mlsanityData to 14 Oct 2026

What is Point Supervision Worth in Video Instance Segmentation?

arXiv 2404.01990 ↗First posted 1 Apr 2024cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

Video instance segmentation (VIS) is a challenging vision task that aims to detect, segment, and track objects in videos. Conventional VIS methods rely on densely-annotated object masks which are expensive. We reduce the human annotations to only one point for each object in a video frame during training, and obtain high-quality mask predictions close to fully supervised models. Our proposed training method consists of a class-agnostic proposal generation module to provide rich negative samples and a spatio-temporal point-based matcher to match the object queries with the provided point annotations. Comprehensive experiments on three VIS benchmarks demonstrate competitive performance of the proposed framework, nearly matching fully supervised methods.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 63 of its 69 references that are in the map. First posted on arXiv 1 Apr 2024.

Builds on

63 of 69 references.

References · 63

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  2. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  3. 2020End-to-End Object Detection with Transformerscited by 7,414
  4. 2017Mask R-CNNcited by 7,277
  5. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,351
  6. 2019YOLACT: Real-time Instance Segmentationcited by 443
  7. 2020End-to-End Video Instance Segmentation with Transformerscited by 443
  8. 2019Video Instance Segmentationcited by 393
  9. 2018Learning Category-Specific Mesh Reconstruction from Image Collectionscited by 317
  10. 2018Learning 3D Human Dynamics from Videocited by 316
  11. 2020Conditional Convolutions for Instance Segmentationcited by 314
  12. 2015What's the Point: Semantic Segmentation with Point Supervisioncited by 298
38 more
  1. 2019SOLO: Segmenting Objects by Locationscited by 289
  2. 2019Weakly Supervised Learning of Instance Segmentation with Inter-pixel Relationscited by 247
  3. 2019CenterMask : Real-Time Anchor-Free Instance Segmentationcited by 201
  4. 2019PolarMask: Single Shot Instance Segmentation with Polar Representationcited by 188
  5. 2021Mask2Former for Video Instance Segmentationcited by 171
  6. 2021Track to Detect and Segment: An Online Multi-Object Trackercited by 156
  7. 2021Occluded Video Instance Segmentation: A Benchmarkcited by 154
  8. 2020BoxInst: High-Performance Instance Segmentation with Box Annotationscited by 151
  9. 2021Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusioncited by 129
  10. 2019Classifying, Segmenting, and Tracking Object Instances in Video with Mask Propagationcited by 125
  11. 2016Fully Convolutional Instance-aware Semantic Segmentationcited by 123
  12. 2020STEm-Seg: Spatio-temporal Embeddings for Instance Segmentation in Videoscited by 121
  13. 2020SipMask: Spatial Information Preservation for Fast Image and Video Instance Segmentationcited by 108
  14. 2019Three-D Safari: Learning to Estimate Zebra Pose, Shape, and Texture from Images "In the Wild"cited by 106
  15. 2021Video Instance Segmentation using Inter-Frame Communication Transformerscited by 105
  16. 2022FreeSOLO: Learning to Segment Objects without Annotationscited by 102
  17. 2022FocalClick: Towards Practical Interactive Image Segmentationcited by 102
  18. 2022In Defense of Online Models for Video Instance Segmentationcited by 97
  19. 2022MinVIS: A Minimal Video Instance Segmentation Framework without Video-based Trainingcited by 94
  20. 2020Shape and Viewpoint without Keypointscited by 92
  21. 2021SG-Net: Spatial Granularity Network for One-Stage Video Instance Segmentationcited by 87
  22. 2021Crossover Learning for Fast Online Video Instance Segmentationcited by 83
  23. 2021Pointly-Supervised Instance Segmentationcited by 83
  24. 2015Learning to Segment Object Candidatescited by 79
  25. 2018Weakly Supervised Instance Segmentation using Class Peak Responsecited by 75
  26. 2021Video Instance Segmentation with a Propose-Reduce Paradigmcited by 74
  27. 2016Learning to Refine Object Segmentscited by 67
  28. 2021Points as Queries: Weakly Semi-supervised Object Detection by Pointscited by 60
  29. 2021DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box Supervisioncited by 59
  30. 2022Temporally Efficient Vision Transformer for Video Instance Segmentationcited by 55
  31. 2020CompFeat: Comprehensive Feature Aggregation for Video Instance Segmentationcited by 53
  32. 2018The 2018 DAVIS Challenge on Video Object Segmentationcited by 47
  33. 2020Mask Encoding for Single Shot Instance Segmentationcited by 47
  34. 2019Dynamic Context Correspondence Network for Semantic Alignmentcited by 43
  35. 2021Spatial Feature Calibration and Temporal Fusion for Effective One-stage Video Instance Segmentationcited by 42
  36. 2022PseudoClick: Interactive Image Segmentation with Click Imitationcited by 42
  37. 2023Towards Scalable Neural Representation for Diverse Videoscited by 37
  38. 2020Weakly Supervised Instance Segmentation by Learning Annotation Consistent Instancescited by 32

50 most cited of 63 All 63 (JSON)

Built on by

Cited by year

Citing papers per year: 2024: 2; 2025: 3.

5 papers.

  1. 2024ARDuP: Active Region Video Diffusion for Universal Policiescited by 10
  2. 2025TREND: Tri-teaching for Robust Preference-based Reinforcement Learning with Demonstrationscited by 7
  3. 2025Trokens: Semantic-Aware Relational Trajectory Tokens for Few-Shot Action Recognitioncited by 7
  4. 2024UVIS: Unsupervised Video Instance Segmentationcited by 5
  5. 2025Hierarchical Visual Prompt Learning for Continual Video Instance Segmentationcited by 2