Du Tran
Google (United States) · 49 works · 17,740 citations · h-index 27
Top works
- Learning Spatiotemporal Features with 3D Convolutional Networks
- A Closer Look at Spatiotemporal Convolutions for Action Recognition
- Deep End2End Voxel2Voxel Prediction
- C3D: Generic Features for Video Analysis.
- Human Activity Recognition with Metric Learning
- Video Classification With Channel-Separated Convolutional Networks
- What Makes Training Multi-Modal Classification Networks Hard?
- ConvNet Architecture Search for Spatiotemporal Feature Learning
- Detect-and-Track: Efficient Pose Estimation in Videos
- Cooperative Learning of Audio and Video Models from Self-Supervised Synchronization
- Large-Scale Weakly-Supervised Pre-Training for Video Action Recognition
- Video Modeling With Correlation Networks
- Self-Supervised Learning by Cross-Modal Audio-Video Clustering
- Video Event Detection: From Subvolume Localization to Spatiotemporal Path Search
- SCSampler: Sampling Salient Clips From Video for Efficient Action Recognition
- Transformation-Based Models of Video Sequences
- Max-Margin Structured Output Regression for Spatio-Temporal Action Localization
- Open-World Instance Segmentation: Exploiting Pseudo Ground Truth From Learned Pairwise Affinity
- Optimal spatio-temporal path discovery for video event detection
- FLAVR: Flow-Agnostic Video Representations for Fast Frame Interpolation