Real-VAS: a Real-World Video Amodal Segmentation Dataset
cs.CV
Submitted: 2026-10-30
Updated: 2026-11-12
Terminology
Sources
- YOLOv4: Optimal Speed and Accuracy of Object Detection
- The WILDTRACK Multi-Camera Person Dataset
- Improved Regularization of Convolutional Neural Networks with Cutout
- CATER: A diagnostic dataset for Compositional Actions and TEmporal Reasoning
- TAO-Amodal: A Benchmark for Tracking Any Object Amodally
- Track Anything Behind Everything: Zero-Shot Amodal Video Object Segmentation
- CoTracker3: Simpler and Better Point Tracking by Pseudo-Labelling Real Videos
- Training for X-Ray Vision: Amodal Segmentation, Amodal Content Completion, and View-Invariant Object Representation from Multi-Camera Video
- SAM 2: Segment Anything in Images and Videos
- Unsupervised Object Learning via Common Fate
- Attentive CutMix: An Enhanced Data Augmentation Approach for Deep Learning Based Image Classification
- Amodal3R: Amodal 3D Reconstruction from Occluded 2D Images
- Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection
- Robustness of Object Recognition under Extreme Occlusion in Humans and Computational Models
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs