ICLR 2021 accepted papers on Video
18 of the 860 papers accepted at ICLR 2021 (2.1%) are on Video, compared with 1.7% at ICLR 2020. They fall into 4 topics.
See ICLR 2021 in the interactive map
Submitting to ICLR? 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
Video segmentation and tracking · 10 papers
- Into the Wild with AudioScope: Unsupervised Audio-Visual Separation of On-Screen Sounds (36 citations)
- CT-Net: Channel Tensorization Network for Video Classification (25 citations)
- Self-Supervised Learning of Compressed Video Representations (10 citations)
- Revisiting Hierarchical Approach for Persistent Long-Term Video Prediction (8 citations)
- Spatially Structured Recurrent Modules (7 citations)
- Hierarchical Autoregressive Modeling for Neural Video Compression (6 citations)
- VA-RED$^2$: Video Adaptive Redundancy Reduction (5 citations)
- Learning Cross-Domain Correspondence for Control with Dynamics Cycle-Consistency (4 citations)
- Unsupervised Audiovisual Synthesis via Exemplar Autoencoders (4 citations)
- Factorizing Declarative and Procedural Knowledge in Structured, Dynamical Environments
