mlsanityData to 7 Oct 2026

Maximal Cliques on Multi-Frame Proposal Graph for Unsupervised Video Object Segmentation

arXiv 2301.12352 ↗First posted 29 Jan 2023cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

Unsupervised Video Object Segmentation (UVOS) aims at discovering objects and tracking them through videos. For accurate UVOS, we observe if one can locate precise segment proposals on key frames, subsequent processes are much simpler. Hence, we propose to reason about key frame proposals using a graph built with the object probability masks initially generated from multiple frames around the key frame and then propagated to the key frame. On this graph, we compute maximal cliques, with each clique representing one candidate object. By making multiple proposals in the clique to vote for the key frame proposal, we obtain refined key frame proposals that could be better than any of the single-frame proposals. A semi-supervised VOS algorithm subsequently tracks these key frame proposals to the entire video. Our algorithm is modular and hence can be used with any instance segmentation and semi-supervised VOS algorithm. We achieve state-of-the-art performance on the DAVIS-2017 validation and test-dev dataset. On the related problem of video instance segmentation, our method shows competitive performance with the previous best algorithm that requires joint training with the VOS algorithm.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 49 of its 64 references that are in the map. First posted on arXiv 29 Jan 2023.

Builds on

49 of 64 references.

References · 49

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2020End-to-End Object Detection with Transformerscited by 7,384
  3. 2017Mask R-CNNcited by 7,259
  4. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,338
  5. 2021Per-Pixel Classification is Not All You Need for Semantic Segmentationcited by 1,148
  6. 2017The 2017 DAVIS Challenge on Video Object Segmentationcited by 942
  7. 2018Path Aggregation Network for Instance Segmentationcited by 796
  8. 2020End-to-End Video Instance Segmentation with Transformerscited by 443
  9. 2019Video Object Segmentation using Space-Time Memory Networkscited by 436
  10. 2019Video Instance Segmentationcited by 391
  11. 2020MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformerscited by 355
  12. 2019SOLO: Segmenting Objects by Locationscited by 289
37 more
  1. 2019Mask Scoring R-CNNcited by 265
  2. 2016One-Shot Video Object Segmentationcited by 233
  3. 2016Associative Embedding: End-to-End Learning for Joint Detection and Groupingcited by 211
  4. 2021Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentationcited by 200
  5. 2019PolarMask: Single Shot Instance Segmentation with Polar Representationcited by 188
  6. 2019FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentationcited by 178
  7. 2016Learning Video Object Segmentation from Static Imagescited by 151
  8. 2020See More, Know More: Unsupervised Video Object Segmentation with Co-Attention Siamese Networkscited by 138
  9. 2019Classifying, Segmenting, and Tracking Object Instances in Video with Mask Propagationcited by 125
  10. 2020STEm-Seg: Spatio-temporal Embeddings for Instance Segmentation in Videoscited by 121
  11. 2017Semantic Instance Segmentation with a Discriminative Loss Functioncited by 118
  12. 2020Kernelized Memory Network for Video Object Segmentationcited by 111
  13. 2020SipMask: Spatial Information Preservation for Fast Image and Video Instance Segmentationcited by 108
  14. 2021Video Instance Segmentation using Inter-Frame Communication Transformerscited by 105
  15. 2018Efficient Video Object Segmentation via Network Modulationcited by 98
  16. 2021SeqFormer: Sequential Transformer for Video Instance Segmentationcited by 98
  17. 2019The 2019 DAVIS Challenge on VOS: Unsupervised Multi-Object Segmentationcited by 95
  18. 2017SegFlow: Joint Learning for Video Object Segmentation and Optical Flowcited by 92
  19. 2019RVOS: End-to-End Recurrent Network for Video Object Segmentationcited by 88
  20. 2020Zero-Shot Video Object Segmentation via Attentive Graph Neural Networkscited by 84
  21. 2018Blazingly Fast Video Object Segmentation with Pixel-Wise Metric Learningcited by 74
  22. 2021Video Instance Segmentation with a Propose-Reduce Paradigmcited by 74
  23. 2021SOLQ: Segmenting Objects by Learning Queriescited by 68
  24. 2020Fast Video Object Segmentation using the Global Context Modulecited by 65
  25. 2020Motion-Attentive Transition for Zero-Shot Video Object Segmentationcited by 62
  26. 2016Learning Motion Patterns in Videoscited by 53
  27. 2019Towards Segmenting Anything That Movescited by 51
  28. 2020UnOVOST: Unsupervised Offline Video Object Segmentation and Trackingcited by 34
  29. 2022Efficient Video Instance Segmentation via Tracklet Query and Proposalcited by 33
  30. 2018Object Discovery in Videos as Foreground Motion Clusteringcited by 32
  31. 2021VISOLO: Grid-Based Space-Time Aggregation for Efficient Online Video Instance Segmentationcited by 29
  32. 2021Target-Aware Object Discovery and Association for Unsupervised Video Multi-Object Segmentationcited by 21
  33. 2022End-to-end video instance segmentation via spatial-temporal graph neural networkscited by 16
  34. 2018Unsupervised Video Object Segmentation for Deep Reinforcement Learningcited by 11
  35. 2022Video Instance Segmentation via Multi-scale Spatio-temporal Split Attention Transformercited by 9
  36. 2020Deep Variational Instance Segmentationcited by 7
  37. 2021Space Time Recurrent Memory Networkcited by 1

Built on by

Cited by year

Citing papers per year: 2023: 1.

1 paper.

  1. 2023Out of Sight, Still in Mind: Reasoning and Planning about Unobserved Objects with Video Tracking Enabled Memory Modelscited by 5