End-to-end learning has taken hold of many computer vision tasks, in particular, related to still images, with task-specific optimization yielding very strong performance. Nevertheless, human-centric action recognition is still largely dominated by hand-crafted pipelines, and only individual components are replaced by neural networks that typically operate on individual frames. As a testbed to study the relevance of such pipelines, we present a new fully annotated video dataset of fitness activities. Any recognition capabilities in this domain are almost exclusively a function of human poses and their temporal dynamics, so pose-based solutions should perform well. We show that, with this labelled data, end-to-end learning on raw pixels can compete with state-of-the-art action recognition pipelines based on pose estimation. We also show that end-to-end learning can support temporally fine-grained tasks such as real-time repetition counting.
MyoMechanix: Biomechanically-Grounded Compositional Skilled Activity Understanding and Coaching
University of Science and Technology of China(中国科学技术大学);Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Sciences(中国科学院苏州生物医学工程技术研究所);Arexeni Research and Technologies Inc.(Arexeni研究与技术公司);Beijing Sports University(北京体育大学);University of Michigan(密歇根大学)
Sensor Data Augmentation from Skeleton Pose Sequences for Improving Human Activity Recognition
Saarland University(萨尔大学);German Research Center for Artificial Intelligence (DFKI)(德国人工智能研究中心);RPTU Kaiserslautern-Landau(凯撒斯劳滕-兰道莱茵-普法尔茨技术大学);Seoul National University of Science and Technology(首尔科学技术大学)
RAG-HAR: Retrieval Augmented Generation-based Human Activity Recognition
University of Sydney Australia(悉尼大学澳大利亚分校);University of Sri Jayewardenepura Sri Lanka(Sri Jayewardenepura大学 Sri Lanka);Curtin University Australia(Curtin大学澳大利亚分校);Colorado State University USA(科罗拉多州立大学美国分校)
Smart Pressure e-Mat for Human Sleeping Posture and Dynamic Activity Recognition
School of Electrical and Computer Engineering, Purdue University(普渡大学电气与计算机工程学院);Department of Electrical and Computer Engineering, Oakland University(奥克兰大学电气与计算机工程系)
Collaborative Temporal Feature Generation via Critic-Free Reinforcement Learning for Cross-User Sensor-Based Activity Recognition
School of Artificial Intelligence (School of Future Technology), Nanjing University of Information Science and Technology(信息科学与技术大学人工智能学院);School of Cyberspace Security, Nanjing University of Information Science and Technology(信息科学与技术大学网络空间安全学院);Jinling Hospital, Affiliated Hospital of Medical School, Nanjing University(南京大学附属医院金陵医院);Department of Electrical, Computer, and Software Engineering, The University of Auckland(奥克兰大学电气、计算机和软件工程系)
A Novel Deep Hybrid Framework with Ensemble-Based Feature Optimization for Robust Real-Time Human Activity Recognition
Department of Computer Science, HITEC University(计算机科学系,HITEC大学);Department of Information Systems, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University (PNU)(信息系,计算机与信息科学学院,普里塞斯努拉·本·阿卜杜勒拉赫曼大学);University of Wollongong(沃林戈大学);College of Engineering and Technology, American University of Middle East(工程与技术学院,中东美国大学)