Hengjia Li

Venues

Frequent coauthors

Papers

1. RoadBench: A Vision-Language Foundation Model and Benchmark for Road Damage Understanding
   WACV 2026 ·

   Xi Xiao

   DBLP profile ↗ORCID search ↗
2. DreamRelation: Relation-Centric Video Customization
   ICCV 2025 ·

   Yujie Wei

   DBLP profile ↗ORCID search ↗
3. Local Conditional Controlling for Text-to-Image Diffusion Models
   AAAI 2025 ·

   Yibo Zhao

   DBLP profile ↗ORCID search ↗
4. Magicid: Hybrid Preference Optimization for Id-Consistent and Dynamic-Preserved Video Customization
   ICCV 2025 · Hengjia Li
5. PersonalVideo: High ID-Fidelity Video Customization without Dynamic and Semantic Degradation
   ICCV 2025 · Hengjia Li
6. SAMRefiner: Taming Segment Anything Model for Universal Mask Refinement
   ICLR 2025 ·

   Yuqi Lin

   DBLP profile ↗ORCID search ↗
7. Singing Timbre Popularity Assessment Based on Multimodal Large Foundation Model
   ACM MM 2025 ·

   Zihao Wang

   DBLP profile ↗ORCID search ↗
8. Few-shot Hybrid Domain Adaptation of Image Generator
   ICLR 2024 · Hengjia Li
9. Pseudo Label Refinery for Unsupervised Domain Adaptation on Cross-Dataset 3D Object Detection
   CVPR 2024 ·

   Zhanwei Zhang

   DBLP profile ↗ORCID search ↗
10. TagCLIP: A Local-to-Global Framework to Enhance Open-Vocabulary Multi-Label Classification of CLIP without Training
    AAAI 2024 ·

    Yuqi Lin

    DBLP profile ↗ORCID search ↗