mlsanityData to 14 Oct 2026

The 1st Solution for MOSEv2 Challenge 2025: Long-term and Concept-aware Video Segmentation via SeC

arXiv 2509.19183 ↗First posted 23 Sep 2025cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

This technical report explores the MOSEv2 track of the LSVOS Challenge, which targets complex semi-supervised video object segmentation. By analysing and adapting SeC, an enhanced SAM-2 framework, we conduct a detailed study of its long-term memory and concept-aware memory, showing that long-term memory preserves temporal continuity under occlusion and reappearance, while concept-aware memory supplies semantic priors that suppress distractors; together, these traits directly benefit several MOSEv2's core challenges. Our solution achieves a JF score of 39.89% on the test set, ranking 1st in the MOSEv2 track of the LSVOS Challenge.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 21 of its 26 references that are in the map. First posted on arXiv 23 Sep 2025.

Builds on

21 of 26 references.

References · 21

  1. 2023Visual Instruction Tuningcited by 7,869
  2. 2025Qwen2.5-VL Technical Reportcited by 5,587
  3. 2024SAM 2: Segment Anything in Images and Videoscited by 2,863
  4. 2024Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scalingcited by 1,599
  5. 2022XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Modelcited by 439
  6. 2019Video Object Segmentation using Space-Time Memory Networkscited by 438
  7. 2018YouTube-VOS: A Large-Scale Video Object Segmentation Benchmarkcited by 383
  8. 2023MOSE: A New Dataset for Video Object Segmentation in Complex Scenescited by 234
  9. 2023MeViS: A Large-scale Benchmark for Video Segmentation with Motion Expressionscited by 228
  10. 2023Putting the Object Back into Video Object Segmentationcited by 188
  11. 2025Sa2VA: Marrying SAM2 with MLLM for Dense Grounded Understanding of Images and Videoscited by 159
  12. 2024VISA: Reasoning Video Object Segmentation via Large Language Modelscited by 127
9 more
  1. 2024One Token to Seg Them All: Language Instructed Reasoning Segmentation in Videoscited by 100
  2. 2024SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memorycited by 94
  3. 2024SAM2Long: Enhancing SAM 2 for Long Video Segmentation with a Training-Free Memory Treecited by 80
  4. 2022LVOS: A Benchmark for Long-term Video Object Segmentationcited by 77
  5. 2024A Distractor-Aware Memory for Visual Object Tracking with SAM2cited by 66
  6. 2025MOSEv2: A More Challenging Dataset for Video Object Segmentation in Complex Scenescited by 62
  7. 2024VideoDirector: Precise Video Editing via Text-to-Video Modelscited by 36
  8. 2025Advancing Complex Video Object Segmentation via Progressive Concept Constructioncited by 26
  9. 2025Caption Anything in Video: Fine-grained Object-centric Captioning via Spatiotemporal Multimodal Promptingcited by 10

Built on by

Not cited yet.