TU2.L3.5
ITERATIVE SELF-IMPROVEMENT OF VISION LANGUAGE MODELS FOR IMAGE SCORING AND SELF-EXPLANATION
Naoto Tanji, Septeni Japan, Inc., Japan; Toshihiko Yamasaki, The University of Tokyo, Japan
Session:
TU2.L3: Machine Learning in Signal Processing 5 Lecture
Track:
[ML] Machine Learning in Signal Processing
Location:
Room 1
Presentation Time:
Tue, 16 Sep, 11:00 - 11:15 Anchorage Time (UTC -8)
Session Chair:
Wan-Chi Siu, Hong Kong Polytechnic University
Presentation
Discussion
Resources
No resources available.
Session TU2.L3
TU2.L3.1: MULTIMAE MEETS EARTH OBSERVATION: PRE-TRAINING MULTI-MODAL MULTI-TASK MASKED AUTOENCODERS FOR EARTH OBSERVATION TASKS
Jose Sosa, Danila Rukhovich, Anis Kacem, Djamila Aouada, University of Luxembourg, Luxembourg
TU2.L3.2: EventEgoHands: Event-based Egocentric 3D Hand Mesh Reconstruction
Ryosei Hara, Wataru Ikeda, Masashi Hatano, Mariko Isogawa, Keio University, Japan
TU2.L3.3: DIFFUSE2ADAPT: CONTROLLED DIFFUSION FOR SYNTHETIC-TO-REAL DOMAIN ADAPTATION
Ketul Shah, Johns Hopkins University, United States; Arushi Sinha, Oxbridge Health, United States; Arun Reddy, Aniket Roy, Rama Chellappa, Johns Hopkins University, United States
TU2.L3.4: DOMAIN TRANSFER GENERATIVE MODEL FOR NEW FACE GENERATION
Chun-Chuen Hui, Wan-Chi Siu, H. Anthony Chan, Hong Kong Polytechnic University, China
TU2.L3.5: ITERATIVE SELF-IMPROVEMENT OF VISION LANGUAGE MODELS FOR IMAGE SCORING AND SELF-EXPLANATION
Naoto Tanji, Septeni Japan, Inc., Japan; Toshihiko Yamasaki, The University of Tokyo, Japan
TU2.L3.6: FPW: Frequency-domain Pixel-by-Pixel Watermarking against unauthorized images used on training generative model
Chi-Yuan Jan, Hong-Han Shuai, National Yang Ming Chiao Tung University, Taiwan
Contacts