相关参考文献
注意:仅列出部分参考文献,下载原文获取全部文献信息。
Article
Computer Science, Artificial Intelligence
G. M. Mashrur E. Elahi et al.
Summary: This paper introduces an online learnable module for keyframe extraction, which selects key shots in videos for summarization and reduces processing time. Additionally, a novel train/test strategy is proposed by combining semantic word vectors with keyframes, providing a new direction for action recognition.
PATTERN RECOGNITION
(2022)
Article
Computer Science, Artificial Intelligence
Wencheng Zhu et al.
Summary: This paper proposes a multiscale hierarchical attention approach for supervised video summarization, which leverages both the short-range and long-range temporal representations via intra-block and inter-block attention. The method integrates frame-level, block-level, and video-level representations to predict importance scores, conducts shot segmentation, computes shot-level scores, and performs key shot selection for producing video summaries. Furthermore, the two-stream framework incorporating appearance and motion information enhances the effectiveness of the method, as validated on the SumMe and TVSum datasets.
PATTERN RECOGNITION
(2022)
Article
Computer Science, Artificial Intelligence
Abhimanyu Sahu et al.
Summary: This paper introduces a new method for summarizing first-person videos by utilizing different graph representations and shot boundary detection techniques. Additionally, a new approach is proposed to characterize egocentric video frames by exploiting differences between center and surround regions. Finally, video frames are clustered and summarized using a Minimum Spanning Tree algorithm and a new measure for inadmissible edges.
PATTERN RECOGNITION LETTERS
(2021)
Article
Computer Science, Artificial Intelligence
Abhimanyu Sahu et al.
Summary: The paper proposes a weakly supervised superpixel level joint framework for localization, recognition, and summarization of actions in egocentric video. Superpixels are extracted within the central regions of the egocentric video frames, a sparse spatio-temporal video representation graph is constructed in the deep feature space, and a weakly supervised solution using random walks yields action labels for each superpixel, with a fractional knapsack type formulation used for obtaining a summary of actions. Experimental comparisons on various datasets demonstrate the effectiveness of the proposed solution.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2021)
Article
Computer Science, Artificial Intelligence
Wencheng Zhu et al.
Summary: The paper proposes a DSNet framework for supervised video summarization, including anchor-based and anchor-free methods. The anchor-based method generates dense sampling of temporal interest proposals and extracts long-range temporal features, while the anchor-free method directly predicts importance scores of video frames and segment locations. Both approaches show effectiveness in experimental evaluations on SumMe and TVSum datasets.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2021)
Article
Computer Science, Artificial Intelligence
Abhimanyu Sahu et al.
Article
Engineering, Electrical & Electronic
Yitian Yuan et al.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2019)
Article
Computer Science, Artificial Intelligence
Xuelong Li et al.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2017)
Article
Computer Science, Artificial Intelligence
Suriya Singh et al.
PATTERN RECOGNITION
(2017)
Article
Engineering, Electrical & Electronic
Alejandro Betancourt et al.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2015)
Article
Computer Science, Artificial Intelligence
Shaohui Mei et al.
PATTERN RECOGNITION
(2015)
Article
Computer Science, Artificial Intelligence
Jurandy Almeida et al.
PATTERN RECOGNITION LETTERS
(2012)
Article
Computer Science, Artificial Intelligence
Sandra Eliza Fontes de Avila et al.
PATTERN RECOGNITION LETTERS
(2011)
Article
Computer Science, Artificial Intelligence
Sinno Jialin Pan et al.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2010)
Article
Computer Science, Artificial Intelligence
Leo Grady
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2006)