CVPR 2023 accepted papers on Video
238 of the 2,359 papers accepted at CVPR 2023 (10.1%) are on Video, compared with 10.7% at CVPR 2022. They fall into 4 topics.
See CVPR 2023 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest accepted papers by meaning and how crowded the spot has become.
Topics and papers
Video segmentation and tracking · 120 papers
- VideoMAE V2: Scaling Video Masked Autoencoders With Dual Masking (497 citations)
- Neural Video Compression With Diverse Contexts (246 citations)
- Temporal Attention Unit: Towards Efficient Spatiotemporal Predictive Learning (209 citations)
- DropMAE: Masked Autoencoders With Spatial-Attention Dropout for Tracking Tasks (178 citations)
- Continuous Sign Language Recognition With Correlation Network (145 citations)
- Extracting Motion and Appearance via Inter-Frame Attention for Efficient Video Frame Interpolation (135 citations)
- AltFreezing for More General Video Face Forgery Detection (126 citations)
- HyperReel: High-Fidelity 6-DoF Video With Ray-Conditioned Sampling (124 citations)
- HNeRV: A Hybrid Neural Representation for Videos (118 citations)
- Video Event Restoration Based on Keyframes for Video Anomaly Detection (110 citations)
- Rethinking the Learning Paradigm for Dynamic Facial Expression Recognition (107 citations)
- TransFlow: Transformer As Flow Learner (104 citations)
and 108 more in the interactive map.
Video-language understanding · 50 papers
- Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning (245 citations)
- Fine-Tuned CLIP Models Are Efficient Video Learners (179 citations)
- Query-Dependent Video Representation for Moment Retrieval and Highlight Detection (157 citations)
- Learning Video Representations From Large Language Models (155 citations)
- All in One: Exploring Unified Video-Language Pre-Training (148 citations)
- Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval? (138 citations)
- Selective Structured State-Spaces for Long-Form Video Understanding (107 citations)
- MIST: Multi-Modal Iterative Spatial-Temporal Transformer for Long-Form Video Question Answering (88 citations)
- Text With Knowledge Graph Augmented Transformer for Video Captioning (84 citations)
- Revisiting Temporal Modeling for CLIP-Based Image-to-Video Knowledge Transferring (72 citations)
- Video-Text As Game Players: Hierarchical Banzhaf Interaction for Cross-Modal Representation Learning (71 citations)
- VoP: Text-Video Co-Operative Prompt Tuning for Cross-Modal Retrieval (70 citations)
and 38 more in the interactive map.
Action recognition · 41 papers
- TriDet: Temporal Action Detection With Relative Boundary Modeling (213 citations)
- Learning Discriminative Representations for Skeleton Based Action Recognition (208 citations)
- SVFormer: Semi-Supervised Video Transformer for Action Recognition (118 citations)
- Vita-CLIP: Video and Text Adaptive CLIP via Multimodal Prompting (111 citations)
- MoLo: Motion-Augmented Long-Short Contrastive Learning for Few-Shot Action Recognition (101 citations)
- Proposal-Based Multiple Instance Learning for Weakly-Supervised Temporal Action Localization (61 citations)
- Hierarchical Temporal Transformer for 3D Hand Pose Estimation and Action Recognition From Egocentric RGB Videos (56 citations)
- LOGO: A Long-Form Video Dataset for Group Action Quality Assessment (51 citations)
- PivoTAL: Prior-Driven Supervision for Weakly-Supervised Temporal Action Localization (48 citations)
- Neural Koopman Pooling: Control-Inspired Temporal Dynamics Encoding for Skeleton-Based Action Recognition (46 citations)
- MammalNet: A Large-Scale Video Benchmark for Mammal Recognition and Behavior Understanding (42 citations)
- Open Set Action Recognition via Multi-Label Evidential Learning (35 citations)
and 29 more in the interactive map.
Video generation · 27 papers
- Executing Your Commands via Motion Diffusion in Latent Space (341 citations)
- Generating Human Motion From Textual Descriptions With Discrete Representations (311 citations)
- Mofusion: A Framework for Denoising-Diffusion-Based Motion Synthesis (153 citations)
- MM-Diffusion: Learning Multi-Modal Diffusion Models for Joint Audio and Video Generation (148 citations)
- MAGVIT: Masked Generative Video Transformer (118 citations)
- Conditional Image-to-Video Generation With Latent Flow Diffusion Models (117 citations)
- Video Probabilistic Diffusion Models in Projected Latent Space (116 citations)
- Seeing What You Said: Talking Face Generation Guided by a Lip Reading Expert (109 citations)
- Identity-Preserving Talking Face Generation With Landmark and Appearance Priors (96 citations)
- Trace and Pace: Controllable Pedestrian Animation via Guided Trajectory Diffusion (92 citations)
- Progressive Disentangled Representation Learning for Fine-Grained Controllable Talking Head Synthesis (57 citations)
- DPE: Disentanglement of Pose and Expression for General Video Portrait Editing (55 citations)
and 15 more in the interactive map.