Author

Shengjie Zhao

h-index 4 View on Semantic Scholar

We have 3 of 24 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Jul 2026

Skeleton-aware SAM2 adaptation for topology-preserving angiographic vessel segmentation

The proposed Skeleton-Aware SAM2 improves both overlap-based and topology-aware performance over strong baselines and topology-aware loss variants and suggests that explicit morphology-guided conditioning provides useful structural bias for topology-sensitive angiographic vessel segmentation under domain shifts.

Shuang Liang, Chun-Yi Yang, Zhicheng Liu et al. · Pattern Analysis and Applica... · 0 citations

Conference Jul 2026

Dual-Prototype Disentanglement Learning for Vision-Language Skeleton Representation

Auxiliary visual and language modalities can improve self-supervised skeleton action representation learning by supplying object, scene, and semantic cues that joint coordinates lack. Existing cross-modal training signals are often defined at the sample level or aligned in a single global space, making them sensitive t...

Kenan Ye, Shengjie Zhao, Shuang Liang · IEEE International Conferenc... · 0 citations

Open access Jul 2026

CrossVLS: Cross-Modal Vision-Language Prototypes for Self-Supervised Skeleton Action Representation Learning

Results show that prototype-mediated vision-language transfer can improve skeleton representations for the behavior-interpretation stage of positioning and tracking pipelines, and CrossVLS is proposed, which is a cross-modal vision-language-guided framework that transfers semantic knowledge from red, green, and blue fr...

Kenan Ye, Shengjie Zhao, Shuang Liang · Electronics · 0 citations