IJCV 2023 papers on Video
19 of the 220 papers published in IJCV 2023 (8.6%) are on Video, compared with 8.1% at IJCV 2022. They fall into 4 topics.
See IJCV 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 · 12 papers
- PhysFormer++: Facial Video-Based Physiological Measurement with SlowFast Temporal Difference Transformer (152 citations)
- Adaptive Deep PnP Algorithm for Video Snapshot Compressive Imaging (43 citations)
- In the Eye of Transformer: Global–Local Correlation for Egocentric Gaze Estimation and Beyond (43 citations)
- Context-Driven Detection of Invertebrate Species in Deep-Sea Video (26 citations)
- DeepFTSG: Multi-stream Asymmetric USE-Net Trellis Encoders with Shared Decoder Feature Fusion Architecture for Video Motion Segmentation (19 citations)
- Fast Ultra High-Definition Video Deblurring via Multi-scale Separable Network (16 citations)
- An Efficient Recurrent Adversarial Framework for Unsupervised Real-Time Video Enhancement (10 citations)
- A Spatio-Temporal Robust Tracker with Spatial-Channel Transformer and Jitter Suppression (9 citations)
- Conditional Temporal Variational AutoEncoder for Action Video Prediction (9 citations)
- Towards Automated Ethogramming: Cognitively-Inspired Event Segmentation for Streaming Wildlife Video Monitoring (7 citations)
- Local Compressed Video Stream Learning for Generic Event Boundary Detection (6 citations)
- Memory Based Temporal Fusion Network for Video Deblurring (4 citations)
Action recognition · 5 papers
- HiEve: A Large-Scale Benchmark for Human-Centric Video Analysis in Complex Events (148 citations)
- CLIP-guided Prototype Modulating for Few-shot Action Recognition (99 citations)
- Extreme Low-Resolution Action Recognition with Confident Spatial-Temporal Attention Transfer (18 citations)
- Dynamic Context Removal: A General Training Strategy for Robust Models on Video Action Predictive Tasks (6 citations)
- Universal Prototype Transport for Zero-Shot Action Recognition and Localization (5 citations)
