TU2.PE.7

EXPLORING THE POTENTIAL OF VISION-LANGUAGE MODELS FOR PURE-IMAGE AND TEXT-GUIDED-IMAGE SALIENCY PREDICTION

Yuxin Zhu, Huiyu Duan, Xiongkuo Min, Guangtao Zhai, Shanghai Jiao Tong University, China; Patrick Le Callet, University of Nantes, France
Session:
TU2.PE: Image and Video Sensing, Modeling, and Representation 3 Poster
Track:
[IV-SMR] Image and video sensing, modeling, and representation
Location:
Poster Area E
Presentation Time:
Tue, 16 Sep, 10:00 - 11:30 Anchorage Time (UTC -8)
Session Chair:
Homer Chen, National Taiwan University
Presentation
Discussion
Resources
No resources available.
Session TU2.PE
TU2.PE.1: SEMANTIC PROTOTYPE-GUIDED SAMPLING FOR LONG-TAILED GENERALIZED CATEGORY DISCOVERY
Nitu Pathak, Anwesha Banerjee, Soma Biswas, Indian Institute of Science, Bangalore, India
TU2.PE.2: Holistic Coreset Selection for Data Efficient Image Quality Assessment
Arpita Nema, Hanwei Zhu, Weisi Lin, Nanyang Technological University, Singapore
TU2.PE.3: SF-VQA: Saliency Fragments No-Reference Video Quality Assessment
Namuk Kim, Cheul-Hee Hahm, Wook-Hyung Kim, Ilhyun Cho, Sojeong Park, Samsung Electronics Co., Ltd., Korea (South)
TU2.PE.4: ARaBIQA: A Novel Blind Image Quality Assessment model for Augmented Reality
Aymen Sekhri, Mohamed-Chaker Larabi, CNRS, Université de Poitiers, XLIM Lab, France; Seyed Ali Amirshahi, Norwegian University of Science and Technology, Norway
TU2.PE.5: PERFACE: METRIC LEARNING IN PERCEPTUAL FACIAL SIMILARITY FOR ENHANCED FACE ANONYMIZATION
Haruka Kumagai, Leslie Wöhler, The University of Tokyo, Japan; Satoshi Ikehata, NII, Japan; Kiyoharu Aizawa, The University of Tokyo, Japan
TU2.PE.6: F-LGAM: Enhancing Single Domain Generalized Object Detection Through Fourier-based Local and Global Amplitude MixUp
Chanyeong Park, Chung-Ang University, Korea (South); Junbo Jang, SK Inc, Korea (South); Jaehong Yoon, Minju Baek, Joonki Paik, Chung-Ang University, Korea (South)
TU2.PE.7: EXPLORING THE POTENTIAL OF VISION-LANGUAGE MODELS FOR PURE-IMAGE AND TEXT-GUIDED-IMAGE SALIENCY PREDICTION
Yuxin Zhu, Huiyu Duan, Xiongkuo Min, Guangtao Zhai, Shanghai Jiao Tong University, China; Patrick Le Callet, University of Nantes, France
TU2.PE.8: A Multi-Level Patch Dataset for JPEG Image Quality Assessment by Absolute Binary Decision
Soichiro Honda, Nagoya Kogyo Daigaku, Japan; Yoshihiro Maeda, Shibaura Kogyo Daigaku - Shibaura Campus, Japan; Osamu Watanabe, Takushoku Daigaku - Kokusai Hachioji Campus, Japan; Norishige Fukushima, Nagoya Kogyo Daigaku, Japan
TU2.PE.9: CLIP-FSQAE: CLIP-guided Finite Scalar Quantized AutoEncoder for Few-Shot Anomaly Detection
Shih-Chih Lin, Shang-Hong Lai, National Tsing Hua University, Taiwan
TU2.PE.10: TRAINING A PHASE DETECTION AUTOFOCUS MODEL USING HYBRID LABELS
Chen-Han Lin, Homer H. Chen, National Taiwan University, Taiwan
TU2.PE.11: CorDis: A novel correlation-based disentanglement measure
Hazal Mogultay Ozcan, Sinan Kalkan, Fatos Yarman Vural, Middle East Technical University, Turkey
TU2.PE.12: LARGESCENEGAUSSIAN: HIGH-EFFICIENCY 3D GAUSSIAN SPLATTING FOR LARGE-SCALE SCENE RECONSTRUCTION
Yifeng Ge, Junqi Liao, Li Li, University of Science and Technology of China, China; Deke Tang, Geovis Technology Co., Ltd., China
Contacts