Boyu Mu — accepted AI-conference papers

2023

Boosting Few-shot Action Recognition with Graph-guided Hybrid Matching

Jiazheng Xing, Mengmeng Wang, Yudi Ruan, Bofan Chen, Yaowei Guo, Boyu Mu +3

ICCV 2023poster

Class prototype construction and matching are core aspects of few-shot action recognition. Previous methods mainly focus on designing spatiotemporal relation modeling modules or complex temporal alignment algorithms. Despite the promising results, they ignored the value of class prototype constructi…

Cited by 37 PDF ↗code ↗Scholar ↗

2023

Revisiting the Spatial and Temporal Modeling for Few-Shot Action Recognition

Jiazheng Xing, Mengmeng Wang, Yong Liu, Boyu Mu

AAAI 2023technical

Spatial and temporal modeling is one of the most core aspects of few-shot action recognition. Most previous works mainly focus on long-term temporal relation modeling based on high-level spatial representations, without considering the crucial low-level spatial features and short-term temporal relat…

Cited by 45 Source ↗PDF ↗Scholar ↗