Text-Driven Video Acceleration: A Weakly-Supervised Reinforcement Learning Method

• Published in: IEEE transactions on pattern analysis and machine intelligence Vol. 45; no. 2; pp. 2492 - 2504
• Main Authors: Ramos, Washington, Silva, Michel, Araujo, Edson, Moura, Victor, Oliveira, Keller, Marcolino, Leandro Soriano, Nascimento, Erickson R.
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.02.2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: cross-modal data; fast-forward; Frames (data processing); instructional video; Reinforcement learning; Semantics; Social networking (online); Task analysis; Training; Tutorials; Untrimmed videos; Video; Visual discrimination; Visualization
• ISSN: 0162-8828; 1939-3539; 2160-9292
• DOI: 10.1109/TPAMI.2022.3157198

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.