WE3.L3.2
CLIP-AE: CLIP-assisted Cross-view Audio-Visual Enhancement for Unsupervised Temporal Action Localization
Rui Xia, Dan Jiang, Quan Zhang, Ke Zhang, Chun Yuan, Tsinghua University, China
Session:
WE3.L3: Image and Video Analysis, Synthesis, and Retrieval 3 Lecture
Track:
[IV-ANA] Image and video analysis, synthesis, and retrieval
Location:
Dena'ina: Kahtnu 1
Presentation Time:
Wed, 17 Sep, 10:15 - 10:30 Anchorage Time (UTC -8)
Session Chair:
Nicola Conci, University of Trento
Session WE3.L3
WE3.L3.1: VITA-PAR: VISUAL AND TEXTUAL ATTRIBUTE ALIGNMENT WITH ATTRIBUTE PROMPTING FOR PEDESTRIAN ATTRIBUTE RECOGNITION
Minjeong Park, Hongbeen Park, Jinkyu Kim, Korea University, Korea (South)
WE3.L3.2: CLIP-AE: CLIP-assisted Cross-view Audio-Visual Enhancement for Unsupervised Temporal Action Localization
Rui Xia, Dan Jiang, Quan Zhang, Ke Zhang, Chun Yuan, Tsinghua University, China
WE3.L3.3: SPECTRAL-AWARE GLOBAL FUSION FOR RGB-THERMAL SEMANTIC SEGMENTATION
Ce Zhang, Zifu Wan, Simon Stepputtis, Katia Sycara, Yaqi Xie, Carnegie Mellon University, United States
WE3.L3.4: LEMORE: LEARN MORE DETAILS FOR LIGHTWEIGHT SEMANTIC SEGMENTATION
Mian Muhammad Naeem Abid, Nancy Mehta, Zongwei Wu, Radu Timofte, University of Würzburg, Germany
WE3.L3.5: FREQUENCY-GUIDED CONTEXTUAL IMAGE CAPTIONING
Al Shahriar Rubel, Frank Shih, Fadi Deek, New Jersey Institute of Technology, United States
WE3.L3.6: Enhancing Visual Question Answering via Clustered In-Context Sequence Configuration
Zilong He, Yijun Pan, Hebei Li, Feipeng Ma, Yansong Peng, Siying Wu, Xiaoyan Sun, University of Science and Technology of China, China
Contacts