PrAViC: Probabilistic Adaptation Framework for Real-Time Video Classification

Magdalena Trędowicz, Marcin Mazur, Szymon Janusz, Arkadiusz Lewicki, Jacek Tabor, Łukasz Struski

Keywords: Online classification, early decision, video processing

Abstract: Video processing is generally divided into two main categories: processing of the entire video, which typically yields optimal classification outcomes, and real-time processing, where the objective is to make a decision as promptly as possible. The latter is often driven by the need to identify rapidly potential critical or dangerous situations. These could include machine failure, traffic accidents, heart problems, or dangerous behavior. Although the models dedicated to the processing of entire videos are typically well-defined and clearly presented in the literature, this is not the case for online processing, where a plethora of hand-devised methods exist. To address this, we present PrAViC, a novel, unified, and theoretically-based adaptation framework for dealing with the online classification problem for video data. The initial phase of our study is to establish a robust mathematical foundation for the theory of classification of sequential data, with the potential to make a decision at an early stage. This allows us to construct a natural function that encourages the model to return an outcome much faster. The subsequent phase is to present a straightforward and readily implementable method for adapting offline models to the online setting with recurrent operations. Finally, PrAViC is evaluated through comparison with existing state-of-the-art offline and online models and datasets, enabling the network to significantly reduce the time required to reach classification decisions while maintaining, or even enhancing, accuracy.

Primary Area: applications to computer vision, audio, language, and other modalities

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 10022