports video, which has seen much progress recently. Nevertheless, state-of-the-art approaches fall quite short of capturing how human experts analyze sports scenes. There are several major reasons: (1) The used dataset is collected from non-official providers, which naturally creates a gap between models trained on those datasets and real-world applications; (2) previously proposed methods require extensive annotation efforts (i.e., player and ball segmentation at pixel level) on localizing useful visual features to yiel…
In problems such as sports video analytics, it is difficult to obtain accurate frame level annotations and exact event duration because of the lengthy videos and sheer volume of video data. This issue is even more pronounced in fast-paced sports such as ice hockey. Obtaining annotations on a coarse scale can be much more practical and time efficient. We propose the task of event detection in coarsely annotated videos. We introduce a multi-tower temporal convolutional network architecture for the proposed task. The network, with the help of multiple receptive fields, processes information at va…
OSL-ActionSpotting: A Unified Library for Action Spotting in Sports Videos
Montefiore Institute, University of Liège（列日大学蒙泰菲奥里研究所）；Cinfo & CITIC Research Center, University of A Coruña（拉科鲁尼亚大学Cinfo与CITIC研究中心）；IVUL, KAUST（阿卜杜拉国王科技大学IVUL）
IIT Roorkee（印度理工学院鲁尔基分校）；Princeton University（普林斯顿大学）；University of Toronto（多伦多大学）
Existing benchmarks for evaluating long video understanding falls short on two critical aspects, either lacking in scale or quality of annotations. These limitations arise from the difficulty in collecting dense annotations for long videos, which often require manually labeling each frame. In this work, we introduce an automated Annotation and Video Stream Alignment Pipeline (abbreviated ASAP). We demonstrate the generality of ASAP by aligning unlabeled videos of four different sports with corresponding freely available dense web annotations (i.e. commentary). We then leverage ASAP scalability…
Sports channel video portals offer an exciting domain for research on multimodal, multilingual analysis. We present methods addressing the problem of automatic video highlight prediction based on joint visual features and textual analysis of the real-world audience discourse with complex slang, in both English and traditional Chinese. We present a novel dataset based on League of Legends championships recorded from North American and Taiwanese Twitch.tv channels (will be released for further research), and demonstrate strong results on these using multimodal, character-level CNN-RNN model arch…
To date, machine learning for human action recognition in video has been widely implemented in sports activities. Although some studies have been successful in the past, precision is still the most significant concern. In this study, we present a high-accuracy framework to automatically clip the sports video stream by using a three-level prediction algorithm based on two classical open-source structures, i.e., YOLO-v3 and OpenPose. It is found that by using a modest amount of sports video training data, our methodology can perform sports activity highlights clipping accurately. Comparing with …
University of São Paulo（圣保罗大学）；CNRS（法国国家科学研究中心）；Télécom ParisTech（巴黎电信学院）
In this paper, we propose a novel approach for exploiting structural relations to track multiple objects that may undergo long-term occlusion and abrupt motion. We use a model-free approach that relies only on annotations given in the first frame of the video to track all the objects online, i.e. without knowledge from future frames. We initialize a probabilistic Attributed Relational Graph (ARG) from the first frame, which is incrementally updated along the video. Instead of using the structural information only to evaluate the scene, the proposed approach considers it to generate new trackin…
University of British Columbia（不列颠哥伦比亚大学）；Zhejiang University（浙江大学）
We present an online SLAM system specifically designed to track pan-tilt-zoom (PTZ) cameras in highly dynamic sports such as basketball and soccer games. In these games, PTZ cameras rotate very fast and players cover large image areas. To overcome these challenges, we propose to use a novel camera model for tracking and to use rays as landmarks in mapping. Rays overcome the missing depth in pure-rotation cameras. We also develop an online pan-tilt forest for mapping and introduce moving objects (players) detection to mitigate negative impacts from foreground objects. We test our method on both…
IBM Research AI（IBM研究人工智能）；Japan Institute of Sports Sciences（日本体育科学研究所）
Image-based sports analytics enable automatic retrieval of key events in a game to speed up the analytics process for human experts. However, most existing methods focus on structured television broadcast video datasets with a straight and fixed camera having minimum variability in the capturing pose. In this paper, we study the case of event detection in sports videos for unstructured environments with arbitrary camera angles. The transition from structured to unstructured video analysis produces multiple challenges that we address in our paper. Specifically, we identify and solve two major p…
