IJCV 2026 papers on Video
71 of the 477 papers published in IJCV 2026 (14.9%) are on Video, compared with 11.7% at IJCV 2025. They fall into 4 topics.
See IJCV 2026 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 · 23 papers
- FoleyCrafter: Bring Silent Videos to Life with Lifelike and Synchronized Sounds (119 citations)
- FreeTraj: Tuning-Free Trajectory Control via Noise Guided Video Diffusion (61 citations)
- Diffusion Model-Based Video Editing: A Survey (55 citations)
- Follow-Your-Emoji-Faster: Towards Efficient, Fine-Controllable, and Expressive Freestyle Portrait Animation (51 citations)
- ObjCtrl-2.5D: Training-free Object Control with Camera Poses (25 citations)
- T2VShield: Model-Agnostic Jailbreak Defense for Text-to-Video Models (14 citations)
- OmniDrag: Enabling Motion Control for Omnidirectional Image-to-Video Generation (10 citations)
- CrowdMoGen: Event-Driven Collective Human Motion Generation (8 citations)
- OpenVid++: A Large-scale High-quality Dataset for Text-to-video Generation (7 citations)
- 4DVD: Cascaded Dense-view Video Diffusion Model for High-quality 4D Content Generation (5 citations)
- Towards Scene-Aware Video-to-Spatial Audio Generation (5 citations)
- Unlock Pose Diversity: Accurate and Efficient Implicit Keypoint-based Spatiotemporal Diffusion for Audio-driven Talking Portrait (5 citations)
and 11 more in the interactive map.
Video segmentation and tracking · 18 papers
- Event-based Simultaneous Localization and Mapping: A Comprehensive Survey (44 citations)
- Spatiotemporal Predictive Pre-training for Robotic Motor Control (28 citations)
- Unveiling Deep Shadows: A Survey and Benchmark on Image and Video Shadow Detection, Removal, and Generation in the Deep Learning Era (18 citations)
- Exploring What Why and How: A Multifaceted Benchmark for Causation Understanding of Video Anomaly (17 citations)
- HR-INR: Continuous Space-Time Video Super-Resolution via Event Camera (11 citations)
- Watching Swarm Dynamics from Above: A Framework for Advanced Object Tracking in Drone Videos (6 citations)
- Recurrence over Video Frames (RoVF) for Animal Re-identification (5 citations)
- AlphaChimp: Tracking and Behavior Recognition of Chimpanzees (4 citations)
- A Motion-Based Compression and Tracking System for Video Camera Trap-Based Insect Behaviour Studies (3 citations)
- Self-Supervised Video Representation Learning in a Heuristic Decoupled Perspective (2 citations)
- FaverNet: All-in-One Video Restoration via Frequency-Discriminative Conditioning (1 citation)
- Video Shadow Detection with Intra-and Inter-video Cooperation (1 citation)
and 6 more in the interactive map.
Video-language understanding · 17 papers
- Kangaroo: A Powerful Video-Language Model Supporting Long-context Video Input (142 citations)
- Sports-QA: A Large-Scale Video Question Answering Benchmark for Complex and Professional Sports (45 citations)
- Long Story Short: Story-level Video Understanding from 20K Short Films (25 citations)
- A Decade of Action Quality Assessment: Largest Systematic Survey of Trends, Challenges, and Future Directions (17 citations)
- Dr.V : A Hierarchical Perception-Temporal-Cognition Framework to Diagnose Video Hallucination by Fine-Grained Spatial-Temporal Grounding (11 citations)
- Bridging Perspectives: A Survey on Cross-view Collaborative Intelligence with Egocentric-Exocentric Vision (9 citations)
- HACG: Leveraging Hierarchical Alignment and Caption Generation for Text-Video Retrieval (4 citations)
- Looking Beyond the Obvious: A Survey on Abstract Concept Recognition for Video Understanding (4 citations)
- Looking Beyond Visible Cues: Implicit Video Question Answering via Dual-Clue Reasoning (3 citations)
- Collaborative Temporal Consistency Learning for Point-supervised Natural Language Video Localization (2 citations)
- It’s Just Another Day: Unique Video Captioning by Discriminitive Prompting (2 citations)
- L-VOCAL: Language-based Video Colorization with Audio Alignment (1 citation)
and 5 more in the interactive map.
Action recognition · 13 papers
- Event Stream based Human Action Recognition: A High-Definition Benchmark Dataset and Algorithms (24 citations)
- DeST: A Decoupled Spatio-Temporal Framework for Action Segmentation (17 citations)
- Efficient Action Counting with Dynamic Queries (6 citations)
- Mouse Lockbox Dataset: Behavior Recognition for Mice Solving Lockboxes (5 citations)
- Selective Volume Mixup for Video Action Recognition (5 citations)
- CompViT: Real-Time Compressed Video Action Recognition with Asymmetric Transformer Networks (1 citation)
- Towards Generalizing Temporal Action Segmentation to Unseen Views (1 citation)
- An Effective-Efficient Approach for Dense Multi-Label Action Detection
- De-biasing Skeleton-Based Action Recognition with Convex Hull Adaptive Shift
- Exocentric-to-Egocentric Adaptation for Temporal Action Segmentation with Unlabeled Synchronized Video Pairs
- Knowledge is Power: Advancing Few-shot Action Recognition with Multimodal Semantics from MLLMs
- MPANet: Motion Pattern Aggregation Network for Gait Recognition
and 1 more in the interactive map.
