CVJun 30, 2023

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

arXiv:2307.00064v11 citationsh-index: 54
Originality Synthesis-oriented
AI Analysis

This is a conceptual position paper that addresses methodological gaps in computer vision for researchers and practitioners, but it is incremental as it builds on existing feminist and egocentric ideas without introducing new empirical results.

The paper tackles the problem of integrating feminist epistemology with egocentric computer vision to propose an 'Egocentric Epistemology' framework, arguing for qualitative, human-centric methods to complement performance benchmarks and center human perspectives.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes