Text-driven video acceleration : A weakly-supervised reinforcement learning method

Ramos, W.L.D.S. and Silva, M.M.D. and Araujo, E. and Moura, V. and Martins de Oliveira, K.C. and Soriano Marcolino, L. and Nascimento, E. (2023) Text-driven video acceleration : A weakly-supervised reinforcement learning method. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45 (2). pp. 2492-2504. ISSN 0162-8828

[thumbnail of TextDrivenVideoAcceleration_TPAMI2022]
Text (TextDrivenVideoAcceleration_TPAMI2022)
TextDrivenVideoAcceleration_TPAMI2022.pdf - Accepted Version
Available under License Creative Commons Attribution-NonCommercial.

Download (13MB)

Abstract

The growth of videos in our digital age and the users' limited time raise the demand for processing untrimmed videos to produce shorter versions conveying the same information. Despite the remarkable progress that summarization methods have made, most of them can only select a few frames or skims, creating visual gaps and breaking the video context. This paper presents a novel weakly-supervised methodology based on a reinforcement learning formulation to accelerate instructional videos using text. A novel joint reward function guides our agent to select which frames to remove and reduce the input video to a target length without creating gaps in the final video. We also propose the Extended Visually-guided Document Attention Network (VDAN+), which can generate a highly discriminative embedding space to represent both textual and visual data. Our experiments show that our method achieves the best performance in Precision, Recall, and F1 Score against the baselines while effectively controlling the video's output length. IEEE

Item Type:
Journal Article
Journal or Publication Title:
IEEE Transactions on Pattern Analysis and Machine Intelligence
Additional Information:
©2022 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
Uncontrolled Keywords:
/dk/atira/pure/subjectarea/asjc/1700/1702
Subjects:
?? cross-modal datafast-forwardinstructional videoreinforcement learningreinforcement learningsemanticssocial networking (online)task analysistrainingtutorialsuntrimmed videosvisualizationartificial intelligencecomputational theory and mathematicssoftwareapp ??
ID Code:
167980
Deposited By:
Deposited On:
29 Mar 2022 13:35
Refereed?:
Yes
Published?:
Published
Last Modified:
10 Jan 2024 00:32