IVMSP-P12.6
TALDS-Net: Task-Aware Adaptive Local Descriptors Selection for Few-shot Image Classification
Qian Qiao, Yu Xie, Ziyin Zeng, Fanzhang Li, Soochow university, China
Session:
IVMSP-P12: Aspects in image/video processing and analysis Poster
Track:
Image, Video, and Multidimensional Signal Processing
Location:
Poster Zone 1C
Poster Board PZ-1C.6
Poster Board PZ-1C.6
Presentation Time:
Wed, 17 Apr, 16:30 - 18:30 (UTC +9)
Session Chair:
Hongwei Dong, CAS, China
Session IVMSP-P12
IVMSP-P12.1: TIME-INTERVAL VISUAL SALIENCY PREDICTION IN MAMMOGRAM READING
Jianxun Lou, Xinbo Wu, Cardiff University, United Kingdom of Great Britain and Northern Ireland; Richard White, University Hospital of Wales, United Kingdom of Great Britain and Northern Ireland; Yingying Wu, Hantao Liu, Cardiff University, United Kingdom of Great Britain and Northern Ireland
IVMSP-P12.2: HADGEO: IMAGE BASED 3-DOF CROSS-VIEW GEO-LOCALIZATION WITH HARD SAMPLE MINING
Chaoran Li, National University of Defense Technology, China; Chao Yan, Nanjing University of Aeronautics and Astronautics, China; Xiaojia Xiang, Jun Lai, Han Zhou, Dengqing Tang, National University of Defense Technology, China
IVMSP-P12.3: EXTENDING IMPLICIT NEURAL REPRESENTATIONS FOR TEXT-TO-IMAGE GENERATION
Guanming Liu, Zhihua Wei, Heng Zhang, Rui Wang, Tongji University, China; Aiquan Yuan, Chuanbao Liu, Biao Chen, Guodong Cao, Alibaba Group, China
IVMSP-P12.4: SO-NET: MODEL-AGNOSTIC SEQUENTIAL HAND POSE OPTIMIZATION FRAMEWORK
Yuanyuan Gao, Pengfei Ren, Beijing University of Posts and Telecommunications, China; Mingen Shu, Rui Chu, Jubiao Li, Jing Jin, China Mobile Information Technology Co., Ltd., China; Wei Li, Beijing University of Posts and Telecommunications, China
IVMSP-P12.5: CSCNET: CLASS-SPECIFIED CASCADED NETWORK FOR COMPOSITIONAL ZERO-SHOT LEARNING
Yanyi Zhang, Qi Jia, Xin Fan, Yu Liu, Dalian University of Technology, China; Ran He, Chinese Academy of Sciences, China
IVMSP-P12.6: TALDS-Net: Task-Aware Adaptive Local Descriptors Selection for Few-shot Image Classification
Qian Qiao, Yu Xie, Ziyin Zeng, Fanzhang Li, Soochow university, China
IVMSP-P12.7: SAR2NDVI: Pre-training for SAR-to-NDVI Image Translation
Daiki Kimura, Tatsuya Ishikawa, IBM Research, Japan; Masanori Mitsugi, IBM Japan Ltd., Japan; Yasunori Kitakoshi, IBM Japan Digital Services Company, Japan; Takahiro Tanaka, IBM Japan Ltd., Japan; Naomi Simumba, IBM Research, Japan; Kentaro Tanaka, Hiroaki Wakabayashi, Masato Sampei, Space Shift Inc., Japan; Michiaki Tatsubori, IBM Research, Japan
IVMSP-P12.8: EXTREMELY LIGHT-WEIGHT LEARNING BASED LDR TO PQ HDR CONVERSION USING BERNSTEIN CURVES
Dung Vo, Chenguang Liu, McClain Nelson, Samsung Research America, United States of America
IVMSP-P12.9: SR-VFA: ACCURATE SELF-REFINED FACE ALIGNMENT IN VIDEOS
Sipeng Yang, Hongyu Huang, Qingchuan Zhu, Xiaogang Jin, Zhejiang University, China
IVMSP-P12.10: Robust Lightweight Depth Estimation Model via Data-free Distillation
Zihan Gao, Beihang University, China; Peng Gao, Hangzhou Dianzi University, China; Wei Yin, Shenzhen DJI Sciences and Technologies Ltd, China; Yifan Liu, The University of Adelaide, China; Zengchang Qin, Beihang University, China
IVMSP-P12.11: BOUNDING BOX-GUIDED PSEUDO POINT CLOUDS EARLY-FUSION AND DENSITY OPTIMIZE FOR 3D OBJECT DETECTION
Shiwei Zhao, Shengye Yan, Nanjing University of Information Science and Technology, China
IVMSP-P12.12: SAM-GEBD : ZERO-COST APPROACH FOR GENERIC EVENT BOUNDARY DETECTION
Pranay Kashyap, Sourabh Vasant Gothe, Vibhav Agarwal, Jayesh Rajkumar Vachhani, Samsung R&D Institute India - Bangalore, India
Contacts