IVMSP-P36: Video Content Analysis
Poster
Thu, 7 May, 14:00 - 16:00
Location: Poster Area 18
Session Type: Poster
Track: Image, Video and Multidimensional Signal Processing [IV]
Click the to view the manuscript on IEEE Xplore Open Preview

IVMSP-P36.1: Free2Frame: A Training-Free Framework for Video Understanding with Memory Boosting
Shiqiang Lang, Peiwen Sun, Beijing University of Posts and Telecommunications, China; Hao Jiang, Shuyuan Zhu, Huiying Zhao, China Unicom Online Information Technology CO.,Ltd, China; Lan Yang, Honggang Zhang, Beijing University of Posts and Telecommunications, China

IVMSP-P36.2: LVC: A LIGHTWEIGHT COMPRESSION FRAMEWORK FOR ENHANCING VLMS IN LONG VIDEO UNDERSTANDING
Ziyi Wang, Haoran Wu, Yiming Rong, Yunlong Zhao, Yixin Zhang, Bo Xu, Institute of Automation, Chinese Academy of Sciences, China

IVMSP-P36.3: Seaf: Semantic-aware Frame Selection for Long-form Video Understanding
Mengyu Yang, Ye Tian, Lanshan Zhang, Beijing University of Posts and Telecommunications, China; Deli Yu, ByteDance Inc., China; Peizhuang Cong, Peking University, China; Wendong Wang, Beijing University of Posts and Telecommunications, China

IVMSP-P36.4: CONTEXTUAL CLUE MINING AND CLASS CALIBRATION FOR WEAKLY SUPERVISED VIDEO ANOMALY DETECTION
Shuangqing Zhang, Wen Dong, Nanjing University, China; Wei Xu, Guanglei Chu, China Mobile (Suzhou) Software Technology Co., Ltd., China; Yuqi Fang, Nanjing University, China; Lyu Fan, Gangming Zhao, Institute of Automation, Chinese Academy of Sciences, China; Fang Zhao, Nanjing University, China

IVMSP-P36.5: BALANCING ACCURACY AND DIVERSITY: EVOLVING ANCHOR MATCHING FOR VIDEO TEMPORAL GROUNDING
Xiaolong Sun, Bo Xu, XPENG Motors, China; Ziyi Liu, University of Science and Technology Beijing, China; Cheng Lu, XPENG Motors, China

IVMSP-P36.6: ENHANCING CLIP-BASED WEAKLY-SUPERVISED VIDEO ANOMALY DETECTION VIA OPTIMAL TRANSPORT
Shuo Li, changfeng wang, Xidian University, China; yanan xi, Engineering University of PAP, China

IVMSP-P36.7: LEARNING TO SEE THROUGH DARKNESS: SELF-SUPERVISED EVENT-BASED VIDEO RECONSTRUCTION UNDER LENS FLARE
Bobaro Chang, Hyunsurk Ryu, Hyuk-jae Lee, Seoul National University, Korea, Republic of

IVMSP-P36.8: Depth-Guided Metric-Aware Temporal Consistency for Monocular Video Human Mesh Recovery
Jiaxin Cen, Xudong Mao, Sun Yat-sen University, China; Guanghui Yue, Shenzhen University, China; Wei Zhou, Cardiff University, China; Ruomei Wang, Fan Zhou, Baoquan Zhao, Sun Yat-sen University, China

IVMSP-P36.9: MOTION-GUIDED SEMANTIC ALIGNMENT WITH NEGATIVE PROMPTS FOR ZERO-SHOT VIDEO ACTION RECOGNITION
Yiming Wang, Frederick W.B. Li, Jingyun Wang, Durham University, United Kingdom of Great Britain and Northern Ireland

IVMSP-P36.10: TRIM: A SELF-SUPERVISED VIDEO SUMMARIZATION FRAMEWORK MAXIMIZING TEMPORAL RELATIVE INFORMATION AND REPRESENTATIVENESS
Pritam Mishra, Coloma Ballester, Pompeu Fabra University, Spain; Dimosthenis Karatzas, Universitat Autònoma de Barcelona, Spain