WA1.L5.2
MULTIMODAL TRANSFORMER USING CROSS-CHANNEL ATTENTION FOR OBJECT DETECTION IN REMOTE SENSING IMAGES
Bissmella Bahaduri, Zuheng Ming, Fangchen Feng, Anissa Mokraoui, University Sorbonne Paris-Nord, France
Session:
WA1.L5: Multi-image & Sensor Fusion Lecture
Track:
Computational Imaging Methods and Models
Location:
Capital Suite - 17
Presentation Time:
Wed, 30 Oct, 08:48 - 09:06 Gulf Standard Time (UTC +4)
Session Chair:
Xin Jin, Eastern Institute of Technology, Ningbo, China
Session WA1.L5
WA1.L5.1: MODIPHY: MULTIMODAL OBSCURED DETECTION FOR IOT USING PHANTOM CONVOLUTION-ENABLED FASTER YOLO
Shubhabrata Mukherjee, Cory Beard, Zhu Li, University of Missouri Kansas City, United States of America
WA1.L5.2: MULTIMODAL TRANSFORMER USING CROSS-CHANNEL ATTENTION FOR OBJECT DETECTION IN REMOTE SENSING IMAGES
Bissmella Bahaduri, Zuheng Ming, Fangchen Feng, Anissa Mokraoui, University Sorbonne Paris-Nord, France
WA1.L5.3: BIDFUSE: HARNESSING BI-DIRECTIONAL ATTENTION WITH MODALITY-SPECIFIC ENCODERS FOR INFRARED-VISIBLE IMAGE FUSION
Wangzhi Xing, Diqi Chen, Mohammadaminul Islam, Jun Zhou, Griffith University, Australia
WA1.L5.4: ILLUMINATION-ENHANCED INFRARED AND LOW-LIGHT VISIBLE IMAGE FUSION
Guohua Lv, Xinyue Fu, Chaoqun Sima, Yanlong Xu, Baodong Zhang, Qilu University of Technology (Shandong Academy of Sciences), China; Hanju Bao, Lianxin Intelligent Technology (Shandong) Co., Ltd, China
WA1.L5.5: OBJECT DETECTION FRAMEWORK USING MULTIPLE TONE MAPPINGS ON HIGH-DYNAMIC-RANGE IMAGES
Takumi Watanabe, Rei Kawakami, Masayuki Tanaka, Masatoshi Okutomi, Tokyo Institute of Technology, Japan
Contacts