IVMSP-L12.4
ProAug: Prototype-Based Augmentation for Long-Tailed Image Classification
Yan Hong, AntGroup, China; Jianfu Zhang, Shanghai Jiao Tong University, China; Zhongyi Sun, Ke Yan, Tencent, China
Session:
IVMSP-L12: Image, video and other applications Lecture
Track:
Image, Video, and Multidimensional Signal Processing
Location:
Room E4
Presentation Time:
Thu, 18 Apr, 14:10 - 14:30 (UTC +9)
Session Co-Chairs:
Joon Son Chung, KAIST and Jianfu Zhang, Shanghai Jiao Tong University
Session IVMSP-L12
IVMSP-L12.1: SAMVG: A MULTI-STAGE IMAGE VECTORIZATION MODEL WITH THE SEGMENT-ANYTHING MODEL
Haokun Zhu, Juang Ian Chong, Teng Hu, Ran Yi, Shanghai Jiao Tong University, China; Yu-Kun Lai, Paul Rosin, Cardiff University, United Kingdom of Great Britain and Northern Ireland
IVMSP-L12.2: COLOR AGNOSTIC CROSS-SPECTRAL DISPARITY ESTIMATION
Frank Sippel, Nils Genser, Hannah Och, Jürgen Seiler, André Kaup, Friedrich-Alexander-University Erlangen-Nuremberg, Germany
IVMSP-L12.3: Look, Listen and Recognise: Character-Aware Audio-Visual Subtitling
Bruno Korbar, Jaesung Huh, Andrew Zisserman, University of Oxford, Croatia
IVMSP-L12.4: ProAug: Prototype-Based Augmentation for Long-Tailed Image Classification
Yan Hong, AntGroup, China; Jianfu Zhang, Shanghai Jiao Tong University, China; Zhongyi Sun, Ke Yan, Tencent, China
IVMSP-L12.5: X-CAUNET: CROSS-COLOR CHANNEL ATTENTION WITH UNDERWATER IMAGE-ENHANCING TRANSFORMER
Alik Pramanick, Sandipan Sarma, Arijit Sur, Indian Institute of Technology Guwahati, India
IVMSP-L12.6: TASK INDICATING TRANSFORMER FOR TASK-CONDITIONAL DENSE PREDICTIONS
Yuxiang Lu, Shalayiding Sirejiding, Bayram Bayramli, Suizhi Huang, Yue Ding, Hongtao Lu, Shanghai Jiao Tong University, China
Contacts