MLSP-P74: Contrastive and Self-Supervised Representation Learning I
Poster
Fri, 8 May, 09:00 - 11:00
Location: Poster Area 7
Session Type: Poster
Track: Machine Learning for Signal Processing [ML]
Click the to view the manuscript on IEEE Xplore Open Preview

MLSP-P74.1: Speech-FT: Merging Pre-Trained and Fine-Tuned Speech Representation Models for Cross-Task Generalization
Tzu-Quan Lin, Wei-Ping Huang, National Taiwan University, Taiwan; Hao Tang, University of Edinburgh, United Kingdom of Great Britain and Northern Ireland; Hung-yi Lee, National Taiwan University, Taiwan

MLSP-P74.2: AUDIOFUSE: UNIFIED SPECTRAL-TEMPORAL LEARNING VIA A HYBRID VIT-1D CNN ARCHITECTURE FOR PHONOCARDIOGRAM CLASSIFICATION
Md. Saiful Bari Siddiqui, Utsab Saha, BRAC University, Bangladesh

MLSP-P74.3: FROM COLD-START TO STABILIZATION: A DUAL-PROTOTYPE FRAMEWORK FOR ONLINE ANY-SHOT CONTINUAL LEARNING
Chengyan Liu, Suzhou University of Science and Technology, China; Linglan Zhao, Shanghai Jiao Tong University, China; Juping Gu, Fuyuan Hu, Suzhou University of Science and Technology, China; Fan Lyu, Universitat Autònoma de Barcelona, China

MLSP-P74.4: BEAM-CLIP: MULTIMODAL ALIGNMENT AND MMWAVE BEAM PATTERN REPRESENTATION LEARNING
Andrew El Kommos, Saba Mohammadhosseini, Nazanin Rahnavard, University of Central Florida, United States of America

MLSP-P74.5: SLTN: Shadow and Lighting Transformation Network for Efficient 3D Shape Recognition
Yongsik Lee, Electronics and Telecommunications Research Institute, Korea, Republic of; Dongjun Kim, Ulsan National Institute of Science and Technology, Korea, Republic of; Seungjae Lee, Electronics and Telecommunications Research Institute, Korea, Republic of; Seungjoon Yang, Ulsan National Institute of Science and Technology, Korea, Republic of

MLSP-P74.6: Direction-PointNet: A Spatiotemporal Anisotropy Network for Human Action Recognition
Jieliang Xu, Hohai University, China; Xing Li, Nanjing Forestry University, China; Shihao Han, Hohai University, China; Ge Gao, Jinting Ren, Hengyi Ren, Nanjing Forestry University, China

MLSP-P74.7: DIFF: DIFFUSION MODEL AIDED FEATURE FUSION NETWORK FOR E2E LONG-TAILED VISUAL RECOGNITION
Xuehui Sun, Nan Chen, Yuan Zheng, Inner Mongolia University, China

MLSP-P74.8: TOPT: TASK-ORIENTED PROMPT TUNING FOR URBAN REGION REPRESENTATION LEARNING
Zitao Guo, Shenzhen University, China; Changyang Jiang, Tianhong Zhao, Jinzhou Cao, Genan Dai, Bowen Zhang, Shenzhen Technology University, China

MLSP-P74.9: MIRRORTALK: FORGING PERSONALIZED AVATARS VIA DISENTANGLED STYLE AND HIERARCHICAL MOTION CONTROL
Renjie Lu, University of Science and Technology of China, China; Xulong Zhang, Xiaoyang Qu, Jianzong Wang, Ping An Technology (Shenzhen) Co., Ltd., China; Shangfei Wang, University of Science and Technology of China, China

MLSP-P74.10: ISOMETRIC IMMERSION LEARNING WITH RIEMANNIAN GEOMETRY FOR DISTORTION-FREE REPRESENTATION
Zihao Chen, Wenyong Wang, Qinye Zhu, Yu Xiang, University of Electronic Science and Technology of China, China