Scene Understanding
- Object Detection
- Video Object Segmentation
- Video Action Recognition
- Saliency Detection
- Image Retrieval
- Anomaly Detection
Research
3D Vision
- 3D Object Detection
- LiDAR Depth Completion
- Odometry Estimation
- 3D View Reconstruction
- 2D-3D Representation Learning
- Depth Estimation
Multi-Modality
- Text-to-Motion Generation
- Sound Source Localization
- Explainable Video Anomaly Detection
- Audio-Video Anomaly Detection
Applied Machine Learning
- Visual Surveillance System
- Autonomous Driving
- Robot Vision
Human Analysis
- Human Pose Estimation
- Heterogeneous Face Recognition
- Facial Landmark Detection
- Head Pose Estimation
General Topics
- Multimodal Learning (Vision, Language, Audio, etc.)
- Domain Adaptation / Generalization
- Metric Learning
- Artificial General Intelligence