AAAI 2024 accepted papers on Video
112 of the 2,864 papers accepted at AAAI 2024 (3.9%) are on Video, compared with 4.0% at AAAI 2023. They fall into 4 topics.
See AAAI 2024 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 · 54 papers
- TF-CLIP: Learning Text-Free CLIP for Video-Based Person Re-identification (57 citations)
- WaveFormer: Wavelet Transformer for Noise-Robust Video Inpainting (55 citations)
- HARDVS: Revisiting Human Activity Recognition with Dynamic Vision Sensors (48 citations)
- Referred by Multi-Modality: A Unified Temporal Transformer for Video Object Segmentation (40 citations)
- EulerMormer: Robust Eulerian Motion Magnification via Dynamic Filtering within Transformer (32 citations)
- Wavelet-Driven Spatiotemporal Predictive Learning: Bridging Frequency and Time Variations (30 citations)
- Offline and Online Optical Flow Enhancement for Deep Video Compression (26 citations)
- Deep Hierarchical Video Compression (25 citations)
- TCNet: Continuous Sign Language Recognition from Trajectories and Correlated Regions (23 citations)
- E2HQV: High-Quality Video Generation from Event Camera via Theory-Inspired Model-Aided Deep Learning (18 citations)
- Hawkes-Enhanced Spatial-Temporal Hypergraph Contrastive Learning Based on Criminal Correlations (18 citations)
- Temporal Correlation Vision Transformer for Video Person Re-Identification (16 citations)
and 42 more in the interactive map.
Video-language understanding · 26 papers
- CoVR: Learning Composed Video Retrieval from Web Video Captions (50 citations)
- Towards Balanced Alignment: Modal-Enhanced Semantic Modeling for Video Moment Retrieval (42 citations)
- Bias-Conflict Sample Synthesis and Adversarial Removal Debias Strategy for Temporal Sentence Grounding in Video (18 citations)
- Gaussian Mixture Proposals with Pull-Push Learning Scheme to Capture Diverse Events for Weakly Supervised Temporal Video Grounding (18 citations)
- Towards Efficient and Effective Text-to-Video Retrieval with Coarse-to-Fine Visual Representation Learning (18 citations)
- GMMFormer: Gaussian-Mixture-Model Based Transformer for Efficient Partially Relevant Video Retrieval (17 citations)
- Local-Global Multi-Modal Distillation for Weakly-Supervised Temporal Video Grounding (16 citations)
- Fewer Steps, Better Performance: Efficient Cross-Modal Clip Trimming for Video Moment Retrieval Using Language (15 citations)
- VLN-Video: Utilizing Driving Videos for Outdoor Vision-and-Language Navigation (14 citations)
- From Raw Video to Pedagogical Insights: A Unified Framework for Student Behavior Analysis (9 citations)
- Exploiting Auxiliary Caption for Video Grounding (8 citations)
- Video-Context Aligned Transformer for Video Question Answering (8 citations)
and 14 more in the interactive map.
Video generation · 20 papers
- Follow Your Pose: Pose-Guided Text-to-Video Generation Using Pose-Free Videos (122 citations)
- LDMVFI: Video Frame Interpolation with Latent Diffusion Models (76 citations)
- Diverse and Aligned Audio-to-Video Generation via Text-to-Video Model Adaptation (35 citations)
- V2Meow: Meowing to the Visual Beat via Video-to-Music Generation (18 citations)
- Collaborative Tooth Motion Diffusion Model in Digital Orthodontics (14 citations)
- MeDM: Mediating Image Diffusion Models for Video-to-Video Translation with Temporal Correspondence Guidance (13 citations)
- AMD: Autoregressive Motion Diffusion (12 citations)
- Say Anything with Any Style (11 citations)
- FG-EmoTalk: Talking Head Video Generation with Fine-Grained Controllable Facial Expressions (9 citations)
- F³-Pruning: A Training-Free and Generalized Pruning Strategy towards Faster and Finer Text-to-Video Synthesis (8 citations)
- Towards Detailed Text-to-Motion Synthesis via Basic-to-Advanced Hierarchical Diffusion Model (7 citations)
- ConditionVideo: Training-Free Condition-Guided Video Generation (6 citations)
and 8 more in the interactive map.
Action recognition · 12 papers
- HR-Pro: Point-Supervised Temporal Action Localization via Hierarchical Reliability Propagation (28 citations)
- Weakly-Supervised Temporal Action Localization by Inferring Salient Snippet-Feature (26 citations)
- Spatio-Temporal Fusion for Human Action Recognition via Joint Trajectory Graph (19 citations)
- Unsupervised Action Segmentation via Fast Learning of Semantically Consistent Actoms (19 citations)
- ViSTec: Video Modeling for Sports Technique Recognition and Tactical Analysis (12 citations)
- Semi-supervised Active Learning for Video Action Detection (11 citations)
- Generative Model-Based Feature Knowledge Distillation for Action Recognition (9 citations)
- Towards Understanding Future: Consistency Guided Probabilistic Modeling for Action Anticipation (8 citations)
- Count What You Want: Exemplar Identification and Few-Shot Counting of Human Actions in the Wild (3 citations)
- Jointly Modeling Spatio-Temporal Features of Tactile Signals for Action Classification (3 citations)
- Open-Vocabulary Video Relation Extraction (1 citation)
- Intentional Evolutionary Learning for Untrimmed Videos with Long Tail Distribution