ECCV 2024 accepted papers on Video
287 of the 2,387 papers accepted at ECCV 2024 (12.0%) are on Video, compared with 12.1% at ECCV 2022. They fall into 4 topics.
See ECCV 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 · 103 papers
- Follow the Rules: Reasoning for Video Anomaly Detection with Large Language Models (75 citations)
- DINO-Tracker: Taming DINO for Self-Supervised Point Tracking in a Single Video (50 citations)
- Stream Query Denoising for Vectorized HD-Map Construction (44 citations)
- Motion-Guided Latent Diffusion for Temporally Consistent Real-world Video Super-resolution (38 citations)
- SAFNet: Selective Alignment Fusion Network for Efficient HDR Imaging (38 citations)
- Learning Natural Consistency Representation for Face Forgery Video Detection (34 citations)
- Event-Adapted Video Super-Resolution (29 citations)
- Cross-Platform Video Person ReID: A New Benchmark Dataset and Adaptation Approach (28 citations)
- Exploring Pre-trained Text-to-Video Diffusion Models for Referring Video Object Segmentation (27 citations)
- Put Myself in Your Shoes: Lifting the Egocentric Perspective from Exocentric Videos (27 citations)
- SNeRV: Spectra-preserving Neural Representation for Video (24 citations)
- Towards Real-world Event-guided Low-light Video Enhancement and Deblurring (24 citations)
and 91 more in the interactive map.
Video generation · 90 papers
- DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors (296 citations)
- Photorealistic Video Generation with Diffusion Models (259 citations)
- EMO: Emote Portrait Alive - Generating Expressive Portrait Videos with Audio2Video Diffusion Model under Weak Conditions (214 citations)
- SparseCtrl: Adding Sparse Controls to Text-to-Video Diffusion Models (152 citations)
- MotionDirector: Motion Customization of Text-to-Video Diffusion Models (138 citations)
- MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Model (113 citations)
- Motion Mamba: Efficient and Long Sequence Motion Generation (109 citations)
- Factorizing Text-to-Video Generation by Explicit Image Conditioning (87 citations)
- TLControl: Trajectory and Language Control for Human Motion Synthesis (81 citations)
- FreeInit: Bridging Initialization Gap in Video Diffusion Models (72 citations)
- STAG4D: Spatial-Temporal Anchored Generative 4D Gaussians (70 citations)
- VideoStudio: Generating Consistent-Content and Multi-Scene Videos (65 citations)
and 78 more in the interactive map.
Video-language understanding · 54 papers
- VideoMamba: State Space Model for Efficient Video Understanding (511 citations)
- InternVideo2: Scaling Foundation Models for Multimodal Video Understanding (438 citations)
- LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models (405 citations)
- VideoAgent: Long-form Video Understanding with Large Language Model as Agent (196 citations)
- VideoAgent: A Memory-augmented Multimodal Agent for Video Understanding (118 citations)
- LongVLM: Efficient Long Video Understanding via Large Language Models (109 citations)
- LITA: Language Instructed Temporal-Localization Assistant (91 citations)
- ST-LLM: Large Language Models Are Effective Temporal Learners (82 citations)
- AutoEval-Video: An Automatic Benchmark for Assessing Large Vision Language Models in Open-Ended Video Question Answering (40 citations)
- Training-free Video Temporal Grounding using Large-scale Pre-trained Models (38 citations)
- BAM-DETR: Boundary-Aligned Moment Detection Transformer for Temporal Sentence Grounding in Videos (35 citations)
- Goldfish: Vision-Language Understanding of Arbitrarily Long Videos (35 citations)
and 42 more in the interactive map.
Action recognition · 40 papers
- VideoMamba: Spatio-Temporal Selective State Space Model (46 citations)
- DyFADet: Dynamic Feature Aggregation for Temporal Action Detection (35 citations)
- PALM: Predicting Actions through Language Models (32 citations)
- EgoExo-Fitness: Towards Egocentric and Exocentric Full-Body Action Understanding (29 citations)
- Referring Atomic Video Action Recognition (25 citations)
- DailyDVS-200: A Comprehensive Benchmark Dataset for Event-Based Action Recognition (24 citations)
- Vision-Language Action Knowledge Learning for Semantic-Aware Action Quality Assessment (23 citations)
- Occluded Gait Recognition with Mixture of Experts: An Action Detection Perspective (21 citations)
- UniMD: Towards Unifying Moment Retrieval and Temporal Action Detection (21 citations)
- Leveraging temporal contextualization for video action recognition (19 citations)
- On the Utility of 3D Hand Poses for Action Recognition (19 citations)
- Masked Video and Body-worn IMU Autoencoder for Egocentric Action Recognition (18 citations)
and 28 more in the interactive map.
