ECCV 2016 accepted papers on Video
45 of the 415 papers accepted at ECCV 2016 (10.8%) are on Video. They fall into 4 topics.
See ECCV 2016 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
Action recognition · 21 papers
- Temporal Segment Networks: Towards Good Practices for Deep Action Recognition (4,257 citations)
- Spatio-Temporal LSTM with Trust Gates for 3D Human Action Recognition (1,377 citations)
- Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding (1,134 citations)
- Shuffle and Learn: Unsupervised Learning Using Temporal Order Verification (816 citations)
- DAPs: Deep Action Proposals for Action Understanding (406 citations)
- Multi-region Two-Stream R-CNN for Action Detection (376 citations)
- Segmental Spatiotemporal CNNs for Fine-Grained Action Segmentation (256 citations)
- Connectionist Temporal Modeling for Weakly Supervised Action Labeling (222 citations)
- Online Human Action Detection Using Joint Classification-Regression Recurrent Neural Networks (219 citations)
- Online Action Detection (211 citations)
- RNN Fisher Vectors for Action Recognition and Image Annotation (173 citations)
- Human Attribute Recognition by Deep Hierarchical Contexts (161 citations)
and 9 more in the interactive map.
Video segmentation and tracking · 16 papers
- MARS: A Video Benchmark for Large-Scale Person Re-Identification (1,020 citations)
- Ambient Sound Provides Supervision for Visual Learning (391 citations)
- Robust Image and Video Dehazing with Visual Artifact Suppression via Gradient Residual Minimization (251 citations)
- A Discriminative Framework for Anomaly Detection in Large Videos (202 citations)
- Learning Image Matching by Simply Watching Video (199 citations)
- MeshFlow: Minimum Latency Online Video Stabilization (164 citations)
- A Recurrent Encoder-Decoder Network for Sequential Face Alignment (153 citations)
- Learning Temporal Transformations from Time-Lapse Videos (137 citations)
- Knowledge Transfer for Scene-Specific Motion Prediction (116 citations)
- Angry Crowds: Detecting Violent Events in Videos (96 citations)
- Ego2Top: Matching Viewers in Egocentric and Top-View Videos (49 citations)
- Learning Dynamic Hierarchical Models for Anytime Scene Labeling (15 citations)
and 4 more in the interactive map.
Video-language understanding · 6 papers
- Video Summarization with Long Short-Term Memory (784 citations)
- Query-Focused Extractive Video Summarization (135 citations)
- Title Generation for User Generated Videos (79 citations)
- CATS: Co-saliency Activated Tracklet Selection for Video Co-localization (61 citations)
- Detecting Engagement in Egocentric Video (47 citations)
- Recurrent Temporal Deep Field for Semantic Video Labeling (13 citations)
Video generation · 2 papers
- ActionSnapping: Motion-Based Video Synchronization (14 citations)
- Heat Diffusion Long-Short Term Memory Learning for 3D Shape Analysis (14 citations)
