Citation :

Snehal Athghara, Apoorva Atre, Shweta Bagade, Gayatri Muttepawar, Shilpa Deshpande, Rashmi Apte, Mangesh Bedekar, "A Deep Learning based Framework for Actor Recognition and Screen Presence Analysis in Bollywood Films," International Journal of Electrical and Electronics Engineering, vol. 13, no. 4, pp. 1-19, 2026. Crossref, https://doi.org/10.14445/23488379/IJEEE-V13I4P101

Abstract

Quantitative and qualitative analysis of actor screen presence is a major aspect of film studies, media analysis, and performance evaluation. Existing approaches largely rely on manual annotation and have insufficient robustness under real-world cinematic conditions. This research proposes Actor Recognition and Screen Presence Analysis (AR-SPA), a deep learning-based framework designed to automate actor identification and screen-time analysis across full-length movies. AR-SPA operates by uniformly sampling frames and implementing a face-detector to localize actors using the You Only Look Once (YOLO) model. A discriminative recognition model is used to identify actors across the frames. This is achieved by experimentation on three different recognition models, namely, Convolutional Neural Network (CNN), CNN-Transformer, and Residual Network-Convolutional Block Attention Model (ResNet-CBAM). Experimental results highlight the tendency of the ResNet-CBAM model to consistently outperform the other conventional baseline models by achieving high Accuracy and F1-score across multiple testing conditions. Hence, this model is integrated into the AR-SPA framework for robust actor recognition. By aggregating these classified actor detections over the film’s duration, the framework generates metrics such as total frame counts, proportional screen time, and actor dominance. This enables direct statistical comparison of actor prominence across sequels and long-running franchises. The framework is validated using a curated dataset of fifty films, from twenty movie series spanning across two decades. Through rigorous testing and validation, AR-SPA demonstrates high Accuracy and reliability in the face of challenges such as aging, dramatic lighting, and occlusions. The results of this research suggest that AR-SPA offers a scalable, reproducible tool for film scholars and industry analysts to track character evolution and performance trends over time.

Keywords

Convolutional Block Attention Module, Face Detection, Long-Form Video Analysis, Movie Series Analysis, Residual Network, Temporal Screen-Time Estimation.

References

1. Chunfang Li et al., “PyCinemetrics: Computational Film Studies Tool based on Deep Learning and PySide2,” SoftwareX, vol. 26, pp. 1-8, 2024.
   [CrossRef] [Google Scholar] [Publisher Link]
2. James E. Cutting, Jordan E. DeLong, and Christine E. Nothelfer, “Attention and the Evolution of Hollywood Film,” Psychological Science, vol. 21, no. 3, pp. 432-439, 2010.
   [CrossRef] [Google Scholar] [Publisher Link]
3. Florian Schroff, Dmitry Kalenichenko, and James Philbin, “FaceNet: A Unified Embedding for Face Recognition and Clustering,” 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA, pp. 815-823, 2015.
   [CrossRef] [Google Scholar] [Publisher Link]
4. Yaniv Taigman et al., “DeepFace: Closing the Gap to Human-Level Performance in Face Verification,” 2014 IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA, pp. 1701-1708, 2014.
   [CrossRef] [Google Scholar] [Publisher Link]
5. SouYoung Jin et al., “End-to-End Face Detection and Cast Grouping in Movies using Erdös-Rényi Clustering,” 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy, pp. 5286-5295, 2017.
   [CrossRef] [Google Scholar] [Publisher Link]
6. Arsha Nagrani, and Andrew Zisserman, “From Benedict Cumberbatch to Sherlock Holmes: Character Identification in TV Series without a Script,” arXiv preprint, pp. 1-13, 2018.
   [CrossRef] [Google Scholar] [Publisher Link]
7. Ijaz Ul Haq et al., “DeepStar: Detecting Starring Characters in Movies,” IEEE Access, vol. 7, pp. 9265-9272, 2019.
   [CrossRef] [Google Scholar] [Publisher Link]
8. Abhinav Aggarwal et al., “Robust Actor Recognition in Entertainment Multimedia at Scale,” Proceedings of the 30^th ACM International Conference on Multimedia, New York, NY, USA, 2079-2087, 2022.
   [CrossRef] [Google Scholar] [Publisher Link]
9. Tomas Kerepecky et al., Automated Actor Recognition in Video Content, Data Science in Applications, Springer, Cham, pp. 3-22, 2025.
   [CrossRef] [Google Scholar] [Publisher Link]
10. Lin He, Lile He, and Lijun Peng, “CFormerFaceNet: Efficient Lightweight Network Merging a CNN and Transformer for Face Recognition,” Applied Sciences, vol. 13, no. 11, pp. 1-14, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
11. Huafeng Wang, Yunhong Wang, and Yuan Cao, “Video-based Face Recognition: A Survey,” World Academy of Science, Engineering and Technology, pp. 293-302, 2009.
    [Google Scholar]
12. Stefanos Zafeiriou, Cha Zhang, and Zhengyou Zhang, “A Survey on Face Detection in the Wild: Past, Present and Future,” Computer Vision and Image Understanding, vol. 138, pp. 1-24, 2015.
    [CrossRef] [Google Scholar] [Publisher Link]
13. Prakhar Kulshreshtha, and Tanaya Guha, “Dynamic Character Graph Via Online Face Clustering for Movie Analysis,” Multimedia Tools and Applications, vol. 79, no. 43-44, pp. 33103-33118, 2020.
    [CrossRef] [Google Scholar] [Publisher Link]
14. Jitao Sang, and Changsheng Xu, “Robust Face-Name Graph Matching for Movie Character Identification,” IEEE Transactions on Multimedia, vol. 14, no. 3, pp. 586-596, 2012.
    [CrossRef] [Google Scholar] [Publisher Link]
15. Hayeon Kim et al., “Character Detection in Animated Movies using Multi-Style Adaptation and Visual Attention,” IEEE Transactions on Multimedia, vol. 23, pp. 1990-2004, 2021.
    [CrossRef] [Google Scholar] [Publisher Link]
16. Salwa Shakir Baawi, Farah Jawad Al-Ghanim, and Nisreen Ryadh Hamza, “Categorization of Celebrity Photos based on Deep Machine Learning for Feature Extraction and Classification,” Wasit Journal of Computer and Mathematics Science, vol. 4, no. 1, pp. 1-16, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
17. Alexander Gabourie, and Connor McClellan, “Actor Identification with Deep Learning,” Stanford University, CS230 Deep Learning, 2018.
    [Google Scholar]
18. Xiawei Lu, “Digital Media Video Image Data Processing based on Computer Vision,” International Journal of Computer Applications in Technology, vol. 78, no. 2, pp. 101-111, 2026.
    [CrossRef] [Google Scholar] [Publisher Link]
19. Zilinghan Li et al., “ViCTer: A Semi-Supervised Video Character Tracker,” Machine Learning with Applications, vol. 12, pp. 1-14, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
20. Joshua Baldwin, and Ralf Schmälzle, “A Character Recognition Tool for Automatic Detection of Social Characters in Visual Media Content,” Computational Communication Research, vol. 4, no. 1, pp. 351-371, 2022.
    [CrossRef] [Google Scholar] [Publisher Link]
21. Vignesh Ramanathan et al., “Detecting Events and Key Actors in Multi-Person Videos,” 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3043-3053, 2015.
    [Google Scholar] [Publisher Link]
22. Minchul Kim, Anil Jain, and Xiaoming Liu, “50 Years of Automated Face Recognition,” IEEE Transactions on Pattern Analysis and Machine Intelligence, pp. 1-20, 2026.
    [CrossRef] [Google Scholar] [Publisher Link]
23. S. Foucher, and L. Gagnon, “Automatic Detection and Clustering of Actor Faces based on Spectral Clustering Techniques,” Fourth Canadian Conference on Computer and Robot Vision (CRV '07), Montreal, QC, Canada, pp. 113-122, 2007.
    [CrossRef] [Google Scholar] [Publisher Link]
24. Christina Chrysouli, Nicholas Vretos, and Ioannis Pitas, “Face Clustering in Videos based on Spectral Clustering Techniques,” The First Asian Conference on Pattern Recognition, Beijing, China, pp. 130-134, 2011.
    [CrossRef] [Google Scholar] [Publisher Link]
25. Remigiusz Baran, Filip Rudzinski, and Andrzej Zeja, “Face Recognition for Movie Character and Actor Discrimination based on Similarity Scores,” 2016 International Conference on Computational Science and Computational Intelligence (CSCI), Las Vegas, NV, USA, pp. 1333-1338, 2016.
    [CrossRef] [Google Scholar] [Publisher Link]
26. Vineet Gandhi, and Remi Ronfard, “Detecting and Naming Actors in Movies using Generative Appearance Models,” 2013 IEEE Conference on Computer Vision and Pattern Recognition, Portland, OR, USA, pp. 3706-3713, 2013.
    [CrossRef] [Google Scholar] [Publisher Link]
27. Guangyu Gao et al., “Cast2Face: Assigning Character Names onto Faces in Movie with Actor-Character Correspondence,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 26, no. 12, pp. 2299-2312, 2016.
    [CrossRef] [Google Scholar] [Publisher Link]
28. Krishna Somandepalli, Rajat Hebbar, and Shrikanth Narayanan, “Robust Character Labeling in Movie Videos: Data Resources and Self-Supervised Feature Adaptation,” IEEE Transactions on Multimedia, vol. 24, pp. 3355-3368, 2022.
    [CrossRef] [Google Scholar] [Publisher Link]
29. Qing Wang et al., “Object Tracking with Joint Optimization of Representation and Classification,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 25, no. 4, pp. 638-650, 2015.
    [CrossRef] [Google Scholar] [Publisher Link]
30. Vijay Kumar, Anoop M. Namboodiri, and C.V. Jawahar, “Face Recognition in Videos by Label Propagation,” 2014 22^nd International Conference on Pattern Recognition, Stockholm, Sweden, pp. 303-308, 2014.
    [CrossRef] [Google Scholar] [Publisher Link]
31. P. Bojanowski et al., “Finding Actors and Actions in Movies,” 2013 IEEE International Conference on Computer Vision, Sydney, NSW, Australia, pp. 2280-2287, 2013.
    [CrossRef] [Google Scholar] [Publisher Link]
32. Shoufa Chen et al., “Watch Only Once: An End-to-End Video Action Detection Framework,” 2021 IEEE/CVF International Conference on Computer Vision (ICCV), Montreal, QC, Canada, pp. 8158-8167, 2021.
    [CrossRef] [Google Scholar] [Publisher Link]
33. Olivier Duchenne et al., “Automatic Annotation of Human Actions in Video,” 2009 IEEE 12^th International Conference on Computer Vision, Kyoto, Japan, pp. 1491-1498, 2009.
    [CrossRef] [Google Scholar] [Publisher Link]
34. Jae Young Choi et al., “An Automatic Face Indexing Framework for Actor-based Video Services in an IPTV Environment,” 2010 Digest of Technical Papers International Conference on Consumer Electronics (ICCE), Las Vegas, NV, USA, pp. 81-82, 2010.
    [CrossRef] [Google Scholar] [Publisher Link]
35. Lai-Tee Cheok et al., “Automatic Actor Recognition for Video Services on Mobile Devices,” 2012 IEEE International Symposium on Multimedia, Irvine, CA, USA, pp. 384-385, 2012.
    [CrossRef] [Google Scholar] [Publisher Link]
36. Himanshu Nainwal, and Koshti Vanshika Shaileshbhai, “An Approach for Face Detection and Face Recognition using OpenCV and Face Recognition Libraries in Python using GPU,” 2024 8^th International Conference on Computational System and Information Technology for Sustainable Solutions (CSITSS), Bengaluru, India, pp. 1-6, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
37. Nithya Manickam, and Sharat Chandran, “Fast Lead Star Detection in Entertainment Videos,” 2009 Workshop on Applications of Computer Vision (WACV), Snowbird, UT, USA, pp. 1-6, 2009.
    [CrossRef] [Google Scholar] [Publisher Link]
38. Sher Muhammad Doudpota, and Sumanta Guha, “Automatic Actors Detection in Musicals,” Seventh International Conference on Digital Information Management (ICDIM 2012), Macau, Macao, pp. 226-231, 2012.
    [CrossRef] [Google Scholar] [Publisher Link]
39. Tomas Kerepecky et al., “STAR: Screen Time and Actor Recognition in Video Content,” Pattern Recognition: 46^th DAGM German Conference, DAGM GCPR 2024, Munich, Germany, pp. 270-284, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
40. Christina Lin, Stephany Liu, and Samuel Wong, “Counting Actor Screen Time in Movies,” Stanford University, CS230, Deep Learning, 2019.
    [Google Scholar]
41. Shankar Setty et al., “Indian Movie Face Database: A Benchmark for Face Recognition Under Wide Variations,” 2013 Fourth National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics (NCVPRIPG), Jodhpur, India, pp. 1-5, 2013.
    [CrossRef] [Google Scholar] [Publisher Link]
42. YouTube, 2026. [Online]. Available: https://www.youtube.com
43. Internet Archive: Digital Library of Free & Borrowable Texts, Movies, Music & Wayback Machine, Archive.Org, 2026. [Online]. Available: https://archive.org
44. Joseph Redmon et al., “You Only Look Once: Unified, Real-Time Object Detection,” 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, pp. 779-788, 2016.
    [CrossRef] [Google Scholar] [Publisher Link]
45. Prashant Udawant et al., “A Systematic Approach to Face Recognition using Convolutional Neural Network,” 2024 International Conference on Advancements in Smart, Secure and Intelligent Computing (ASSIC), Bhubaneswar, India, pp. 1-6, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
46. Sanghyun Woo et al., “CBAM: Convolutional Block Attention Module,” Computer Vision-ECCV 2018: 15^th European Conference, Munich, Germany, pp. 3-19, 2018.
    [CrossRef] [Google Scholar] [Publisher Link]
47. Kaiming He et al., “Deep Residual Learning for Image Recognition,” 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, pp. 770-778, 2016.
    [CrossRef] [Google Scholar] [Publisher Link]