Visual Style in Two Network Era Sitcoms

Abstract

Extensive scholarship in media studies has established how formal elements of moving images—such as camera angles, sound, and framing—reflect, establish, and challenge cultural norms. Prior computational analyses attempting to analyze these elements have primarily relied on summarizing relatively low-level-features. Beginning with the early work of Barry Salt, one particularly prominent metric is the distribution of median shot lengths. Works on shot length include Yuri Tsivian’s Cinemetrics project, Arclight, and Jeremy Butler’s ShotLogger. Other computational analyses examine the aggregation of language and average shot color, image compositions, and analysis of film scripts. These projects have demonstrated the feasibility of distributing extracted metadata from copyrighted materials and the power of computational techniques in accessing useful information over a large collection of moving images. However, there is much to be learned from other extractable metadata beyond shot detection and much to be studied in audiovisual media that can only be discovered through computer vision.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 21 citations exist upstream.