116 citations · 225 across the 27 of their papers we have counts for
3 papers · 2 filters
Disentangled Generation with Information Bottleneck for Few-Shot Learning
Zhuohang Dang, Jihong Wang, Minnan Luo +3
Few-shot learning (FSL), which aims to classify unseen classes with few samples, is challenging due to data scarcity. Although various generative methods have been explored for FSL…
Noise-Tolerant Learning for Audio-Visual Action Recognition
Haochen Han, Qinghua Zheng, Minnan Luo +3
Recently, video recognition is emerging with the help of multi-modal learning, which focuses on integrating distinct modalities to improve the performance or robustness of the mode…
CGUA: Context-Guided and Unpaired-Assisted Weakly Supervised Person Search
Chengyou Jia, Minnan Luo, Caixia Yan +2
Recently, weakly supervised person search is proposed to discard human-annotated identities and train the model with only bounding box annotations. A natural way to solve this prob…