Xuesong Liu — accepted AI-conference papers

2026

Decompose and Conquer: Compositional Reasoning for Zero-Shot Temporal Action Localization

Haoyu Tang, Tianyuan Liang, Han Jiang, Xuesong Liu, Qinghai Zheng, Yupeng Hu

AAAI 2026technical

Current Zero-Shot Temporal Action Localization (ZSTAL) methods, whether training-based or training-free ones, still predominantly rely on a single, unified query to localize an entire action. This unified representation is fundamentally ill-suited for complex real-world activities, as it fails to ca

Cited by 0 Source ↗PDF ↗Scholar ↗

2026

Structure-Aware Representation Distillation for Tiny-Dense Object Segmentation

Xuesong Liu, Anke Xu, Wenbo Cao, Emmett Ientilucci

CVPR 2026

Dense scenes containing numerous tiny objects pose a fundamental challenge for segmentation models, where small localization errors can significantly degrade downstream measurements. We present Structure-Aware Representation Distillation (SARD), a teacher-compatible framework that transfers structur

Cited by 0 Source ↗code ↗Scholar ↗