mlsanityData to 14 Oct 2026

THU-Warwick Submission for EPIC-KITCHEN Challenge 2025: Semi-Supervised Video Object Segmentation

arXiv 2506.06748 ↗First posted 7 Jun 2025cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

In this report, we describe our approach to egocentric video object segmentation. Our method combines large-scale visual pretraining from SAM2 with depth-based geometric cues to handle complex scenes and long-term tracking. By integrating these signals in a unified framework, we achieve strong segmentation performance. On the VISOR test set, our method reaches a J&F score of 90.1%.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 21 of its 24 references that are in the map. First posted on arXiv 7 Jun 2025.

Builds on

21 of 24 references.

References · 21

  1. 2024SAM 2: Segment Anything in Images and Videoscited by 2,863
  2. 2021Vision Transformers for Dense Predictioncited by 1,803
  3. 2024Depth Anything V2cited by 1,422
  4. 2017The 2017 DAVIS Challenge on Video Object Segmentationcited by 957
  5. 2023Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectivescited by 490
  6. 2022XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Modelcited by 439
  7. 2019Video Object Segmentation using Space-Time Memory Networkscited by 438
  8. 2018YouTube-VOS: A Large-Scale Video Object Segmentation Benchmarkcited by 383
  9. 2023Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistlescited by 290
  10. 2016One-Shot Video Object Segmentationcited by 235
  11. 2023MOSE: A New Dataset for Video Object Segmentation in Complex Scenescited by 234
  12. 2023Putting the Object Back into Video Object Segmentationcited by 188
9 more
  1. 2019FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentationcited by 178
  2. 2022EPIC-KITCHENS VISOR Benchmark: VIdeo Segmentations and Object Relationscited by 140
  3. 2025HD-EPIC: A Highly-Detailed Egocentric Video Datasetcited by 104
  4. 2020Video Object Segmentation with Adaptive Feature Bank and Uncertain-Region Refinementcited by 101
  5. 2024SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memorycited by 94
  6. 2023An Outlook into the Future of Egocentric Visioncited by 84
  7. 2024SAM2Long: Enhancing SAM 2 for Long Video Segmentation with a Training-Free Memory Treecited by 80
  8. 2024A Distractor-Aware Memory for Visual Object Tracking with SAM2cited by 66
  9. 2024LVOS: A Benchmark for Large-scale Long-term Video Object Segmentationcited by 44

Built on by

Not cited yet.