Scholar
Di Chen
Google Scholar ID: Ht9e9D4AAAAJ
Researcher, Alibaba Damo Academy
Citations & Impact
Citations
1,257
H-index
13
i10-index
13
Publications
17
Co-authors
6
list available
Publications
Resume (English only)
Academic Achievements
- CVPR 2024 Oral: Ranni: Taming Text-to-Image Diffusion for Accurate Instruction Following
- ICML 2023: Composer: Creative and Controllable Image Synthesis with Composable Conditions
- ECCV 2022: GeoAug: Data Augmentation for Few-Shot NeRF with Geometry Constraints
- AAAI 2024: Divide and Conquer: Hybrid Pre-training for Person Search
- AAAI 2022 Oral: Keypoint Message Passing for Video-based Person Re-Identification
- CVPR 2022: PoseTrack21: A Dataset for Person Search, Multi-Object Tracking and Multi-Person Pose Tracking
- ACM MM 2022: Grouped Adaptive Loss Weighting for Person Search
- IJCV 2021 (two papers): Norm-Aware Embedding for Efficient Person Search And Tracking; Guided Attention in CNNs for Occluded Pedestrian Detection and Re-Identification
- CVPR 2020: Norm-Aware Embedding for Efficient Person Search
- AAAI 2020: Hierarchical Online Instance Matching for Person Search
- TIP 2020: Person Search by Separated Modeling and A Mask-Guided Two-Stream CNN Model
- ECCV 2018: Person Search via A Mask-Guided Two-Stream CNN Model
- SIGIR 2022: Animating Images to Transfer CLIP for Video-Text Retrieval
- Neurocomputing 2018: Joint Bayesian Guided Metric Learning for End-to-end Face Verification
Research Experience
- Algorithm Researcher at Alibaba, July 2021–present
- Worked on Tongyi Wanxiang: a comprehensive image and video generation service
- Research includes diffusion model distillation & acceleration, Neural Radiance Fields (NeRF), and 3D reconstruction
- Developed large-scale diffusion models for Taobao image generation, inpainting, and outpainting
- Multi-modal retrieval for large-scale data collection and filtering
