Attention is All They Need: Exploring the Media Archaeology of the Computer Vision Research Paper
Not on the map. Why?
Abstract (arXiv)
Research papers, in addition to textual documents, are a designed interface through which researchers communicate. Recently, rapid growth has transformed that interface in many fields of computing. In this work, we examine the effects of this growth from a media archaeology perspective, through the changes to figures and tables in research papers. Specifically, we study these changes in computer vision over the past decade, as the deep learning revolution has driven unprecedented growth in the discipline. We ground our investigation through interviews with veteran researchers spanning computer vision, graphics, and visualization. Our analysis focuses on the research attention economy: how research paper elements contribute towards advertising, measuring, and disseminating an increasingly commodified "contribution." Through this work, we seek to motivate future discussion surrounding the design of both the research paper itself as well as the larger sociotechnical research publishing system, including tools for finding, reading, and writing research papers.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 30 of its 132 references that are in the map. First posted on arXiv 22 Sep 2022.
Builds on
30 of 132 references.
References · 30
- 2014Microsoft COCO: Common Objects in Contextcited by 17,498
- 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
- 2019A Survey on Bias and Fairness in Machine Learningcited by 1,911
- 2016YOLO9000: Better, Faster, Strongercited by 1,429
- 2019VIBE: Video Inference for Human Body Pose and Shape Estimationcited by 615
- 2021CoAtNet: Marrying Convolution and Attention for All Data Sizescited by 566
- 2015MovieQA: Understanding Stories in Movies through Question-Answeringcited by 304
- 2020Data and its (dis)contents: A survey of dataset development and use in machine learning researchcited by 259
- 2021RobustNet: Improving Domain Generalization in Urban-Scene Segmentation via Instance Selective Whiteningcited by 213
- 2016DeMoN: Depth and Motion Network for Learning Monocular Stereocited by 200
- 2020GLEAN: Generative Latent Bank for Large-Factor Image Super-Resolutioncited by 158
- 2021ForgeryNet: A Versatile Benchmark for Comprehensive Forgery Analysiscited by 124
18 more
- 2021VisualVoice: Audio-Visual Speech Separation with Cross-Modal Consistencycited by 114
- 2020HOPE-Net: A Graph-based Model for Hand-Object Pose Estimationcited by 112
- 2021Distilling Object Detectors via Decoupled Featurescited by 105
- 2017Detailed, accurate, human shape estimation from clothed 3D scan sequencescited by 89
- 2021Do Datasets Have Politics? Disciplinary Values in Computer Vision Dataset Developmentcited by 85
- 2021Locally Aware Piecewise Transformation Fields for 3D Human Mesh Registrationcited by 41
- 2020Augmenting Scientific Papers with Just-in-Time, Position-Sensitive Definitions of Terms and Symbolscited by 36
- 2021AI4VIS: Survey on Artificial Intelligence Approaches for Data Visualizationcited by 32
- 2021How AI Developers Overcome Communication Challenges in a Multidisciplinary Team: A Case Studycited by 29
- 2021FBI-Denoiser: Fast Blind Image Denoiser for Poisson-Gaussian Noisecited by 22
- 2021Learning to Solve Hard Minimal Problemscited by 18
- 2021A Deep Emulator for Secondary Motion of 3D Characterscited by 16
- 2020VIS30K: A Collection of Figures and Tables from IEEE Visualization Conference Publicationscited by 13
- 2020Exploring intermediate representation for monocular vehicle pose estimationcited by 12
- 2018Deep Paper Gestaltcited by 6
- 2021Hole-robust Wireframe Detectioncited by 5
- 2022Affective Learning Objectives for Communicative Visualizationscited by 4
- 2015Linear Shape Deformation Models with Local Support Using Graph-based Structured Matrix Factorisationcited by 2
Built on by
Citing papers per year: 2023: 1.
1 paper.