MovieCLIP: Visual Scene Recognition in Movies

Digbalay Bose, Rajat Hebbar, Krishna Somandepalli, Haoyang Zhang, Yin Cui, Kree Cole-McLaughlin, Huisheng Wang, Shrikanth Narayanan; Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2023, pp. 2083-2092

Abstract


Longform media such as movies have complex narrative structures, with events spanning a rich variety of ambient visual scenes. Domain-specific challenges associated with visual scenes in movies include transitions, person coverage, and a wide array of real-life and fictional scenarios. Existing visual scene datasets in movies have limited taxonomies and don't consider the visual scene transition within movie clips. In this work, we address the problem of visual scene recognition in movies by first automatically curating a new and extensive movie-centric taxonomy of 179 scene labels derived from movie scripts and auxiliary web-based video datasets. Instead of manual annotations which can be expensive, we use CLIP to weakly label 1.12 million shots from 32K movie clips based on our proposed taxonomy. We provide baseline visual models trained on the weakly labeled dataset called MovieCLIP and evaluate them on an independent dataset verified by human raters. We show that leveraging features from models pretrained on MovieCLIP benefits downstream tasks such as multi-label scene and genre classification of web videos and movie trailers.

Related Material


[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Bose_2023_WACV, author = {Bose, Digbalay and Hebbar, Rajat and Somandepalli, Krishna and Zhang, Haoyang and Cui, Yin and Cole-McLaughlin, Kree and Wang, Huisheng and Narayanan, Shrikanth}, title = {MovieCLIP: Visual Scene Recognition in Movies}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2023}, pages = {2083-2092} }