Moviescc New! May 2026

Existing video classification models (e.g., VideoBERT, TimeSformer) often treat movies as generic video streams, ignoring unique cinematic structures such as shot transitions, pacing, and narrative tropes. fills this gap by focusing specifically on scene-level classification —the atomic narrative unit typically comprising multiple shots unified by time and location.

: 87.4% Macro F1-score : 0.85

[5] Devlin, J., et al. (2019). BERT: Pre-training of deep bidirectional transformers for language understanding. NAACL . moviescc

[2] Gemmeke, J. F., et al. (2017). AudioSet: An ontology and human-labeled dataset for audio events. ICASSP . Existing video classification models (e

[4] Zhou, B., et al. (2018). Movie genre classification via scene categorization. ACM MM . Existing video classification models (e.g.