IJCV 2025 papers on Video
31 of the 266 papers published in IJCV 2025 (11.7%) are on Video, compared with 10.5% at IJCV 2024. They fall into 4 topics.
See IJCV 2025 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 generation · 10 papers
- Swap Attention in Spatiotemporal Diffusions for Text-to-Video Generation (160 citations)
- MoonShot: Towards Controllable Video Generation and Editing with Motion-Aware Multimodal Conditions (67 citations)
- Fg-T2M++: LLMs-Augmented Fine-Grained Text Driven Human Motion Generation (45 citations)
- LaMD: Latent Motion Diffusion for Image-Conditional Video Generation (43 citations)
- Contrastive Decoupled Representation Learning and Regularization for Speech-Preserving Facial Expression Manipulation (14 citations)
- LDTrack: Dynamic People Tracking by Service Robots Using Diffusion Models (10 citations)
- Audio-Guided Video Scene Editing (6 citations)
- ScenarioDiff: Text-to-video Generation with Dynamic Transformations of Scene Conditions (5 citations)
- Autoregressive Temporal Modeling for Advanced Tracking-by-Diffusion (1 citation)
- FreerCustom: Training-Free Multi-Concept Customization for Image and Video Generation (1 citation)
Action recognition · 10 papers
- A Comprehensive Review of Few-Shot Action Recognition (33 citations)
- About Time: Advances, Challenges, and Outlooks of Action Understanding (17 citations)
- UIL-AQA: Uncertainty-Aware Clip-Level Interpretable Action Quality Assessment (16 citations)
- From Forest to Zoo: Great Ape Behavior Recognition with ChimpBehave (14 citations)
- FineBio: A Fine-Grained Video Dataset of Biological Experiments with Hierarchical Annotation (10 citations)
- Feature Hallucination for Self-supervised Action Recognition (7 citations)
- Skim then Focus: Integrating Contextual and Fine-grained Views for Repetitive Action Counting (7 citations)
- Are you Struggling? Dataset and Baselines for Struggle Determination in Assembly Videos (4 citations)
- Pre-training for Action Recognition with Automatically Generated Fractal Datasets (1 citation)
- $$\text {A}^2\text {M}^2$$-Net: Adaptively Aligned Multi-scale Moment for Few-Shot Action Recognition
Video segmentation and tracking · 6 papers
- Dual-Space Video Person Re-identification (34 citations)
- Temporal Transductive Inference for Few-Shot Video Object Segmentation (15 citations)
- Few-Shot Referring Video Single- and Multi-Object Segmentation Via Cross-Modal Affinity with Instance Sequence Matching (11 citations)
- Instance-Level Moving Object Segmentation from a Single Image with Events (7 citations)
- RIGID: Recurrent GAN Inversion and Editing of Real Face Videos and Beyond (4 citations)
- Language-guided Recursive Spatiotemporal Graph Modeling for Video Summarization (3 citations)
Video-language understanding · 5 papers
- Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding (177 citations)
- LvBench: A Benchmark for Long-form Video Understanding with Versatile Multi-modal Question Answering (48 citations)
- StimuVAR: Spatiotemporal Stimuli-Aware Video Affective Reasoning with Multimodal Large Language Models (41 citations)
- VideoQA in the Era of LLMs: An Empirical Study (28 citations)
- Effectively Leveraging CLIP for Generating Situational Summaries of Images and Videos (5 citations)
