MO3.L1.2
BEVANET: BILATERAL EFFICIENT VISUAL ATTENTION NETWORK FOR REAL-TIME SEMANTIC SEGMENTATION
Ping-Mao Huang, I-Tien Chao, Ping-Chia Huang, Jia-Wei Liao, Yung-Yu Chuang, National Taiwan University, Taiwan
Session:
MO3.L1: Image and Video Analysis, Synthesis, and Retrieval 1 Spotlight
Track:
[IV-ANA] Image and video analysis, synthesis, and retrieval
Location:
Dena'ina: Tikahtnu Ballroom A
Presentation Time:
Mon, 15 Sep, 15:20 - 15:40 Anchorage Time (UTC -8)
Session Chair:
Gozde Bozdagi Akar, Middle East Technical University
Session MO3.L1
MO3.L1.1: BAYESIAN SURPRISE FOR SMALL AND SUB-PIXEL MOVING TARGET DETECTION
Laurent Itti, Daben Liu, University of Southern California, United States; Corinne Teeter, Srideep Musuvathy, Sandia National Laboratories, United States
MO3.L1.2: BEVANET: BILATERAL EFFICIENT VISUAL ATTENTION NETWORK FOR REAL-TIME SEMANTIC SEGMENTATION
Ping-Mao Huang, I-Tien Chao, Ping-Chia Huang, Jia-Wei Liao, Yung-Yu Chuang, National Taiwan University, Taiwan
MO3.L1.3: MEASURING DISTORTION STRENGTH WITH DEWARPING DIFFUSION MODELS IN ANOMALY DETECTION
Akira Uchida, Institute of Science Tokyo, Japan; Satoshi Ikehata, National Institute of Informatics / Institute of Science Tokyo, Japan; Yuichi Yoshida, DENSO IT Laboratory, Inc., Japan; Ikuro Sato, Institute of Science Tokyo, / Denso IT Laboratory, Japan
Contacts