mlsanityData to 7 Oct 2026

Tube-Link: A Flexible Cross Tube Framework for Universal Video Segmentation

arXiv 2303.12782 ↗First posted 22 Mar 2023cs.CVcited by 23

Not on the map. Why?

Abstract (arXiv)

Video segmentation aims to segment and track every pixel in diverse scenarios accurately. In this paper, we present Tube-Link, a versatile framework that addresses multiple core tasks of video segmentation with a unified architecture. Our framework is a near-online approach that takes a short subclip as input and outputs the corresponding spatial-temporal tube masks. To enhance the modeling of cross-tube relationships, we propose an effective way to perform tube-level linking via attention along the queries. In addition, we introduce temporal contrastive learning to instance-wise discriminative features for tube-level association. Our approach offers flexibility and efficiency for both short and long video inputs, as the length of each subclip can be varied according to the needs of datasets or scenarios. Tube-Link outperforms existing specialized architectures by a significant margin on five video segmentation datasets. Specifically, it achieves almost 13% relative improvements on VIPSeg and 4% improvements on KITTI-STEP over the strong baseline Video K-Net. When using a ResNet50 backbone on Youtube-VIS-2019 and 2021, Tube-Link boosts IDOL by 3% and 4%, respectively.

Key facts. Cited by 23 papers in the map (data through 7 Oct 2026). Builds on 70 of its 77 references that are in the map. First posted on arXiv 22 Mar 2023.

Builds on

70 of 77 references.

References · 70

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  4. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  5. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  6. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  7. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  8. 2020End-to-End Object Detection with Transformerscited by 7,384
  9. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  10. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
  11. 2016Pyramid Scene Parsing Networkcited by 2,472
  12. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,385
38 more
  1. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,338
  2. 2016V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentationcited by 2,284
  3. 2019MMDetection: Open MMLab Detection Toolbox and Benchmarkcited by 1,379
  4. 2021Per-Pixel Classification is Not All You Need for Semantic Segmentationcited by 1,148
  5. 2017Simple Online and Realtime Tracking with a Deep Association Metriccited by 908
  6. 2016Simple Online and Realtime Trackingcited by 862
  7. 2020End-to-End Video Instance Segmentation with Transformerscited by 443
  8. 2019Video Instance Segmentationcited by 391
  9. 2020MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformerscited by 355
  10. 2020Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentationcited by 326
  11. 2019SOLO: Segmenting Objects by Locationscited by 289
  12. 2023MOSE: A New Dataset for Video Object Segmentation in Complex Scenescited by 232
  13. 2020Quasi-Dense Similarity Learning for Multiple Object Trackingcited by 220
  14. 2021K-Net: Towards Unified Image Segmentationcited by 211
  15. 2016Deep Feature Flow for Video Recognitioncited by 186
  16. 2017Flow-Guided Feature Aggregation for Video Object Detectioncited by 177
  17. 2021Mask2Former for Video Instance Segmentationcited by 169
  18. 2021Occluded Video Instance Segmentation: A Benchmarkcited by 154
  19. 2020Video Panoptic Segmentationcited by 141
  20. 2019Classifying, Segmenting, and Tracking Object Instances in Video with Mask Propagationcited by 125
  21. 2021Rethinking BiSeNet For Real-time Semantic Segmentationcited by 124
  22. 2021Video Instance Segmentation using Inter-Frame Communication Transformerscited by 105
  23. 2021SeqFormer: Sequential Transformer for Video Instance Segmentationcited by 98
  24. 2022In Defense of Online Models for Video Instance Segmentationcited by 97
  25. 2020ViP-DeepLab: Learning Visual Perception with Depth-aware Video Panoptic Segmentationcited by 95
  26. 2022VITA: Video Instance Segmentation via Object Token Associationcited by 94
  27. 2022MinVIS: A Minimal Video Instance Segmentation Framework without Video-based Trainingcited by 94
  28. 2021Crossover Learning for Fast Online Video Instance Segmentationcited by 83
  29. 2016Learning by tracking: Siamese CNN for robust target associationcited by 79
  30. 2022Video K-Net: A Simple, Strong, and Unified Baseline for Video Segmentationcited by 79
  31. 2022TransVOD: End-to-End Video Object Detection with Spatial-Temporal Transformerscited by 78
  32. 2019Online Multi-Object Tracking with Dual Matching Attention Networkscited by 77
  33. 2019Relation Distillation Networks for Video Object Detectioncited by 77
  34. 2019Spatial-Temporal Relation Networks for Multi-Object Trackingcited by 74
  35. 2021Video Instance Segmentation with a Propose-Reduce Paradigmcited by 74
  36. 2021STEP: Segmenting and Tracking Every Pixelcited by 72
  37. 2021Do Different Tracking Tasks Require Different Appearance Models?cited by 62
  38. 2016Clockwork Convnets for Video Semantic Segmentationcited by 55

50 most cited of 70 All 70 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 4; 2024: 9; 2025: 8; 2026: 2.

23 papers.

Sort:

By area:

  1. 2023MeViS: A Large-scale Benchmark for Video Segmentation with Motion Expressionscited by 225
  2. 2025MatAnyone: Stable Video Matting with Consistent Memory Propagationcited by 24
  3. 2025Are They the Same? Exploring Visual Correspondence Shortcomings of Multimodal LLMscited by 16
  4. 2025Exploiting Temporal State Space Sharing for Video Semantic Segmentationcited by 15
  5. 2024CAVIS: Context-Aware Video Instance Segmentationcited by 11
  6. 2024Motion-aware Contrastive Learning for Temporal Panoptic Scene Graph Generationcited by 9
  7. 2025The 1st Solution for 7th LSVOS RVOS Track: SaSaSa2VAcited by 7
  8. 2023Integrating Boxes and Masks: A Multi-Object Framework for Unified Visual Tracking and Segmentationcited by 5
  9. 2023Iterative Robust Visual Grounding with Masked Reference based Centerpoint Supervisioncited by 3
  10. 20254th PVUW MeViS 3rd Place Report: Sa2VAcited by 2
  11. 2025A Comprehensive Survey on Video Scene Parsing:Advances, Challenges, and Prospectscited by 2
  12. 2023MED-VT++: Unifying Multimodal Learning with a Multiscale Encoder-Decoder Video Transformercited by 1
11 more
  1. 2024Deep Spectral Improvement for Unsupervised Image Instance Segmentationcited by 1
  2. 2024PiPa++: Towards Unification of Domain Adaptive Semantic Segmentation via Self-supervised Learningcited by 1
  3. 2024Semantic Segmentation on VSPW Dataset through Masked Video Consistencycited by 0
  4. 2024Rethinking Video Segmentation with Masked Video Consistency: Did the Model Learn as Intended?cited by 0
  5. 2024Improving Weakly-supervised Video Instance Segmentation by Leveraging Spatio-temporal Consistencycited by 0
  6. 2024Shift and matching queries for video semantic segmentationcited by 0
  7. 2024Configurable Embodied Data Generation for Class-Agnostic RGB-D Video Segmentationcited by 0
  8. 2025Local2Global query Alignment for Video Instance Segmentationcited by 0
  9. 2025Temporal Cluster Assignment for Efficient Real-Time Video Segmentationcited by 0
  10. 2026SaSaSaSa2VA: 2nd Place of the 5th PVUW MeViS-Text Trackcited by 0
  11. 2026Hard-Region Supervision: #1 on the Waymo Open Dataset 2D Video Panoptic Segmentation Leaderboardcited by 0