2 Hits in 3.1 sec

PR-Net: Preference Reasoning for Personalized Video Highlight Detection [article]

Runnan Chen, Penghao Zhou, Wenzhe Wang, Nenglun Chen, Pai Peng, Xing Sun, Wenping Wang
2021 arXiv   pre-print
In this paper, we propose a simple yet efficient preference reasoning framework (PR-Net) to explicitly take the diverse interests into account for frame-level highlight prediction.  ...  Personalized video highlight detection aims to shorten a long video to interesting moments according to a user's preference, which has recently raised the community's attention.  ...  In this paper, we propose a preference reasoning framework (PR-Net) for frame-level personalized video highlight detection, which overcomes the above limitations.  ... 
arXiv:2109.01799v1 fatcat:mzawjvvsafhhbapuak5ocnr4re

Show Me What I Like: Detecting User-Specific Video Highlights Using Content-Based Multi-Head Attention [article]

Uttaran Bhattacharya and Gang Wu and Stefano Petrangeli and Viswanathan Swaminathan and Dinesh Manocha
2022 arXiv   pre-print
We propose a method to detect individualized highlights for users on given target videos based on their preferred highlight clips marked on previous videos they have watched.  ...  Our method explicitly leverages the contents of both the preferred clips and the target videos using pre-trained features for the objects and the human activities.  ...  [16] , PHD-GIF by del Molino and Gygli [11] , Personalized Summarization by Panagiotakis et al. [32] , Adaptive-FCSN by Rochan et al. [35] , and PR-Net by Chen et al.  ... 
arXiv:2207.08352v1 fatcat:z6fclew26bajpfcwyddl4hkkhe