Scholar
Chung-Ching Lin
Google Scholar ID: legkbM0AAAAJ
Microsoft
Citations & Impact
Citations
2,960
H-index
21
i10-index
37
Publications
20
Co-authors
0
Contact
Publications
Resume (English only)
Academic Achievements
- ThinkLite-VL: Data-efficient visual reasoning
- Point-RFT: Visually grounded reinforcement finetuning
- GenXD: Generating any 3D and 4D scenes
- SlowFast-VGen: Dual-speed action-driven video generation
- VisVM: For VLM self-training
- Motion Consistency Model: Accelerating video diffusion
- Idea2Img: An LMM-based agent system for visual design and creation
- IDOL: Joint video-depth generation for human dance videos
- MM-Narrator: Audio descriptions (AD) generation with GPT-4
- DisCo: Human dance generation with disentangled controls
- MaskComp: Completing visual objects
- MPT: Human pose and mesh reconstruction
- PaintSeg: Training-free segmentation
- AdaM: Video matting
- NVF: 3D Hand Pose Estimation
- LAVENDER: Unifying video-language understanding
- ResT: Zero-shot action recognition
- SwinBERT: Video captioning
- AdaFuse: Efficient action recognition
- VA-RED2: Efficient action recognition
- AR-Net: Efficient action recognition
- VIST: Video instance segmentation tracking
Research Experience
- Works at Microsoft, part of Azure and OpenAI collaboration.
Background
- Principal Researcher at Microsoft, focusing on pushing the boundaries of multimodal understanding and generation. Has worked in the fields of computer vision, machine learning, and statistical deep learning. Research interests include algorithms for visual perception (object recognition, localization, segmentation, tracking, etc.), representation learning, and the interaction of vision and language.
Co-authors