IJCV 2021 papers on Video
16 of the 130 papers published in IJCV 2021 (12.3%) are on Video, compared with 5.9% at IJCV 2020. They fall into 3 topics.
See IJCV 2021 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 · 9 papers
- Rescaling Egocentric Vision: Collection, Pipeline and Challenges for EPIC-KITCHENS-100 (499 citations)
- Synthetic Humans for Action Recognition from Unseen Viewpoints (99 citations)
- Mimetics: Towards Understanding Human Actions Out of Context (79 citations)
- Quo Vadis, Skeleton Action Recognition? (69 citations)
- SportsCap: Monocular 3D Human Motion Capture and Fine-Grained Understanding in Challenging Sports Videos (69 citations)
- A Coarse-to-Fine Framework for Resource Efficient Video Recognition (44 citations)
- SODA: Weakly Supervised Temporal Action Localization Based on Astute Background Response and Self-Distillation Learning (39 citations)
- Spatial–Temporal Relation Reasoning for Action Prediction in Videos (35 citations)
- Object Priors for Classifying and Localizing Unseen Actions (19 citations)
Video segmentation and tracking · 5 papers
- Just Recognizable Distortion for Machine Vision Oriented Image and Video Coding (28 citations)
- Deep Maximum a Posterior Estimator for Video Denoising (25 citations)
- Dual-view Snapshot Compressive Imaging via Optical Flow Aided Recurrent Neural Network (12 citations)
- Physical Representation Learning and Parameter Identification from Video Using Differentiable Physics (12 citations)
- A Decomposable Winograd Method for N–D Convolution Acceleration in Video Analysis (6 citations)
