mlsanityData to 7 Oct 2026

Hierarchical Instance Tracking to Balance Privacy Preservation with Accessible Information

arXiv 2512.10102 ↗First posted 10 Dec 2025cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

We propose a novel task, hierarchical instance tracking, which entails tracking all instances of predefined categories of objects and parts, while maintaining their hierarchical relationships. We introduce the first benchmark dataset supporting this task, consisting of 2,765 unique entities that are tracked in 552 videos and belong to 40 categories (across objects and parts). Evaluation of seven variants of four models tailored to our novel task reveals the new dataset is challenging. Our dataset is available at https://vizwiz.org/tasks-and-datasets/hierarchical-instance-tracking/

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 45 of its 68 references that are in the map. First posted on arXiv 10 Dec 2025.

Builds on

45 of 68 references.

References · 45

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2024SAM 2: Segment Anything in Images and Videoscited by 2,784
  5. 2016Semantic Understanding of Scenes through the ADE20K Datasetcited by 1,063
  6. 2017The 2017 DAVIS Challenge on Video Object Segmentationcited by 942
  7. 2020HOTA: A Higher Order Metric for Evaluating Multi-Object Trackingcited by 546
  8. 2019Video Instance Segmentationcited by 391
  9. 2014Detect What You Can: Detecting and Representing Objects using Holistic Models and Body Partscited by 230
  10. 2023Semantic-SAM: Segment and Recognize Anything at Any Granularitycited by 185
  11. 2021Mask2Former for Video Instance Segmentationcited by 169
  12. 2023PACO: Parts and Attributes of Common Objectscited by 146
33 more
  1. 2018Instance-level Human Parsing via Part Grouping Networkcited by 134
  2. 2020Captioning Images Taken by People Who Are Blindcited by 108
  3. 2021PartImageNet: A Large, High-Quality Dataset of Partscited by 107
  4. 2018Look into Person: Joint Body Parsing & Pose Estimation Network and A New Benchmarkcited by 79
  5. 2018Understanding Humans in Crowded Scenes: Deep Nested Adversarial Learning and A New Benchmark for Multi-Human Parsingcited by 60
  6. 2018ApolloCar3D: A Large 3D Car Instance Understanding Benchmark for Autonomous Drivingcited by 59
  7. 2018Fast and Accurate Online Video Object Segmentation via Tracking Partscited by 57
  8. 2021Part-aware Panoptic Segmentationcited by 56
  9. 2023Hierarchical Open-vocabulary Universal Image Segmentationcited by 53
  10. 2023XMem++: Production-level Video Segmentation From Few Annotated Framescited by 53
  11. 2022Grounding Answers for Visual Questions Asked by Visually Impaired Peoplecited by 47
  12. 2022Tracking Every Thing in the Wildcited by 44
  13. 2019Why Does a Visual Question Have Different Answers?cited by 34
  14. 2018ModaNet: A Large-Scale Street Fashion Dataset with Polygon Annotationscited by 33
  15. 2023OV-PARTS: Towards Open-Vocabulary Part Segmentationcited by 31
  16. 2021ORBIT: A Real-World Few-Shot Dataset for Teachable Object Recognitioncited by 29
  17. 2020Assessing Image Quality Issues for Real-World Problemscited by 28
  18. 2025EgoBlind: Towards Egocentric Visual Assistance for the Blindcited by 19
  19. 2024Long-Form Answers to Visual Questions from Blind and Low Vision Peoplecited by 18
  20. 2020Vision Skills Needed to Answer Visual Questionscited by 17
  21. 2023VQA Therapy: Exploring Answer Differences by Visually Grounding Answerscited by 14
  22. 2023Visual Dependency Transformers: Dependency Tree Emerges from Reversed Attentioncited by 12
  23. 2024Privacy-Aware Visual Language Modelscited by 12
  24. 2022VizWiz-FewShot: Locating Objects in Images Taken by People With Visual Impairmentscited by 11
  25. 2023Salient Object Detection for Images Taken by People With Vision Impairmentscited by 7
  26. 2025Acknowledging Focus Ambiguity in Visual Questionscited by 7
  27. 2024BIV-Priv-Seg: Locating Private Content in Images Taken by People With Visual Impairmentscited by 5
  28. 2024Identifying Crucial Objects in Blind and Low-Vision Individuals' Navigationcited by 5
  29. 2024A Dataset for Crucial Object Recognition in Blind and Low-Vision Individuals' Navigationcited by 4
  30. 2016Deformable Parts Correlation Filters for Robust Visual Trackingcited by 2
  31. 2018Learning a Robust Society of Tracking Parts using Co-occurrence Constraintscited by 2
  32. 2025Exploring Object Status Recognition for Recipe Progress Tracking in Non-Visual Cookingcited by 2
  33. 2018Part-based Tracking by Samplingcited by 1

Built on by

Not cited yet.