mlsanityData to 7 Oct 2026

Revisiting Click-based Interactive Video Object Segmentation

arXiv 2203.01784 ↗First posted 3 Mar 2022cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

While current methods for interactive Video Object Segmentation (iVOS) rely on scribble-based interactions to generate precise object masks, we propose a Click-based interactive Video Object Segmentation (CiVOS) framework to simplify the required user workload as much as possible. CiVOS builds on de-coupled modules reflecting user interaction and mask propagation. The interaction module converts click-based interactions into an object mask, which is then inferred to the remaining frames by the propagation module. Additional user interactions allow for a refinement of the object mask. The approach is extensively evaluated on the popular interactive~DAVIS dataset, but with an inevitable adaptation of scribble-based interactions with click-based counterparts. We consider several strategies for generating clicks during our evaluation to reflect various user inputs and adjust the DAVIS performance metric to perform a hardware-independent comparison. The presented CiVOS pipeline achieves competitive results, although requiring a lower user workload.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 25 of its 33 references that are in the map. First posted on arXiv 3 Mar 2022.

Builds on

25 of 33 references.

References · 25

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,417
  3. 2017The 2017 DAVIS Challenge on Video Object Segmentationcited by 942
  4. 2019Segmentation Transformer: Object-Contextual Representations for Semantic Segmentationcited by 573
  5. 2015What's the Point: Semantic Segmentation with Point Supervisioncited by 297
  6. 2016One-Shot Video Object Segmentationcited by 233
  7. 2021Reviving Iterative Training with Mask Guidance for Interactive Segmentationcited by 162
  8. 2016Deep Interactive Object Selectioncited by 160
  9. 2021A Survey on Deep Learning Technique for Video Segmentationcited by 132
  10. 2021Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusioncited by 129
  11. 2020f-BRS: Rethinking Backpropagating Refinement for Interactive Segmentationcited by 117
  12. 2019Large-scale interactive object segmentation with human annotatorscited by 109
13 more
  1. 2019The 2019 DAVIS Challenge on VOS: Unsupervised Multi-Object Segmentationcited by 95
  2. 2018Blazingly Fast Video Object Segmentation with Pixel-Wise Metric Learningcited by 74
  3. 2018Iteratively Trained Interactive Segmentationcited by 52
  4. 2018The 2018 DAVIS Challenge on Video Object Segmentationcited by 47
  5. 2020Memory Aggregation Networks for Efficient Interactive Video Object Segmentationcited by 40
  6. 2019Continuous Adaptation for Interactive Object Segmentation by Learning from Correctionscited by 36
  7. 2019Fast User-Guided Video Object Segmentation by Interaction-and-Propagation Networkscited by 33
  8. 2020Interactive Video Object Segmentation Using Global and Local Transfer Modulescited by 26
  9. 2021Guided Interactive Video Object Segmentation Using Reliability-Based Attention Mapscited by 21
  10. 2021Learning to Recommend Frame for Interactive Video Object Segmentation in the Wildcited by 18
  11. 2017Interactive Video Object Segmentation in the Wildcited by 16
  12. 2020ScribbleBox: Interactive Annotation Framework for Video Object Segmentationcited by 14
  13. 2016Click Carving: Segmenting Objects in Video with Point Clickscited by 8

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 3; 2025: 1.

5 papers.

  1. 2024SAM 2: Segment Anything in Images and Videoscited by 2,784
  2. 2025MOSEv2: A More Challenging Dataset for Video Object Segmentation in Complex Scenescited by 59
  3. 2023Learning the What and How of Annotation in Video Object Segmentationcited by 19
  4. 2024Strike the Balance: On-the-Fly Uncertainty based User Interactions for Long-Term Video Object Segmentationcited by 4
  5. 2024IDPro: Flexible Interactive Video Object Segmentation by ID-queried Concurrent Propagationcited by 1