IVMSP-L2: Vision-Language Models
Oral
Tue, 5 May, 14:00 - 16:00
Location: Room 120+121
Session Type: Oral
Track: Image, Video and Multidimensional Signal Processing [IV]
Click the to view the manuscript on IEEE Xplore Open Preview
Tue, 5 May, 14:00 - 14:20

IVMSP-L2.1: Less Redundancy: Boosting Practicality of Vision Language Model in Walking Assistants
Chongyang Li, Tencent, University of Chinese Academy of Sciences, China; Zhiqiang Yuan, Hanbo Bi, Zexi Jia, Jinchao Zhang, Tencent, China
Tue, 5 May, 14:20 - 14:40

IVMSP-L2.2: TOWARDS OPEN-WORLD HUMAN-OBJECT INTERACTION REASONING WITH MULTIMODAL LARGE LANGUAGE MODEL
Eastman ZY WU, Yali Li, Shengjin Wang, Tsinghua University, China
Tue, 5 May, 14:40 - 15:00

IVMSP-L2.3: TennisTV: Do Multimodal Large Language Models Understand Tennis Rallies?
Zhongyuan Bao, Fudan University, China; Lejun Zhang, New York University, United States of America
Tue, 5 May, 15:00 - 15:20

IVMSP-L2.4: N2CDrive: Negotiate to Cooperate for Multi-Agent Autonomous Driving via Large Vision-Language Model
Xingpeng Li, Enwen Hu, Beijing University of Posts and Telecommunications, China; Jinrong Liu, University of Science and Technology Beijing, China; Siyuan Jin, Huirong Cai, Beijing University of Posts and Telecommunications, China
Tue, 5 May, 15:20 - 15:40

IVMSP-L2.5: MVP: MODELING VARIANTS OF PROMPTS FOR VISION-LANGUAGE MODELS
Ao Li, Shandong University, China; Zongfang Liu, Mohamed bin Zayed University of Artificial Intelligence, China; Xinhua Li, Shandong University, China; Jinghui Zhang, Mohamed bin Zayed University of Artificial Intelligence, China; Pengwei Wang, Shandong University, China; Hu Wang, Mohamed bin Zayed University of Artificial Intelligence, China
Tue, 5 May, 15:40 - 16:00

IVMSP-L2.6: TRIAGE: HIERARCHICAL VISUAL BUDGETING FOR EFFICIENT VIDEO REASONING IN VISION-LANGUAGE MODELS
Anmin Wang, Huazhong University of Science and Technology, China; Nan Zhang, Ping An Technology (Shenzhen) Co., Ltd., China; Wei Tao, Huazhong University of Science and Technology, China; Xiaoyang Qu, Ping An Technology (Shenzhen) Co., Ltd., China; Guokuan Li, Jiguang Wan, Huazhong University of Science and Technology, China; Jianzong Wang, Ping An Technology (Shenzhen) Co., Ltd., China