TA2.PA.4
SCALABLE HYPERSPHERE EMBEDDING FOR SEMANTIC METRIC LEARNING
Lovre Antonio Budimir, Marko Subašić, Zoran Kalafatić, Sven Lončarić, University of Zagreb Faculty of Electrical Engineering and Computing, Croatia
Session:
TA2.PA: Image & Video Representation Poster
Track:
Image and Video Sensing, Modeling, and Representation
Location:
Poster Area A
Presentation Time:
Tue, 29 Oct, 10:30 - 12:00 Gulf Standard Time (UTC +4)
Session Chair:
Wei Zhou, Cardiff University
Session TA2.PA
TA2.PA.1: Representation Synthesis by Probabilistic Many-Valued Logic Operation in Self-Supervised Learning
Hiroki Nakamura, Masashi Okada, Panasonic Holdings Corporation, Japan; Tadahiro Taniguchi, Ritsumeikan University, Japan
TA2.PA.2: SANeRV: Scene-Adaptive Neural Representation for Videos
Hochang Rhee, Samsung Advanced Institute of Technology, Korea, Republic of; Hae Soo Chung, Jun Ho Jo, Eun Ji Lee, Nam Ik Cho, Seoul National University, Korea, Republic of
TA2.PA.3: ESTATE: EXPERT-GUIDED STATE TEXT ENHANCEMENT FOR ZERO-SHOT INDUSTRIAL ANOMALY DETECTION
Bingke Zhu, Institute of Automation, Chinese Academy of Sciences, China; Hao Li, Central South University, China; Changlin Chen, Hefei University of Technology, China; Liujie Hua, Central South University, China; Jinqiao Wang, Institute of Automation, Chinese Academy of Sciences, China
TA2.PA.4: SCALABLE HYPERSPHERE EMBEDDING FOR SEMANTIC METRIC LEARNING
Lovre Antonio Budimir, Marko Subašić, Zoran Kalafatić, Sven Lončarić, University of Zagreb Faculty of Electrical Engineering and Computing, Croatia
TA2.PA.5: TEMPORAL TRANSFORMER ENCODER FOR VIDEO CLASS INCREMENTAL LEARNING
Nattapong Kurpukdee, Adrian Bors, University of York, United Kingdom of Great Britain and Northern Ireland
TA2.PA.6: IMPROVING SELF-SUPERVISED VISION TRANSFORMERS FOR VISUAL CONTROL
Wonil Song, Kwanghoon Sohn, Yonsei University, Korea, Republic of; Dongbo Min, Ewha Womans University, Korea, Republic of
TA2.PA.7: MULTI-TASK AFFINITY PROPAGATION BASED NATURAL IMAGE MATTING
Renkai Zhang, Nong Sang, Huazhong University of Science and Technology, China
TA2.PA.8: ADAVIPRO: REGION-BASED ADAPTIVE VISUAL PROMPT FOR LARGE-SCALE MODELS ADAPTING
Mengyu Yang, Ye Tian, Lanshan Zhang, Beijing University of Posts and Telecommunications, China; Xiao Liang, Xidian University, China; Xuming Ran, Dalian University of Technology, China; Wendong Wang, Beijing University of Posts and Telecommunications, China
TA2.PA.9: Localization of Image Splicing Under Segment Anything Model with Integrated Compression and Edge Artifacts
Ruhao Zhao, Xian Zhong, Wuhan University of Technology, China; Liang Liao, Nanyang Technological University, Singapore; Wenxuan Liu, Wuhan University of Technology, China; Wenxin Huang, Hubei University, China; Zheng Wang, Wuhan University, China
TA2.PA.10: Collaborative Intelligence for Vision Transformers: A Token Sparsity-Driven Edge-Cloud Framework
Monikka Busto, Shohei Enomoto, 日本電信電話株式会社, Japan; Takeharu Eda, NTT, Japan
TA2.PA.11: DTPose: Learning Disentangled Token Representation for Effective Human Pose Estimation
Shiyang Ye, Yuan Fang, Hong Liu, Hu Chen, Wenchao Du, Hongyu Yang, Sichuan University, China
Contacts