TP-V1.V5.8

DPNET: DUAL-PATH NETWORK FOR EFFICIENT OBJECT DETECTION WITH LIGHTWEIGHT SELF-ATTENTION

Huimin Shi, Quan Zhou, Yinghao Ni, Xiaofu Wu, Nanjing University of Posts and Telecommunications, China; Longin Jan Latecki, Temple University, United States of America
Session:
Image & Video Interpretation and Understanding
Virtual Poster
Track:
Image and Video Analysis, Synthesis, and Retrieval
Location:
Gather.Town 5
Presentation Time:
Tue, 4 Oct, 21:00 - 22:00 China Standard Time (UTC +8)
Tue, 4 Oct, 15:00 - 16:00 Central European Time (UTC +1)
Tue, 4 Oct, 13:00 - 14:00 UTC
Tue, 4 Oct, 09:00 - 10:00 Eastern Time (UTC -5)
Session Co-Chairs:
Jean-Christophe Pesquet, CentraleSupélec and Andrea Cavallaro, Queen Mary University of London and Rebecca Willett, University of Chicago
Presentation
Discussion
Resources
No resources available.
Session TP-V1.V5
TP-V1.V5.1: SPATIAL-SEMANTIC ATTENTION FOR GROUNDED IMAGE CAPTIONING
Wenzhe Hu, Lanxiao Wang, Linfeng Xu, University of Electronic Science and Technology of China, China
TP-V1.V5.2: A MULTI-STAGE DUPLEX FUSION CONVNET FOR AERIAL SCENE CLASSIFICATION
Jingjun Yi, Beichen Zhou, Wuhan University, China
TP-V1.V5.3: Back To Old Constraints to Jointly Supervise Learning Depth, Camera Motion and Optical Flow in a Monocular Video
Hicham Sekkati, Jean-Francois Lapointe, National Research Council Canada (NRC Canada), Canada
TP-V1.V5.4: STRUCTURED DROPCONNECT FOR UNCERTAINTY INFERENCE IN IMAGE CLASSIFICATION
Wenqing Zheng, Jiyang Xie, Zhanyu Ma, Beijing University of Posts and Telecommunications, China; Xian Sun, Aerospace Information Research Institute, Chinese Academy of Sciences, China
TP-V1.V5.5: QUES-TO-VISUAL GUIDED VISUAL QUESTION ANSWERING
Xiangyu Wu, Jianfeng Lu, Zhuanfeng Li, Fengchao Xiong, Nanjing University of Science and Technology, China
TP-V1.V5.6: OPEN-WORLD OBJECT DETECTION VIA DISCRIMINATIVE CLASS PROTOTYPE LEARNING
Jinan Yu, Liyan Ma, Zhenglin Li, Yan Peng, Shaorong Xie, Shanghai University, China
TP-V1.V5.7: VISUAL SENTIMENT PREDICTION USING CROSS-WAY FEW-SHOT LEARNING BASED ON KNOWLEDGE DISTILLATION
Yingrui Ye, Yuya Moroto, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama, Hokkaido University, Japan
TP-V1.V5.8: DPNET: DUAL-PATH NETWORK FOR EFFICIENT OBJECT DETECTION WITH LIGHTWEIGHT SELF-ATTENTION
Huimin Shi, Quan Zhou, Yinghao Ni, Xiaofu Wu, Nanjing University of Posts and Telecommunications, China; Longin Jan Latecki, Temple University, United States of America
TP-V1.V5.9: SUPERPIXEL GROUP-CORRELATION NETWORK FOR CO-SALIENCY DETECTION
Minhyeok Lee, Chaewon Park, Suhwan Cho, Sangyoun Lee, Yonsei University, Korea, Republic of
TP-V1.V5.10: SALIENCY DETECTION VIA GLOBAL CONTEXT ENHANCED FEATURE FUSION AND EDGE WEIGHTED LOSS
Chaewon Park, Minhyeok Lee, MyeongAh Cho, Sangyoun Lee, Yonsei University, Korea, Republic of
TP-V1.V5.11: REAL-WORLD VIDEO ANOMALY DETECTION BY EXTRACTING SALIENT FEATURES
Yudai Watanabe, Makoto Okabe, Shizuoka University, Japan; Yasunori Harada, Naoji Kashima, Chubu Electric Power Co., Inc., Japan
TP-V1.V5.12: EMCENET: EFFICIENT MULTI-SCALE CONTEXT EXPLORATION NETWORK FOR SALIENT OBJECT DETECTION
Yanguang Sun, College of Computer Science and Engineering, Anhui University of Science and Technology, China; Chenxing Xia, College of Computer Science and Engineering, Anhui University of Science and Technology; Institute of Energy, Hefei Comprehensive National Science Center., China; Xiuju Gao, Bin Ge, College of Computer Science and Engineering, Anhui University of Science and Technology., China; Hanling Zhang, School of Design, Hunan University, China; Kuan-Ching Li, Department of Computer Science and Information Engineering, Providence University, Taiwan
TP-V1.V5.13: MULTI-MODALITY DIVERSITY FUSION NETWORK WITH SWINTRANSFORMER FOR RGB-D SALIENT OBJECT DETECTION
Songsong Duan, Chenxing Xia, Xiuju Gao, Bin Ge, Anhui University of Science and Technology, China; Hanling Zhang, Hunan University, China; Kuan-Ching Li, Providence University, Taiwan
TP-V1.V5.14: MDNET: MOTION DISTINCTION NETWORK FOR EFFECTIVE ACTION RECOGNITION
Rongrong Jin, Weirong Ye, Xiao Wang, Yan Yan, Hanzi Wang, Xiamen University, China
TP-V1.V5.15: HIGHER-ORDER RECURRENT NETWORK WITH SPACE-TIME ATTENTION FOR VIDEO EARLY ACTION RECOGNITION
Tsung-Ming Tai, Oswald Lanz, Free University of Bozen-Bolzano, Italy; Giuseppe Fiameni, Cheng-Kuang Lee, NVIDIA AI Technology Center, Italy