mlsanityData to 7 Oct 2026

BIV-Priv-Seg: Locating Private Content in Images Taken by People With Visual Impairments

arXiv 2407.18243 ↗First posted 25 Jul 2024cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

Individuals who are blind or have low vision (BLV) are at a heightened risk of sharing private information if they share photographs they have taken. To facilitate developing technologies that can help them preserve privacy, we introduce BIV-Priv-Seg, the first localization dataset originating from people with visual impairments that shows private content. It contains 1,028 images with segmentation annotations for 16 private object categories. We first characterize BIV-Priv-Seg and then evaluate modern models' performance for locating private content in the dataset. We find modern models struggle most with locating private objects that are not salient, small, and lack text as well as recognizing when private content is absent from an image. We facilitate future extensions by sharing our new dataset with the evaluation server at https://vizwiz.org/tasks-and-datasets/object-localization.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 44 of its 61 references that are in the map. First posted on arXiv 25 Jul 2024.

Builds on

44 of 61 references.

References · 44

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  3. 2023Segment Anythingcited by 8,158
  4. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  5. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,274
  6. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,350
  7. 2019LVIS: A Dataset for Large Vocabulary Instance Segmentationcited by 1,215
  8. 2016Semantic Understanding of Scenes through the ADE20K Datasetcited by 1,063
  9. 2016COCO-Stuff: Thing and Stuff Classes in Contextcited by 858
  10. 2018VizWiz Grand Challenge: Answering Visual Questions from Blind Peoplecited by 852
  11. 2023CogVLM: Visual Expert for Pretrained Language Modelscited by 704
  12. 2018The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scalecited by 542
32 more
  1. 2018Object Detection with Deep Learning: A Reviewcited by 524
  2. 2023GLaMM: Pixel Grounding Large Multimodal Modelcited by 447
  3. 2019YOLACT: Real-time Instance Segmentationcited by 441
  4. 2017One-Shot Learning for Semantic Segmentationcited by 337
  5. 2018Few-shot Object Detection via Feature Reweightingcited by 265
  6. 2019Few-Shot Object Detection with Attention-RPN and Multi-Relation Detectorcited by 206
  7. 2019Feature Weighting and Boosting for Few-Shot Segmentationcited by 189
  8. 2020Captioning Images Taken by People Who Are Blindcited by 108
  9. 2021DeFRCN: Decoupled Faster R-CNN for Few-Shot Object Detectioncited by 106
  10. 2017Towards a Visual Privacy Advisor: Understanding and Predicting Privacy Risks in Imagescited by 101
  11. 2021DETReg: Unsupervised Pretraining with Region Priors for Object Detectioncited by 76
  12. 2022Grounding Answers for Visual Questions Asked by Visually Impaired Peoplecited by 47
  13. 2020FGN: Fully Guided Network for Few-Shot Instance Segmentationcited by 46
  14. 2018One-Shot Instance Segmentationcited by 43
  15. 2022Revisiting Image Pyramid Structure for High Resolution Salient Object Detectioncited by 36
  16. 2019Why Does a Visual Question Have Different Answers?cited by 34
  17. 2021ORBIT: A Real-World Few-Shot Dataset for Teachable Object Recognitioncited by 29
  18. 2020Assessing Image Quality Issues for Real-World Problemscited by 28
  19. 2017Connecting Pixels to Privacy and Utility: Automatic Redaction of Private Information in Imagescited by 24
  20. 2023Few-Shot Object Detection via Variational Feature Aggregationcited by 22
  21. 2023Generating Features with Increased Crop-related Diversity for Few-Shot Object Detectioncited by 21
  22. 2020Vision Skills Needed to Answer Visual Questionscited by 17
  23. 2021FAPIS: A Few-shot Anchor-free Part-based Instance Segmentercited by 15
  24. 2022Disentangle and Remerge: Interventional Knowledge Distillation for Few-Shot Object Detection from A Conditional Causal Perspectivecited by 13
  25. 2022Breaking Immutable: Information-Coupled Prototype Elaboration for Few-Shot Object Detectioncited by 12
  26. 2024Privacy-Aware Visual Language Modelscited by 12
  27. 2022VizWiz-FewShot: Locating Objects in Images Taken by People With Visual Impairmentscited by 11
  28. 2021A Comparative Review of Recent Few-Shot Object Detection Algorithmscited by 10
  29. 2023NIFF: Alleviating Forgetting in Generalized Few-Shot Object Detection via Neural Instance Feature Forgingcited by 10
  30. 2023Salient Object Detection for Images Taken by People With Vision Impairmentscited by 7
  31. 2017Predicting Foreground Object Ambiguity and Efficiently Crowdsourcing the Segmentation(s)cited by 4
  32. 2023Meta-tuning Loss Functions and Data Augmentation for Few-shot Object Detectioncited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 4; 2026: 1.

5 papers.

  1. 2025Beyond Blanket Masking: Examining Granularity for Privacy Protection in Images Captured by Blind and Low Vision Userscited by 2
  2. 2025Are Large Vision-Language Models Ready to Guide Blind and Low-Vision Individuals?cited by 1
  3. 2025How Blind and Low-Vision Individuals Prefer Large Vision-Language Model-Generated Scene Descriptionscited by 0
  4. 2025Hierarchical Instance Tracking to Balance Privacy Preservation with Accessible Informationcited by 0
  5. 2026When Recovery Matters: The Blind Spot of Surrogate Privacy in MLLM Editingcited by 0