TPAMI 2024 papers on Video
65 of the 666 papers published in TPAMI 2024 (9.8%) are on Video, compared with 6.3% at TPAMI 2023. They fall into 4 topics.
See TPAMI 2024 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 · 37 papers
- Contrast-Phys+: Unsupervised and Weakly-Supervised Video-Based Remote Physiological Measurement via Spatiotemporal Contrast (81 citations)
- Dense Continuous-Time Optical Flow From Event Cameras (74 citations)
- Analysis of Video Quality Datasets via Design of Minimalistic Video Quality Models (57 citations)
- Fully Unsupervised Deepfake Video Detection Via Enhanced Contrastive Learning (57 citations)
- Scalable Video Object Segmentation With Identification Mechanism (55 citations)
- A Coding Framework and Benchmark Towards Low-Bitrate Video Understanding (52 citations)
- Scene-Dependent Prediction in Latent Space for Video Anomaly Detection and Anticipation (46 citations)
- E-Gaze: Gaze Estimation With Event Camera (42 citations)
- VNVC: A Versatile Neural Video Coding Framework for Efficient Human-Machine Vision (41 citations)
- BiSTNet: Semantic Image Prior Guided Bidirectional Temporal Feature Fusion for Deep Exemplar-Based Video Colorization (36 citations)
- Self-Supervised Deep Blind Video Super-Resolution (32 citations)
- Learning Local and Global Temporal Contexts for Video Semantic Segmentation (31 citations)
and 25 more in the interactive map.
Action recognition · 13 papers
- InfoGCN++: Learning Representation by Predicting the Future for Online Skeleton-Based Action Recognition (39 citations)
- Hypergraph-Based Multi-View Action Recognition Using Event Cameras (34 citations)
- One-Shot Action Recognition via Multi-Scale Spatial-Temporal Skeleton Matching (29 citations)
- A Semantic and Motion-Aware Spatiotemporal Transformer Network for Action Detection (27 citations)
- Building an Open-Vocabulary Video CLIP Model With Better Architectures, Optimization and Data (27 citations)
- DeTAL: Open-Vocabulary Temporal Action Localization With Decoupled Networks (27 citations)
- Multi-Task Learning of Object States and State-Modifying Actions From Web Videos (23 citations)
- Human-Centric Transformer for Domain Adaptive Action Recognition (21 citations)
- Uni-AdaFocus: Spatial-Temporal Dynamic Computation for Video Recognition (20 citations)
- DiffAct++: Diffusion Action Segmentation (17 citations)
- Uncertainty-Boosted Robust Video Activity Anticipation (13 citations)
- Markov Progressive Framework, a Universal Paradigm for Modeling Long Videos (4 citations)
and 1 more in the interactive map.
Video-language understanding · 8 papers
- Enhancing Video-Language Representations With Structural Spatio-Temporal Alignment (72 citations)
- A Review of Deep Learning for Video Captioning (71 citations)
- CoVR-2: Automatic Data Construction for Composed Video Retrieval (38 citations)
- Query-Oriented Micro-Video Summarization (17 citations)
- Cap4Video++: Enhancing Video Understanding With Auxiliary Captions (9 citations)
- Single-Frame Supervision for Spatio-Temporal Video Grounding (7 citations)
- Hierarchical Banzhaf Interaction for General Video-Language Representation Learning (5 citations)
- Ego4D: Around the World in 3,600 Hours of Egocentric Video
Video generation · 7 papers
- MotionDiffuse: Text-Driven Human Motion Generation With Diffusion Model (896 citations)
- LIA: Latent Image Animator (160 citations)
- A Modular Neural Motion Retargeting System Decoupling Skeleton and Shape Perception (54 citations)
- Memories are One-to-Many Mapping Alleviators in Talking Face Generation (27 citations)
- StyleTalk++: A Unified Framework for Controlling the Speaking Styles of Talking Heads (18 citations)
- Fast-Vid2Vid++: Spatial-Temporal Distillation for Real-Time Video-to-Video Synthesis (8 citations)
- Chinese Title Generation for Short Videos: Dataset, Metric and Algorithm
