mlsanityData to 14 Oct 2026

SegFlow: Joint Learning for Video Object Segmentation and Optical Flow

arXiv 1709.06750 ↗First posted 20 Sep 2017cs.CVcited by 92

Not on the map. Why?

Abstract (arXiv)

This paper proposes an end-to-end trainable network, SegFlow, for simultaneously predicting pixel-wise object segmentation and optical flow in videos. The proposed SegFlow has two branches where useful information of object segmentation and optical flow is propagated bidirectionally in a unified framework. The segmentation branch is based on a fully convolutional network, which has been proved effective in image segmentation task, and the optical flow branch takes advantage of the FlowNet model. The unified framework is trained iteratively offline to learn a generic notion, and fine-tuned online for specific objects. Extensive experiments on both the video object segmentation and optical flow datasets demonstrate that introducing optical flow improves the performance of segmentation and vice versa, against the state-of-the-art algorithms.

Key facts. Cited by 92 papers in the map (data through 14 Oct 2026). First posted on arXiv 20 Sep 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 28; 2022: 23; 2023: 24; 2024: 6; 2025: 9; 2026: 2.

92 papers.

Sort:

By area:

  1. 2023MOSE: A New Dataset for Video Object Segmentation in Complex Scenescited by 234
  2. 2021Self-supervised Video Object Segmentation by Motion Groupingcited by 147
  3. 2021A Survey on Deep Learning Technique for Video Segmentationcited by 132
  4. 2022Towards An End-to-End Framework for Flow-Guided Video Inpaintingcited by 113
  5. 2021SSTVOS: Sparse Spatiotemporal Transformers for Video Object Segmentationcited by 106
  6. 2021Efficient Regional Memory Network for Video Object Segmentationcited by 86
  7. 2021Full-Duplex Strategy for Video Object Segmentationcited by 78
  8. 2021STEP: Segmenting and Tracking Every Pixelcited by 73
  9. 2021Hierarchical Memory Matching Network for Video Object Segmentationcited by 72
  10. 2022Segmenting Moving Objects via an Object-Centric Layered Representationcited by 63
  11. 2025MOSEv2: A More Challenging Dataset for Video Object Segmentation in Complex Scenescited by 62
  12. 2022DIP: Deep Inverse Patchmatch for High-Resolution Optical Flowcited by 40
38 more
  1. 2022Per-Clip Video Object Segmentationcited by 40
  2. 2022Hierarchical Feature Alignment Network for Unsupervised Video Object Segmentationcited by 37
  3. 2021Reliable Propagation-Correction Modulation for Video Object Segmentationcited by 36
  4. 2022Learning Quality-aware Dynamic Memory for Video Object Segmentationcited by 35
  5. 2022Look Before You Match: Instance Understanding Matters in Video Object Segmentationcited by 34
  6. 2022EM-driven unsupervised learning for efficient motion segmentationcited by 33
  7. 2021Self-supervised Multi-view Stereo via Effective Co-Segmentation and Data-Augmentationcited by 31
  8. 2021AuxAdapt: Stable and Efficient Test-Time Adaptation for Temporally Consistent Video Semantic Segmentationcited by 31
  9. 2022Unsupervised Video Object Segmentation via Prototype Memory Networkcited by 30
  10. 2021Iteratively Selecting an Easy Reference Frame Makes Unsupervised Video Object Segmentation Easiercited by 27
  11. 2022PVO: Panoptic Visual Odometrycited by 26
  12. 2022OGC: Unsupervised 3D Object Segmentation from Rigid Dynamics of Point Cloudscited by 25
  13. 2022Vision+X: A Survey on Multimodal Learning in the Light of Datacited by 22
  14. 2022Global Spectral Filter Memory Network for Video Object Segmentationcited by 22
  15. 2021VIL-100: A New Dataset and A Baseline Model for Video Instance Lane Detectioncited by 21
  16. 2021HODOR: High-level Object Descriptors for Object Re-segmentation in Video Learned from Static Imagescited by 21
  17. 2023Guided Slot Attention for Unsupervised Video Object Segmentationcited by 19
  18. 2021Multi-Source Fusion and Automatic Predictor Selection for Zero-Shot Video Object Segmentationcited by 18
  19. 2022MulViMotion: Shape-aware 3D Myocardial Motion Tracking from Multi-View Cardiac MRIcited by 16
  20. 2023MobileVOS: Real-Time Video Object Segmentation Contrastive Learning meets Knowledge Distillationcited by 16
  21. 2022A Simple and Powerful Global Optimization for Unsupervised Video Object Segmentationcited by 15
  22. 2025Exploiting Temporal State Space Sharing for Video Semantic Segmentationcited by 15
  23. 2022BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentationcited by 14
  24. 2021Video Salient Object Detection via Contrastive Features and Attention Modulescited by 13
  25. 2022SiamMask: A Framework for Fast Online Object Tracking and Segmentationcited by 13
  26. 2021Video Instance Segmentation by Instance Flow Assemblycited by 12
  27. 2022Towards Robust Video Object Segmentation with Adaptive Object Calibrationcited by 11
  28. 2021Accelerating Video Object Segmentation with Compressed Videocited by 10
  29. 2022Implicit Motion-Compensated Network for Unsupervised Video Object Segmentationcited by 10
  30. 2021Learning to Better Segment Objects from Unseen Classes with Unlabeled Videoscited by 9
  31. 2023Co-attention Propagation Network for Zero-Shot Video Object Segmentationcited by 9
  32. 2023Tracking Anything in High Qualitycited by 9
  33. 2023CML-MOTS: Collaborative Multi-task Learning for Multi-Object Tracking and Segmentationcited by 9
  34. 2022The Right Spin: Learning Object Motion from Rotation-Compensated Flow Fieldscited by 8
  35. 2023Event-Free Moving Object Segmentation from Moving Ego Vehiclecited by 8
  36. 2023Amodal Optical Flowcited by 8
  37. 2024UnSAMFlow: Unsupervised Optical Flow Guided by Segment Anything Modelcited by 8
  38. 2021MUNet: Motion Uncertainty-aware Semi-supervised Video Object Segmentationcited by 7

50 most cited of 92 All 92 (JSON)