Hengjia Li
9 papers · 2024–2026 · 5 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (22) 🏆 Keyword Champion (3) ⚡ Prolific Year · Productive
🗃️
Keyword Collector
(54)
Top co-authors
Research topics
Computer Vision
(8)
Machine Learning
(7)
Deep Learning
(6)
Artificial Intelligence
(5)
Generation
(4)
Models
(4)
Analysis
(3)
Application Areas
(3)
Core AI
(3)
Learning Types · Machine Learning
(3)
Learning Types · Deep Learning
(3)
Core Methods
(2)
Domain-Specific
(2)
Learning Paradigms
(2)
Processing
(1)
Keywords
video customization
(3)
video generation
(3)
attention mechanism
(2)
semantic segmentation
(2)
reward modeling
(2)
domain adaptation
(2)
identity preservation
(2)
multi-label classification
(1)
image generation
(1)
image segmentation
(1)
preference optimization
(1)
multimodal learning
(1)
reward learning
(1)
autonomous driving
(1)
prompt engineering
(1)
pseudo labeling
(1)
unsupervised domain adaptation
(1)
image synthesis
(1)
point cloud
(1)
subspace learning
(1)
Papers
RoadBench: A Vision-Language Foundation Model and Benchmark for Road Damage Understanding
WACV 2026
DreamRelation: Relation-Centric Video Customization
ICCV 2025
Local Conditional Controlling for Text-to-Image Diffusion Models
AAAI 2025
MagicID: Hybrid Preference Optimization for ID-Consistent and Dynamic-Preserved Video Customization
ICCV 2025
PersonalVideo: High ID-Fidelity Video Customization without Dynamic and Semantic Degradation
ICCV 2025
SAMRefiner: Taming Segment Anything Model for Universal Mask Refinement
ICLR 2025
Few-shot Hybrid Domain Adaptation of Image Generator
ICLR 2024
Pseudo Label Refinery for Unsupervised Domain Adaptation on Cross-dataset 3D Object Detection
CVPR 2024
TagCLIP: A Local-to-Global Framework to Enhance Open-Vocabulary Multi-Label Classification of CLIP without Training
AAAI 2024