Chaorui Deng
Fudan University · 27 works · 5,676 citations · h-index 12
Top works
- Deep High-Resolution Representation Learning for Visual Recognition
- Deep High-Resolution Representation Learning for Visual Recognition
- Visual Grounding via Accumulated Attention
- Referring Expression Comprehension: A Survey of Methods and Datasets
- Length-Controllable Image Captioning
- Sketch, Ground, and Refine: Top-Down Dense Video Captioning
- Double Forward Propagation for Memorized Batch Normalization
- Prompt Switch: Efficient CLIP Adaptation for Text-Video Retrieval
- Visual Grounding Via Accumulated Attention
- R-GAN: Exploring Human-like Way for Reasonable Text-to-Image Synthesis via Generative Adversarial Networks
- Image Captioning With Controllable and Adaptive Length Levels
- Identity-Consistent Aggregation for Video Object Detection
- Seed1.5-VL Technical Report
- You Only Look & Listen Once: Towards Fast and Accurate Visual Grounding
- Learning Distinct and Representative Styles for Image Captioning
- Learning Distinct and Representative Modes for Image Captioning
- Causal Diffusion Transformers for Generative Modeling
- ARM: An AutoRegressive Large Multimodal Model with Unified Discrete Representations
- Scaling Properties of Text Conditioning in Visual Generation
- LightFusion: A Light-weighted, Double Fusion Framework for Unified Multimodal Understanding and Generation