Min Sun
National Tsing Hua University · 158 works · 5,157 citations · h-index 33
Top works
- Make3D: Learning 3D Scene Structure from a Single Still Image
- Articulated part-based model for joint object detection and pose estimation
- Learning 3-D Scene Structure from a Single Still Image
- A multi-view probabilistic model for 3D object classes
- Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstruction
- Learning a dense multi-view representation for detection, viewpoint classification and synthesis of object categories
- Depth-Encoded Hough Voting for Joint Object Detection and Shape Recovery
- Relating Things and Stuff by High-Order Potential Modeling
- Conditional regression forests for human pose estimation
- DPP-Net: Device-Aware Progressive Search for Pareto-Optimal Neural Architectures
- No More Discrimination: Cross City Adaptation of Road Scene Segmenters
- Tactics of Adversarial Attack on Deep Reinforcement Learning Agents
- A Unified Model for Extractive and Abstractive Summarization using Inconsistency Loss
- Anticipating Accidents in Dashcam Videos
- Joint Monocular 3D Vehicle Detection and Tracking
- Ranking Domain-Specific Highlights by Analyzing Edited Videos
- Toward coherent object detection and scene layout understanding
- Make3D: depth perception from a single still image
- Deep 360 Pilot: Learning a Deep Agent for Piloting through 360° Sports Videos
- Cube Padding for Weakly-Supervised Saliency Prediction in 360° Videos