Mingshuang Luo
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Mingshuang Luo has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Hong Chang
Key Laboratory of Intelligent Information Processing, Institute of Computing Technology (ICT), Chinese Academy of Sciences (CAS), Beijing, China
2 shared publications - Ruibing Hou
Key Laboratory of Intelligent Information Processing, Institute of Computing Technology (ICT), Chinese Academy of Sciences (CAS), Beijing, China
2 shared publications Bo Chao
Key Laboratory of Intelligent Information Processing, Institute of Computing Technology (ICT)Chinese Academy of Sciences (CAS)
1 shared publicationMingyuan Gao
Bytedance, Beijing, China
1 shared publication- Shiguang Shan
Institute of Computing Technology, Chinese Academy of Sciences
1 shared publication - Shuang Liang
ByteDance, Shanghai, China
1 shared publication
Latest Publications
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-11
DreamActor-M2: Universal Character Image Animation via Spatiotemporal In-Context Learning
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-11
Open AccessDreamActor-M2: Universal Character Image Animation via Spatiotemporal In-Context Learning
- 4 June 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. PP (15209210) , 1-17
CLIP-Guided Adaptable Self-Supervised Learning for Human-Centric Visual Tasks
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.
- 4 June 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. PP (15209210) , 1-17
CLIP-Guided Adaptable Self-Supervised Learning for Human-Centric Visual Tasks
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.