Print Email Facebook Twitter Evaluation of Video Summarization Using Fully Convolutional Sequence Networks on Action Localization Datasets Title Evaluation of Video Summarization Using Fully Convolutional Sequence Networks on Action Localization Datasets Author Frolke, Paul (TU Delft Electrical Engineering, Mathematics and Computer Science; TU Delft Intelligent Systems) Contributor Strafforello, O. (mentor) Khademi, S. (graduation committee) Höllt, T. (graduation committee) Degree granting institution Delft University of Technology Programme Computer Science and Engineering Project CSE3000 Research Project Date 2021-07-01 Abstract In the problem of video summarization, the goal is to select a subset of the input frames conveying the most important information of the input video. The collection of data proves to be a challenging task. In part because there exists a disagreement among human annotators on what segments of a video should be considered important for a summary. In this study we analyse a new dataset created with the goal of increasing agreement between the human annotators. The dataset has been created with the use of a novel annotation method, which uses existing action localization labels for segmenting the videos. We train a supervised and an unsupervised deep learning framework on popularly used benchmark datasets and the new dataset. Experimental results show the effectiveness of this novel summary annotation method in improvingthe agreement between annotators. Analysis reveals some issues with the evaluation of the deep learning framework. Subject Video summarizationfully convolutional neural networksaction localization dataset To reference this document use: http://resolver.tudelft.nl/uuid:7b1da021-0216-4977-b339-961960cd2880 Part of collection Student theses Document type bachelor thesis Rights © 2021 Paul Frolke Files PDF RP_paper_Paul_Frolke_final.pdf 9.3 MB Close viewer /islandora/object/uuid:7b1da021-0216-4977-b339-961960cd2880/datastream/OBJ/view