NeurIPS 2018 accepted papers on Video
15 of the 1,008 papers accepted at NeurIPS 2018 (1.5%) are on Video, compared with 1.2% at NeurIPS 2017. They fall into 4 topics.
See NeurIPS 2018 in the interactive map
Submitting to NeurIPS? Checklist →
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 · 7 papers
- Cooperative Learning of Audio and Video Models from Self-Supervised Synchronization (331 citations)
- Unsupervised Learning of View-invariant Action Representations (90 citations)
- Trajectory Convolution for Action Recognition (80 citations)
- A flexible model for training action localization with varying levels of supervision (25 citations)
- VideoCapsuleNet: A Simplified Network for Action Detection (16 citations)
- A^2-Nets: Double Attention Networks (13 citations)
- Sequence-to-Segment Networks for Segment Detection (9 citations)
Video segmentation and tracking · 6 papers
- Learning to Decompose and Disentangle Representations for Video Prediction (136 citations)
- Compact Generalized Non-local Network (131 citations)
- Video-to-Video Synthesis (123 citations)
- Self-Supervised Generation of Spatial Audio for 360° Video (77 citations)
- Video Prediction via Selective Sampling (16 citations)
- Adaptive Skip Intervals: Temporal Abstraction for Recurrent Dynamical Models (6 citations)
Video generation · 1 paper
Video-language understanding · 1 paper
- Weakly Supervised Dense Event Captioning in Videos (62 citations)
