Effective Feature Representation and Learning in Computer Vision

Computer vision is a field of artificial intelligence that trains computers using images or videos to interpret and understand the visual world. Effective feature representation and learning is the key issue in computer vision, and it significantly influences the performance of many tasks in computer vision, such as image classification, object detection and image segmentation. Before the deep learning era, feature representation was dominated by handcrafted feature descriptors such as SIFT, HOG, LBP and so on. Recently, deep learning techniques have provided significant improvements in academia, especially CNNs and Transformer which can learn powerful feature representations with multiple levels.

This workshop mainly focuses on effective feature representation and learning in computer vision. We welcome original and high-quality contributions from academia as well as industry on topics including, but not limited to:

l Discriminative feature learning using deep neural network

l Efficient feature learning using deep neural network

l Effective feature representation and learning for vision applications

l Feature learning theory

l Optimization for feature learning

Workshop Chair:

Zhong Zhang, Tianjin Normal University, zhong.zhang8848@gmail.com

Workshop Co-chair:

Baihua Xiao, Institute of Automation, Chinese Academy of Sciences, baihua.xiao@ia.ac.cn

Yuan Xie, East China Normal University, yxie@sei.ecnu.edu.cn

Shuang Liu, Tianjin Normal University, shuangliu.tjnu@gmail.com