MMSP-P27: Parameter-Efficient Fine-Tuning and Prompt-Based Learning
Poster
Fri, 8 May, 14:00 - 16:00
Location: Poster Area 20
Session Type: Poster
Track: Multimedia Signal Processing [MM]
Click the to view the manuscript on IEEE Xplore Open Preview

MMSP-P27.1: MMC: Min-Max Calibration for Test-Time Prompt Tuning in Vision-Language Models
Yue Wu, Yunhong Wang, Jinjin Zhang, Di Huang, Beihang University, China

MMSP-P27.2: Affordance Benchmark for MLLMs
Junying Wang, Fudan University, China; Wenzhe Li, Shanghai AI Laboratory, China; Yalun Wu, Shanghai Jiao Tong University, China; Yingji Liang, Yijin Guo, Shanghai AI Laboratory, China; Chunyi Li, Shanghai Jiao Tong University, China; Haodong Duan, Zicheng Zhang, Guangtao Zhai, Shanghai AI Laboratory, China

MMSP-P27.3: Structured Persona-Driven Authentic and Controllable Moment Generation
Junwen Xiong, Peng Zhang, Northwestern Polytechnical University, China

MMSP-P27.4: EFFICIENT VISUO-TACTILE LEARNING VIA FINE-GRAINED ALIGNMENT AND IMPORTANCE-AWARE TOKEN RETENTION
Jingzhi Ruan, Lin Wu, Dezong Zhao, University of Glasgow, United Kingdom of Great Britain and Northern Ireland; Fan Guo, Tianjin University, China; Wenjing Zhao, David Flynn, University of Glasgow, United Kingdom of Great Britain and Northern Ireland

MMSP-P27.5: DIAL: DATABASE-INFORMED INTERACTIVE MULTI-AGENT SYSTEM LOOP FOR PERSONALIZED IMAGE GENERATION
Taiyo Sato, Keisuke Maeda, Naoki Saito, Takahiro Ogawa, Miki Haseyama, Hokkaido University, Japan

MMSP-P27.6: TAILORED TEXT INTEGRATION AND SEMANTIC DIFFERENTIAL ENHANCEMENT FOR FEW-SHOT CLASS-INCREMENTAL LEARNING
Xin Huang, Shilong Wang, Peihao Li, Nanyang Normal University, China; Runsheng Zhang, North China Electric Power University, China; Zhimin Yuan, Nanyang Normal University, China

MMSP-P27.7: PRODISTILL: A PROGRESSIVE PROMPTING FRAMEWORK FOR FINE-GRAINED VLM DISTILLATION
Siqi Luo, Chunlei Meng, Hongda Zhang, Zhongxue Gan, Chun Ouyang, Fudan University, China

MMSP-P27.8: DANCINGMATE: COORDINATED AND SYNCHRONIZED DANCE ACCOMPANIMENT GENERATION
Xin Guo, Yifan Zhao, Jia Li, Beihang University, China

MMSP-P27.9: FineLongCLIP: Advancing Fine-Grained Image-Text Matching via a Dual-Branch Visual Encoder Capturing Global and Detailed Features
ZhiYuan Hu, Ying Zhang, XueFeng Liang, Xin Chen, ShiHao Liu, Xidian University, China

MMSP-P27.10: TER: TEST-TIME EMBEDDING REGULARIZATION FOR CALIBRATION-AWARE PROMPT TUNING IN VISION-LANGUAGE MODELS
Meijie Zhao, Qingdao University of Science and Technology, China; Yu Liu, University Putra Malaysia, Malaysia; Keyan Jin, University of Granada, Spain; Hao Yang, National University of Defense Technology, China