YouTube-VO
Emerging21papers using it
19HF downloads
0HF likes
2018first seen
YouTube-VO is a dataset used to evaluate video action detection, specifically focusing on spatiotemporal localization and classification in the context of semi-supervised learning.
Papers using YouTube-VO (21)
- Collaborative Video Object Segmentation By Foreground-background IntegrationYoutube-vos: Sequence-to-sequence Video Object SegmentationDmm-net: Differentiable Mask-matching Network For Video Object SegmentationRegion Aware Video Object Segmentation With Deep Motion ModelingStable Mean Teacher For Semi-supervised Video Action DetectionAdaptive Memory Management For Video Object SegmentationRVOS: End-to-end Recurrent Network For Video Object SegmentationUnidentified Video Objects: A Benchmark For Dense, Open-world SegmentationSWEM: Towards Real-time Video Object Segmentation With Sequential Weighted Expectation-maximizationBoltvos: Box-level Tracking For Video Object SegmentationALBA : Reinforcement Learning For Video Object SegmentationCollaborative Video Object Segmentation by Foreground-Background IntegrationTransVOS: Video Object Segmentation with TransformersCollaborative Video Object Segmentation by Multi-Scale Foreground-Background IntegrationVORNet: Spatio-temporally Consistent Video Inpainting for Object RemovalLearning Position and Target Consistency for Memory-based Video Object SegmentationDiscriminative Online Learning for Fast Video Object SegmentationLearning Dynamic Network Using a Reuse Gate Function in Semi-supervised Video Object SegmentationWeakly Supervised Few-shot Object Segmentation using Co-Attention with Visual and Semantic EmbeddingsHierarchical Spatiotemporal Transformers for Video Object SegmentationSSTVOS: Sparse Spatiotemporal Transformers for Video Object Segmentation