IEEE ICASSP 2022

2022 IEEE International Conference on Acoustics, Speech and Signal Processing

7-13 May 2022
  • Virtual (all paper presentations)
22-27 May 2022
  • Main Venue: Marina Bay Sands Expo & Convention Center, Singapore
27-28 October 2022
  • Satellite Venue: Crowne Plaza Shenzhen Longgang City Centre, Shenzhen, China

ICASSP 2022
IVMSP-12.3

EQUAL LOSS: A SIMPLE LOSS FUNCTION FOR NOISE ROBUST LEARNING

Lei Cui, Tsinghua University, China; Huan Peng, Huazhong University of Science and Technology, China; Yangguang Li, Chuming Li, Sensetime Group, China; Xingrun Xing, Beihang University, China

Session:
Image and Video Understanding II

Track:
Image, Video, and Multidimensional Signal Processing

Location:
Gather Area J

Presentation Time:
Mon, 9 May, 21:00 - 21:45 China Time (UTC +8)
Mon, 9 May, 13:00 - 13:45 UTC

Session Chair:
Ee Leng Joseph Tan, Nanyang Technological University
Presentation
Discussion
Resources
Session IVMSP-12
IVMSP-12.1: PMP-NET: RETHINKING VISUAL CONTEXT FOR SCENE GRAPH GENERATION
Xuezhi Tong, College of Intelligence and Computing, Tianjin University, China; Rui Wang, Zhejiang Lab and State Key Laboratory of Information Security, Institute of Information Engineering, Chinese Academy of Sciences, China; Chuan Wang, Sanyi Zhang, Xiaochun Cao, State Key Laboratory of Information Security, Institute of Information Engineering, Chinese Academy of Sciences, China
IVMSP-12.2: IMPROVE IMAGE CAPTIONING VIA RELATION MODELING
Feicheng Huang, Zhixin Li, Guangxi Normal University, China
IVMSP-12.3: EQUAL LOSS: A SIMPLE LOSS FUNCTION FOR NOISE ROBUST LEARNING
Lei Cui, Tsinghua University, China; Huan Peng, Huazhong University of Science and Technology, China; Yangguang Li, Chuming Li, Sensetime Group, China; Xingrun Xing, Beihang University, China
IVMSP-12.4: Informative Attention Supervision for Grounded Video Description
Boyang Wan, Wenhui Jiang, Yuming Fang, Jiangxi University of Finance and Economics, China
IVMSP-12.5: SPATIAL-CONTEXT-AWARE DEEP NEURAL NETWORK FOR MULTI-CLASS IMAGE CLASSIFICATION
Jialu Zhang, Qian Zhang, Jianfeng Ren, University of Nottingham Ningbo China, China; Yitian Zhao, Chinese Academy of Sciences, China; Jiang Liu, Southern University of Science and Technology, China
IVMSP-12.6: TranSTL: Spatial-Temporal Localization Transformer for Multi-Label Video Classification
Hongjun Wu, Mengzhu Li, Hongzhe Liu, Cheng Xu, Xuewei Li, Beijing Union University, China; Yongcheng Liu, Chinese Academy of Sciences, China