Editing Designing Internet Research (Spring 2022) (section)

=== Monday April 25: Visual Analysis  ===

'''Required Readings:'''

* Faulkner, Simon, Farida Vis, and Francesco D’Orazio. 2018. “Analysing Social Media Images.” In The SAGE Handbook of Social Media, edited by Jean Burgess, Alice Marwick, and Thomas Poell, 160–78. London, UK: SAGE. https://doi.org/10.4135/9781473984066. {{avail-canvas|1=https://canvas.uw.edu/files/91222224/download?download_frd=1}}
* Casas, Andreu, and Nora Webb Williams. 2019. “Images That Matter: Online Protests and the Mobilizing Role of Pictures.” Political Research Quarterly 72 (2): 360–75. https://doi.org/10.1177/1065912918786805. {{avail-uw|https://doi.org/10.1177/1065912918786805}}
* Casas, Andreu, and Nora Webb Williams. 2017. “Computer Vision for Political Science Research: A Study of Online Protest Images.” In. College Park, PA: Pennsylvania State University. http://andreucasas.com/casas_webb_williams_NewFaces2017_images_as_data.pdf. {{avail-free|http://andreucasas.com/casas_webb_williams_NewFaces2017_images_as_data.pdf}}
* Hochman, Nadav, and Raz Schwartz. 2012. “Visualizing Instagram: Tracing Cultural Visual Rhythms.” In Sixth International AAAI Conference on Weblogs and Social Media. https://pdfs.semanticscholar.org/780d/c7ff86eb36731d5faa043ac635cbae6bbe45.pdf. {{avail-free|https://pdfs.semanticscholar.org/780d/c7ff86eb36731d5faa043ac635cbae6bbe45.pdf}}

'''Optional Readings:'''

* Torralba, Antonio. 2009. “Understanding Visual Scenes.” Tutorial presented at the NIPS, Vancouver, BC, Canada. http://videolectures.net/nips09_torralba_uvs/. {{avail-uw|http://videolectures.net/nips09_torralba_uvs/}}
: Note: This is a two-part (each part is one hour) lecture and tutorial by an expert in computer vision. I strongly recommend watching Part I. I think this gives you a good sense of the nature of the kinds of challenges that were (and still are) facing the field of computer vision and anybody trying to have their computer look at images.
* Hochman, Nadav, and Lev Manovich. 2013. “Zooming into an Instagram City: Reading the Local through Social Media.” First Monday 18 (7). https://firstmonday.org/article/view/4711/3698. {{avail-free|https://firstmonday.org/article/view/4711/3698}}

These five papers are all technical approaches to doing image classification using datasets from Internet-based datasets of images like Flickr, Google Image Search, Google Street View, or Instagram. Each of these describes interesting and challenges technical issues. If you're interested, it would be a great idea to read these to get a sense for the state of the art and what is and isn't possible:

* Jaffe, Alexandar, Mor Naaman, Tamir Tassa, and Marc Davis. 2006. “Generating Summaries and Visualization for Large Collections of Geo-Referenced Photographs.” In Proceedings of the 8th ACM International Workshop on Multimedia Information Retrieval, 89–98. MIR ’06. New York, NY, USA: ACM. https://doi.org/10.1145/1178677.1178692. {{avail-uw|https://doi.org/10.1145/1178677.1178692}}
* Simon, Ian, Noah Snavely, and Steven M. Seitz. 2007. “Scene Summarization for Online Image Collections.” In Computer Vision, IEEE International Conference On, 0:1–8. Los Alamitos, CA, USA: IEEE Computer Society. https://doi.org/10.1109/ICCV.2007.4408863. {{avail-free|https://doi.org/10.1109/ICCV.2007.4408863}}
* Crandall, David J., Lars Backstrom, Daniel Huttenlocher, and Jon Kleinberg. 2009. “Mapping the World’s Photos.” In Proceedings of the 18th International Conference on World Wide Web, 761–770. WWW ’09. New York, NY, USA: ACM. https://doi.org/10.1145/1526709.1526812. {{avail-uw|https://doi.org/10.1145/1526709.1526812}}
* San Pedro, Jose, and Stefan Siersdorfer. 2009. “Ranking and Classifying Attractiveness of Photos in Folksonomies.” In Proceedings of the 18th International Conference on World Wide Web, 771–780. WWW ’09. New York, NY, USA: ACM. https://doi.org/10.1145/1526709.1526813. {{avail-uw|https://doi.org/10.1145/1526709.1526813}}
* Doersch, Carl, Saurabh Singh, Abhinav Gupta, Josef Sivic, and Alexei A. Efros. 2012. “What Makes Paris Look like Paris?” ACM Trans. Graph. 31 (4): 101:1–101:9. https://doi.org/10.1145/2185520.2185597. {{avail-uw|https://doi.org/10.1145/2185520.2185597}}