TPAMI 2023 papers on Video
42 of the 664 papers published in TPAMI 2023 (6.3%) are on Video, compared with 6.3% at TPAMI 2022. They fall into 4 topics.
See TPAMI 2023 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
Video segmentation and tracking · 23 papers
- Local-Global Context Aware Transformer for Language-Guided Video Segmentation (116 citations)
- Neighbourhood Representative Sampling for Efficient End-to-End Video Quality Assessment (114 citations)
- Facial Video-based Remote Physiological Measurement via Self-supervised Learning (89 citations)
- CycMuNet+: Cycle-Projected Mutual Learning for Spatial-Temporal Video Super-Resolution (40 citations)
- Event-Based Background-Oriented Schlieren (39 citations)
- Cascaded Deep Video Deblurring Using Temporal Sharpness Prior and Non-Local Spatial-Temporal Similarity (30 citations)
- Language-Aware Spatial-Temporal Collaboration for Referring Video Segmentation (30 citations)
- SequenceMorph: A Unified Unsupervised Learning Framework for Motion Tracking on Cardiac Image Sequences (29 citations)
- Learning to Super-Resolve Blurry Images With Events (26 citations)
- Temporal Perceiver: A General Architecture for Arbitrary Boundary Detection (23 citations)
- Learning Degradation-Robust Spatiotemporal Frequency-Transformer for Video Super-Resolution (20 citations)
- Sensing Diversity and Sparsity Models for Event Generation and Video Reconstruction from Events (19 citations)
and 11 more in the interactive map.
Action recognition · 13 papers
- Video Transformers: A Survey (200 citations)
- Temporal Action Segmentation: An Analysis of Modern Techniques (155 citations)
- Progressive Instance-Aware Feature Learning for Compositional Action Recognition (117 citations)
- Vectorized Evidential Learning for Weakly-Supervised Temporal Action Localization (83 citations)
- Temporal Action Localization in the Deep Learning Era: A Survey (81 citations)
- C2F-TCN: A Framework for Semi- and Fully-Supervised Temporal Action Segmentation (65 citations)
- Action Recognition and Benchmark Using Event Cameras (61 citations)
- Gate-Shift-Fuse for Video Action Recognition (38 citations)
- Self-Supervised 3D Action Representation Learning With Skeleton Cloud Colorization (37 citations)
- Uncertainty-Aware Dual-Evidential Learning for Weakly-Supervised Temporal Action Localization (33 citations)
- ContextLoc++: A Unified Context Model for Temporal Action Localization (15 citations)
- Bilateral Relation Distillation for Weakly Supervised Temporal Action Localization (12 citations)
and 1 more in the interactive map.
Video-language understanding · 4 papers
- Temporal Sentence Grounding in Videos: A Survey and Future Directions (106 citations)
- Contrastive Video Question Answering via Video Graph Transformer (75 citations)
- Learning Hierarchical Modular Networks for Video Captioning (43 citations)
- Variational Cross-Graph Reasoning and Adaptive Structured Semantics Learning for Compositional Temporal Grounding (22 citations)
Video generation · 2 papers
- Human Motion Generation: A Survey (143 citations)
- MNET++: Music-Driven Pluralistic Dancing Toward Multiple Dance Genre Synthesis (20 citations)
