Mingshuang Luo

Mingshuang Luo

Auto-generated profile, based on publicly available information

Mingshuang Luo

ByteDance, Beijing, China; Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China

Research Focus & Metrics

Representative Publications

View All Publications
4 June 2026 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
MLMingshuang Luo
Mingshuang Luo
RHRuibing Hou
Ruibing Hou
BCBo Chao
Bo Chao
HCHong Chang
Hong Chang
ZLZimo Liu
Zimo Liu
SSShiguang Shan
Shiguang Shan
Human-centric visual analysis plays a pivotal role in diverse applications, including surveillance, healthcare, and human-computer interaction. With the emergence of large-scale unlabeled human image datasets, there is an increasing need for a general unsupervised pre-training model capable of supporting diverse human-centric downstream tasks. To achieve this goal, we propose CLASP (CLIP-guided Adaptable Self-suPervised learning), a novel framework designed for unsupervised pre-training in human-centric visual tasks. CLASP leverages the powerful vision-language model CLIP to generate both low-level (e.g. body parts) and high-level (e.g. attributes) semantic pseudo-labels. These multi-level semantic cues are then integrated into the learned visual representations, enriching their expressiveness and generalizability. Recognizing that different downstream tasks demand varying levels of semantic granularity, CLASP incorporates a Prompt-Controlled Mixture-of-Experts (MoE) module. MoE dynamically adapts feature extraction based on task-specific prompts, mitigating potential feature conflicts and enhancing transferability. Furthermore, CLASP employs a multi-task pre-training strategy, where part- and attribute-level pseudo-labels derived from CLIP guide the representation learning process. Extensive experiments across multiple benchmarks demonstrate that CLASP consistently outperforms existing unsupervised pre-training methods, advancing the field of human-centric visual analysis.

19 July 2026
Verified
Conference Paper
Open access
MLMingshuang Luo
Mingshuang Luo
SLShuang Liang
Shuang Liang
ZRZhengkun Rong
Zhengkun Rong
YLYuxuan Luo
Yuxuan Luo
THTianshu Hu
Tianshu Hu
MGMingyuan Gao
Mingyuan Gao