Discontinuity Is Not a Cut: Automatic Shot Boundary Detection and The Measurement of Film Editing

References

[1] Bachl, M., & Scharkow, M. (2017). Correcting measurement error in content analysis. Communication Methods and Measures. https://doi.org/10.1080/19312458.2017.1305103.

[2] Bakels, J.-H., Grotkopp, M., Scherer, T., & Stratil, J. (2020). Matching computational analysis and human experience: performative arts and the digital humanities. Digital Humanities Quarterly, 14(4). https://doi.org/10.17169/refubium-30938.

[3] Chávez Heras, D. (2024). Creanalytics: automating the supercut as a form of critical technical practice. Convergence: The International Journal of Research into New Media Technologies, 30(1), 264–284. https://doi.org/10.1177/13548565231174592.

[4] Chen, B. (2025). Cinemetrics in the digital humanities era: theoretical evolution, methodological innovation, and research frontiers. The Development of Humanities and Social Sciences. https://doi.org/10.71204/dxaqff27.

[5] Cutting, J.E., Brunick, K.L., & DeLong, J.E. (2011). How act structure sculpts shot lengths and shot transitions in Hollywood film. Projections, 5(1), 1–16. https://doi.org/10.3167/proj.2011.050102.

[6] Cutting, J.E., Brunick, K.L., DeLong, J.E., Iricinschi, C., & Candan, A. (2011). Quicker, faster, darker: changes in Hollywood film over 75 years. i-Perception, 2(6), 569–576. https://doi.org/10.1068/i0441aap.

[7] Cutting, J.E., Brunick, K.L., & DeLong, J.E. (2011). The changing poetics of the dissolve in Hollywood film. Empirical Studies of the Arts, 29(2), 149–169. https://doi.org/10.2190/em.29.2.b.

[8] Cutting, J.E., Brunick, K.L., & DeLong, J.E. (2012). On shot lengths and film acts: a revised view. Projections, 6(1). https://doi.org/10.3167/proj.2012.060106.

[9] Cutting, J.E. (2014). Event segmentation and seven types of narrative discontinuity in popular movies. Acta Psychologica, 149, 69–77. https://doi.org/10.1016/j.actpsy.2014.03.003.

[10] Hanjalic, A. (2002). Shot-boundary detection: unraveled and resolved? IEEE Transactions on Circuits and Systems for Video Technology. https://doi.org/10.1109/76.988656.

[11] Kar, T., & Kanungo, P. (2024). Video shot-boundary detection: issues, challenges and solutions. Artificial Intelligence Review. https://doi.org/10.1007/s10462-024-10742-1.

[12] Li, C., Lu, J., Pei, Y., Shen, Y., Hu, Y., Fan, Y., Tian, Y., Linghu, X., Wang, K., Shi, Z., & Sun, J. (2024). PyCinemetrics: computational film studies tool based on deep learning and PySide2. SoftwareX, 26, 101686. https://doi.org/10.1016/j.softx.2024.101686.

[13] Li, C., Wang, K., Pei, Y., Fan, Y., & Zhang, F. (2026). FilmShots: a fast film shot boundary detection based on dilated Conv3D and attention. IEEE Access, 14, 49497–49510. https://doi.org/10.1109/access.2026.3677190.

[14] Lienhart, R. (1998). Comparison of automatic shot boundary detection algorithms. https://doi.org/10.1117/12.333848.

[15] Pustu-Iren, K., Sittel, J., Mauer, R., Bulgakowa, O., & Ewerth, R. (2020). Automated visual content analysis for film studies: current status and challenges. Digital Humanities Quarterly, 14(4). https://doi.org/10.63744/8rc7hctnsxrx.

[16] Qiao, M., & Huang, K. (2025). Correcting measurement error in regression models with variables constructed from aggregated output of data mining models. MIS Quarterly, 49(1), 29–60. https://doi.org/10.25300/misq/2024/18026.

[17] Redfern, N. (2014). Comparing the shot length distributions of motion pictures using dominance statistics. Empirical Studies of the Arts, 32(2). https://doi.org/10.2190/em.32.2.g.

[18] Redfern, N. (2015). The log-normal distribution is not an appropriate parametric model for shot length distributions of Hollywood films. Digital Scholarship in the Humanities. https://doi.org/10.1093/llc/fqs066.

[19] Redfern, N. (2022). Distributional thinking about film style. Exchanges: The Interdisciplinary Research Journal, 10(1). https://doi.org/10.31273/eirj.v10i1.853.

[20] Redfern, N. (2022). Analysing motion picture cutting rates. Wide Screen, 9(1). ISSN 1757-3920. http://widescreenjournal.org.

[21] Salt, B. (1974). Statistical style analysis of motion pictures. Film Quarterly, 28(1), 13–22. https://doi.org/10.2307/1211438.

[22] Salt, B. (2004). The shape of 1999. New Review of Film and Television Studies. https://doi.org/10.1080/17400300410001679106.

[23] Salt, B. (2021). The end of the Great Speed-Up - and after. Digital Scholarship in the Humanities. https://doi.org/10.1093/llc/fqab049.

[24] Smeaton, A.F., Over, P., & Doherty, A.R. (2010). Video shot boundary detection: seven years of TRECVid activity. Computer Vision and Image Understanding. https://doi.org/10.1016/j.cviu.2009.03.011.

[25] Song, H., Tolochko, P., Eberl, J.-M., Eisele, O., Greussing, E., Heidenreich, T., Lind, F., Galyga, S., & Boomgaarden, H.G. (2020). In validations we trust? The impact of imperfect human annotations as a gold standard on the quality of validation of automated content analysis. Political Communication, 37(4), 550–572. https://doi.org/10.1080/10584609.2020.1723752.

[26] Tang, S., Feng, L., Kuang, Z., Chen, Y., & Zhang, W. (2018). Fast video shot transition localization with deep structured models. arXiv:1808.04234.

[27] TeBlunthuis, N., Hase, V., & Chan, C.-H. (2023). Misclassification in automated content analysis causes bias in regression. Can we fix it? Yes we can! Communication Methods and Measures, 18(3). https://doi.org/10.1080/19312458.2023.2293713 Preprint: arXiv:2307.06483.

[28] Wang, S., McCormick, T.H., & Leek, J.T. (2020). Methods for correcting inference based on outcomes predicted by machine learning. PNAS. https://doi.org/10.1073/pnas.2001238117.

[29] Wu, X. (2026). Kurosawa shot-level dataset: shot boundaries, color, and face-derived shot-scale features for 30 films. Journal of Open Humanities Data, 12. https://doi.org/10.5334/johd.507.

[30] Zhu, W., Huang, Y., Xie, X., Liu, W., Deng, J., Zhang, D., Wang, Z., & Liu, J. (2023). AutoShot: a short video dataset and state-of-the-art shot boundary detection. 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2238–2247. https://doi.org/10.1109/cvprw59228.2023.00218.

@article{1722842,
      author = {Md Riaz Uddin, Sameer Ahmed},
      title = {Discontinuity Is Not a Cut: Automatic Shot Boundary Detection and The Measurement of Film Editing},
      journal = {Iconic Research And Engineering Journals},
      year = {2026},
      volume = {9},
      number = {12},
      pages = {3972-3986},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1722842.pdf},
      abstract = {Film studies increasingly computes average shot length from automatically detected shot boundaries. Detectors do not identify shots. They identify discontinuities in the visual signal, which coincide with shots only approximately. Because that divergence is structured by the footage rather than random, it biases shot-length statistics rather than adding noise. Using the ClipShots ground truth (5,138 shots across 92 videos) with detector performance figures published for that corpus, we simulate how detection error propagates into the statistics the field reports. In these simulations average shot length is systematically deflated, by 15.4% and 10.6% for the two stronger detector profiles, because false boundaries outnumber missed ones. Video is made to appear as though it cuts faster than it does. The bias does not track detector quality, and it is confounded with the object of study. Since gradual transitions are missed far more often than cuts, a film's bias varies almost perfectly with the proportion of its transitions that are gradual, itself a stylistic property. Films that cut hard and films that dissolve are distorted in opposite directions by the feature distinguishing them. Differences below about 5% prove unrecoverable under every profile tested. Researchers comparing moving images on shot length cannot assume the size of their measurement error, nor remove it by choosing a detector with a better F-score.},
      keywords = {average shot length, cinemetrics, film editing, measurement error, shot boundary detection},
      month = {June},
      doi = {https://doi.org/10.64388/IREV9I12-1722842}
  }