Papers
Topics
Authors
Recent
Search
2000 character limit reached

Situated Cameras, Situated Knowledges: Towards an Egocentric Epistemology for Computer Vision

Published 30 Jun 2023 in cs.CV | (2307.00064v1)

Abstract: In her influential 1988 paper, Situated Knowledges, Donna Haraway uses vision and perspective as a metaphor to discuss scientific knowledge. Today, egocentric computer vision discusses many of the same issues, except in a literal vision context. In this short position paper, we collapse that metaphor, and explore the interactions between feminist epistemology and egocentric CV as "Egocentric Epistemology." Using this framework, we argue for the use of qualitative, human-centric methods as a complement to performance benchmarks, to center both the literal and metaphorical perspective of human crowd workers in CV.

Authors (2)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (24)
  1. S. Bambach. A survey on recent advances of computer vision algorithms for egocentric video. arXiv, 2015.
  2. Lending a hand: Detecting hands and recognizing activities in complex egocentric interactions. In ICCV, pages 1949–1957, 2015.
  3. S. Bardzell and J. Bardzell. Towards a feminist hci methodology: social science, feminism, and hci. In CHI, pages 675–684, 2011.
  4. K.-K. Bhavnani. Tracing the contours: Feminist research and feminist objectivity. In Women’s Studies International Forum, volume 16, pages 95–104. Elsevier, 1993.
  5. J. Buolamwini and T. Gebru. Gender shades: Intersectional accuracy disparities in commercial gender classification. In FAccT, pages 77–91. PMLR, 2018.
  6. K. Crawford. The atlas of AI: Power, politics, and the planetary costs of artificial intelligence. Yale University Press, 2021.
  7. Scaling egocentric vision: The epic-kitchens dataset. In ECCV, pages 720–736, 2018.
  8. On the genealogy of machine learning datasets: A critical history of imagenet. Big Data & Society, 8(2), 2021.
  9. C. D’ignazio and L. F. Klein. Data feminism. MIT press, 2020.
  10. Identifying first-person camera wearers in third-person videos. In CVPR, pages 5125–5133, 2017.
  11. Understanding egocentric activities. In ICCV, pages 407–414. IEEE, 2011.
  12. S. Goree. What does it take to cross the aesthetic gap? the development of image aesthetic quality assessment in computer vision. In ICCC, pages 11–15, 2021.
  13. Attention is all they need: Exploring the media archaeology of the computer vision research paper. arXiv, 2022.
  14. D. Haraway. Situated knowledges: The science question in feminism and the privilege of partial perspective. Feminist studies, 14(3):575–599, 1988.
  15. Most people are not weird. Nature, 466(7302):29–29, 2010.
  16. I. Hermann. Artificial intelligence in fiction: between narratives and metaphors. AI & society, 38(1):319–329, 2023.
  17. A. Hertzmann. The choices hidden in photography. Journal of Vision, 22(11):10–10, 2022.
  18. Dog’s life: wearable activity recognition for dogs. In UBICOMP, pages 415–418, 2013.
  19. Jrdb: A dataset and benchmark of egocentric robot visual perception of humans in built environments. PAMI, 2021.
  20. A survey on bias and fairness in machine learning. CSUR, 54(6):1–35, 2021.
  21. Ava: A large-scale database for aesthetic visual analysis. In CVPR, pages 2408–2415. IEEE, 2012.
  22. Data and its (dis) contents: A survey of dataset development and use in machine learning research. Patterns, 2(11):100336, 2021.
  23. L. Suchman. Imaginaries of omniscience: Automating intelligence in the us department of defense. Social Studies of Science, 2022.
  24. Egocentric vision-based future vehicle localization for intelligent driving assistance systems. In ICRA, pages 9711–9717. IEEE, 2019.

Summary

No one has generated a summary of this paper yet.

Paper to Video (Beta)

No one has generated a video about this paper yet.

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Continue Learning

We haven't generated follow-up questions for this paper yet.

Collections

Sign up for free to add this paper to one or more collections.