Semi-supervised and Active Learning in Video Scene Classification from Statistical Features

0493293 - ÚI 2019 RIV IE eng C - Konferenční příspěvek (zahraniční konf.)
Šabata, T. - Pulc, Petr - Holeňa, Martin
Semi-supervised and Active Learning in Video Scene Classification from Statistical Features.
ECML PKDD 2018: Workshop on Interactive Adaptive Learning. Proceedings. Dublin, 2018 - (Krempl, G.; Lemaire, V.; Kottke, D.; Calma, A.; Holzinger, A.; Polikar, R.; Sick, B.), s. 24-35
[ECML PKDD 2018: The European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases. Dublin (IE), 10.09.2018-14.09.2018]
Grant CEP: GA ČR(CZ) GA18-18080S
Institucionální podpora: RVO:67985807
Klíčová slova: video data * scene classification * semi-supervised learning * active learning * colour statistics * feedforward neural networks
Obor OECD: Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

PUBLISHED: ECML PKDD 2018: Workshop on Interactive Adaptive Learning. Proceedings. Dublin, 2018 - (Krempl, G., Lemaire, V., Kottke, D., Calma, A., Holzinger, A., Polikar, R., Sick, B.), s. 24-35. [ECML PKDD 2018: The European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases. Dublin (IE), 10.09.2018-14.09.2018]. Grant CEP: GA ČR(CZ) GA18-18080S. ABSTRACT: In multimedia classification, the background is usually considered an unwanted part of input data and is often modeled only to be removed in later processing. Contrary to that, we believe that a background model (i.e., the scene in which the picture or video shot is taken) should be included as an essential feature for both indexing and followup content processing. Information about image background, however, is not usually the main target in the labeling process and the number of annotated samples is very limited. Therefore, we propose to use a combination of semi-supervised and active learning to improve the performance of our scene classifier, specifically a combination of self-training with uncertainty sampling. As a result, we utilize a combination of statistical features extractor, a feed-forward neural network and support vector machine classifier, which consistently achieves higher accuracy on less diverse data. With the proposed approach, we are currently able to achieve precision over 80% on a dataset trained on a single series of a popular TV show.
Trvalý link: http://hdl.handle.net/11104/0286680