VSS-Net: Visual Semantic Self-Mining Network for Video Summarization

• Published in: IEEE transactions on circuits and systems for video technology Vol. 34; no. 4; pp. 2775 - 2788
• Main Authors: Zhang, Yunzuo, Liu, Yameng, Kang, Weili, Tao, Ran
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.04.2024; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Cognitive tasks; Computational modeling; Context; Context modeling; Feature extraction; Graphical representations; information exchange; Learning; Predictions; Segments; self-mining; semantic representation; Semantics; Streaming media; Target detection; Task analysis; temporal cues; Video data; Video summarization; Visualization
• DOI: 10.1109/TCSVT.2023.3312325
• ISSN: 1051-8215

Video summarization, with the target to detect valuable segments given untrimmed videos, is a meaningful yet understudied topic. Previous methods primarily consider inter-frame and inter-shot temporal dependencies, which might be insufficient to pinpoint important content due to limited valuable information that can be learned. To address this limitation, we elaborate on a Visual Semantic Self-mining Network (VSS-Net), a novel summarization framework motivated by the widespread success of cross-modality learning tasks. VSS-Net initially adopts a two-stream structure consisting of a Context Representation Graph (CRG) and a Video Semantics Encoder (VSE). They are jointly exploited to establish the groundwork for further boosting the capability of content awareness. Specifically, CRG is constructed using an edge-set strategy tailored to the hierarchical structure of videos, enriching visual features with local and non-local temporal cues from temporal order and visual relationship perspectives. Meanwhile, by learning visual similarity across features, VSE adaptively acquires an instructive video-level semantic representation of the input video from coarse to fine. Subsequently, the two streams converge in a Context-Semantics Interaction Layer (CSIL) to achieve sophisticated information exchange across frame-level temporal cues and video-level semantic representation, guaranteeing informative representations and boosting the sensitivity to important segments. Eventually, importance scores are predicted utilizing a prediction head, followed by key shot selection. We evaluate the proposed framework and demonstrate its effectiveness and superiority against state-of-the-art methods on the widely used benchmarks.