TP1.PA.3
Dual Temporal Transformers for Fine-Grained Dangerous Action Recognition
Wenfeng Song, Xingliang Jin, Yang Ding, Beijing Information Science and Technology University, China; Yang Gao, Beihang University, China; Xia Hou, Beijing Information Science and Technology University, China
Session:
TP1.PA: Action Recognition Poster
Track:
Applications of Machine Learning
Location:
Poster Area A
Presentation Time:
Tue, 10 Oct, 14:30 - 16:00 Malaysia Time (UTC +8)
Session Chair:
Syed Abu-Bakar, Universiti Teknologi Malaysia
Session TP1.PA
TP1.PA.1: SELF-SUPERVISED 3D SKELETON REPRESENTATION LEARNING WITH ACTIVE SAMPLING AND ADAPTIVE RELABELING FOR ACTION RECOGNITION
Guoquan Wang, Hong Liu, Tianyu Guo, Jingwen Guo, Ti Wang, Yidi Li, Peking University, China
TP1.PA.2: HOKEM: HUMAN AND OBJECT KEYPOINT-BASED EXTENSION MODULE FOR HUMAN-OBJECT INTERACTION DETECTION
Yoshiki Ito, Hitachi, Ltd., Japan
TP1.PA.3: Dual Temporal Transformers for Fine-Grained Dangerous Action Recognition
Wenfeng Song, Xingliang Jin, Yang Ding, Beijing Information Science and Technology University, China; Yang Gao, Beihang University, China; Xia Hou, Beijing Information Science and Technology University, China
TP1.PA.4: FEATURE SPACE DATA AUGMENTATION FOR VIEWPOINT-ROBUST ACTION RECOGNITION IN VIDEOS
Carla Geara, Aleksandr Setkov, Astrid Orcesi, Bertrand Luvison, Universite Paris-Saclay, CEA, List, France
TP1.PA.5: FREQUENCY ENHANCEMENT NETWORK FOR EFFICIENT COMPRESSED VIDEO ACTION RECOGNITION
Yue Ming, Lu Xiong, Beijing University of Posts and Telecommunications, China; Xia Jia, Qingfang Zheng, ZTE corpration, China; Jiangwan Zhou, Fan Feng, Nannan Hu, Beijing University of Posts and Telecommunications, China
TP1.PA.6: SELF-SUPERVISED CONTRASTIVE LEARNING FOR AUDIO-VISUAL ACTION RECOGNITION
Yang Liu, Ying Tan, Haoyuan Lan, Sun Yat-sen University, China
TP1.PA.7: Enhancing Next Active Object-based Egocentric Action Anticipation with Guided Attention
Sanket Thakur, Istituto Italiano di Tecnologia, Italy; Cigdem Beyan, University of Trento, Italy; Pietro Morerio, Istituto Italiano di Tecnologia, Italy; Vittorio Murino, University of Verona, Italy; Alessio Del Bue, Istituto Italiano di Tecnologia, Italy
TP1.PA.8: ACTION ANTICIPATION WITH GOAL CONSISTENCY
Olga Zatsarynna, Juergen Gall, University of Bonn & Lamarr Institute, Germany
TP1.PA.9: SCRATCHHOI: TRAINING HUMAN-OBJECT INTERACTION DETECTORS FROM SCRATCH
Jun Yi Lim, Vishnu Monn Baskaran, Joanne Mun Yee Lim, Ricky Sutopo, Kok Sheik Wong, Monash University Malaysia, Malaysia; Massimo Tistarelli, University of Sassari, Italy
TP1.PA.10: Multi-scale temporal feature fusion for few-shot action recognition
Jun-Tae Lee, Sungrack Yun, Qualcomm, Korea, Republic of
TP1.PA.11: Implicit Attention-based Cross-modal Collaborative Learning for Action Recognition
Jianghao Zhang, Xian Zhong, Wenxuan Liu, Wuhan University of Technology, China; Kui Jiang, Harbin Institute of Technology, China; Zhengwei Yang, Zheng Wang, Wuhan University, China
TP1.PA.12: A BASELINE ON CONTINUAL LEARNING METHODS FOR VIDEO ACTION RECOGNITION
Giulia Castagnolo, Concetto Spampinato, PeRCeiVe Lab,University of Catania, Italy; Francesco Rundo, STMicroelectronics, Italy; Daniela Giordano, Simone Palazzo, PeRCeiVe Lab,University of Catania, Italy
Contacts