Xiao-Jun Wu* — accepted AI-conference papers

2024

C2C: Component-to-Composition Learning for Zero-Shot Compositional Action Recognition

Rongchang Li, Zhenhua Feng, Tianyang Xu, Linze Li, Xiao-Jun Wu*, Muhammad Awais +2

ECCV 2024oral

"Compositional actions consist of dynamic (verbs) and static (objects) concepts. Humans can easily recognize unseen compositions using the learned concepts. For machines, solving such a problem requires a model to recognize unseen actions composed of previously observed verbs and objects, thus requi…

Cited by 6 Source ↗PDF ↗code ↗Scholar ↗

2024

Efficient Few-Shot Action Recognition via Multi-Level Post-Reasoning

Cong Wu, Xiao-Jun Wu*, Linze Li, Tianyang Xu, Zhenhua Feng, Josef Kittler

ECCV 2024poster

"The integration with CLIP (Contrastive Vision-Language Pre-training) has significantly refreshed the accuracy leaderboard of FSAR (Few-Shot Action Recognition). However, the trainable overhead of ensuring that the domain alignment of CLIP and FSAR is often unbearable. To mitigate this issue, we pre…

Cited by 4 Source ↗PDF ↗code ↗Scholar ↗