Understanding animals' behaviors is significant for a wide range of applications. However, existing animal behavior datasets have limitations in multiple aspects, including limited numbers of animal classes, data samples and provided tasks, and also limited variations in environmental conditions and viewpoints. To address these limitations, we create a large and diverse dataset, Animal Kingdom, that provides multiple annotated tasks to enable a more thorough understanding of natural animal behaviors. The wild animal footages used in our dataset record different times of the day in extensive range of environments containing variations in backgrounds, viewpoints, illumination and weather conditions. More specifically, our dataset contains 50 hours of annotated videos to localize relevant animal behavior segments in long videos for the video grounding task, 30K video sequences for the fine-grained multi-label action recognition task, and 33K frames for the pose estimation task, which correspond to a diverse range of animals with 850 species across 6 major animal classes. Such a challenging and comprehensive dataset shall be able to facilitate the community to develop, adapt, and evaluate various types of advanced methods for animal behavior analysis. Moreover, we propose a Collaborative Action Recognition (CARe) model that learns general and specific features for action recognition with unseen new animals. This method achieves promising performance in our experiments. Our dataset can be found at https://sutdcv.github.io/Animal-Kingdom.
Prompt When the Animal is: Temporal Animal Behavior Grounding with Positional Recovery Training
School of Artificial Intelligence, Chongqing University of Technology（重庆理工大学人工智能学院）；National Key Laboratory of General Artificial Intelligence, Shenzhen Graduate School, Peking University（北京大学深圳研究生院国家通用人工智能实验室）
AnimalMotionCLIP: Embedding motion in CLIP for Animal Behavior Analysis
Grupo de Tratamiento de Imágenes (GTI), Information Processing and Telecommunications Center, ETSI Telecomunicación, Universidad Politécnica de Madrid（图像处理小组（GTI）、信息处理与电信中心、电信工程学院、马德里理工大学）
VastMAT: A Large-Scale Multi-Category Benchmark for Multi-Animal Tracking
Dalian University of Technology（大连理工大学）；Wuhan University（武汉大学）；University of North Texas（北德克萨斯大学）；The Hong Kong University of Science and Technology（香港科技大学）
AniMer: Animal Pose and Shape Estimation Using Family Aware Transformer
Southern University of Science and Technology（南方科技大学）；China Mobile Research Institute（中国移动研究院）；The Hong Kong University of Science and Technology（香港科技大学）；The University of Hong Kong（香港大学）；Tsinghua University（清华大学）
MoZoo:Unleashing Video Diffusion power in animal fur and muscle simulation
tabular c 1 Tsinghua University 2 University of Glasgow 3 The Chinese University of Hong Kong 4 HUIJING Digital Media \& Entertainment Group 2mm Project Page: tabular
Animal3D: A Comprehensive Dataset of 3D Animal Pose and Shape
Johns Hopkins University（约翰斯·霍普金斯大学）；University of Freiburg（弗莱堡大学）；Beihang University（北京航空航天大学）；HUST（华中科技大学）；University of Oulu（奥卢大学）；University of Alberta（阿尔伯塔大学）；Tsinghua University（清华大学）；UCLA（加州大学洛杉矶分校）；City University of Hong Kong（香港城市大学）；East China Normal University（华东师范大学）；Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）
UniMo: Unifying Human and Animal Motion Generation
The Australian National University（澳大利亚国立大学）；Adelaide University（阿德莱德大学）；Westlake University（西湖大学）；The University of Sydney（悉尼大学）；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）
SketchANIMAR: Sketch-based 3D Animal Fine-Grained Retrieval
University of Science, VNU-HCM（胡志明市国家大学理学院）；Vietnam National University, Ho Chi Minh City（胡志明市国家大学）；University of Dayton（戴顿大学）；University of Information Technology, VNU-HCM（胡志明市国家大学信息技术学院）
AniMer+: Unified Pose and Shape Estimation Across Mammalia and Aves via Family-Aware Transformer
Department of Electronic and Electrical Engineering, Southern University of Science and Technology, Shenzhen, China（南方科技大学电子与电气工程系）；Department of Automation, Tsinghua University, Beijing, China（清华大学自动化系）；Jiaxing Research Institute, Southern University of Science and Technology, Jiaxing, China（南方科技大学嘉兴研究所）；Department of Electrical and Electronic Engineering, the University of Hong Kong, Hong Kong, China（香港大学电子与电气工程系）
UniMC: Taming Diffusion Transformer for Unified Keypoint-Guided Multi-Class Image Generation
The Hong Kong University of Science and Technology（香港科学与技术大学）；The University of Hong Kong（香港大学）；The Chinese University of Hong Kong（香港中文大学）；Peking University（北京大学）；Tencent（腾讯）；National University of Singapore（新加坡国立大学）
Benchmarking pig detection and tracking under diverse and challenging conditions
Chair of Statistics and Econometrics, Faculty of Economics, University of Göttingen, Germany（经济学院统计与计量经济学系，乌特雷赫大学）；Campus Institute Data Science（校园数据科学研究所）；Institute of Animal Breeding and Husbandry, Kiel University, Germany（动物育种与饲养研究所，基尔大学）；Institute of Animal Breeding（动物育种研究所）；work performed during employment at University of Göttingen, Germany（在乌特雷赫大学任职期间的工作）；work performed during employment at Kiel University, Germany（在基尔大学任职期间的工作）
Markerless tracking of user-defined features with deep learning
Eberhard Karls Universität Tübingen（图宾根大学）；Harvard University（哈佛大学）；Columbia University（哥伦比亚大学）；The Rowland Institute at Harvard, Harvard University（哈佛大学罗兰研究所）；Max Planck Institute for Biological Cybernetics（马克斯·普朗克生物控制论研究所）；Baylor College of Medicine（贝勒医学院）
