Chong Shi — accepted AI-conference papers

2025

SGC-Net: Stratified Granular Comparison Network for Open-Vocabulary HOI Detection

Xin Lin, Chong Shi, Zuopeng Yang, Haojin Tang, Zhili Zhou

CVPR 2025poster

Recent open-vocabulary human-object interaction (OV-HOI) detection methods primarily rely on large language model (LLM) for generating auxiliary descriptions and leverage knowledge distilled from CLIP to detect unseen interaction categories. Despite their effectiveness, these methods face two challe…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2024

TD²-Net: Toward Denoising and Debiasing for Video Scene Graph Generation

Xin Lin, Chong Shi, Yibing Zhan, Zuopeng Yang, Yaqi Wu, Dacheng Tao

AAAI 2024technical

Dynamic scene graph generation (SGG) focuses on detecting objects in a video and determining their pairwise relationships. Existing dynamic SGG methods usually suffer from several issues, including 1) Contextual noise, as some frames might contain occluded and blurred objects. 2) Label bias, primari…

Cited by 4 Source ↗PDF ↗Scholar ↗