Show and Recall: Learning What Makes Videos Memorable

Published in ICCV Workshop on Mutual Benefits of Cognitive and Computer Vision, 2017

Recommended citation: Sumit Shekhar, Dhruv Singal, Harvineet Singh, Manav Kedia, Akhil Shetty; "Show and Recall: Learning What Makes Videos Memorable." The IEEE International Conference on Computer Vision (ICCV), 2017, pp. 2730-2739. http://openaccess.thecvf.com/content_ICCV_2017_workshops/w40/html/Shekhar_Show_and_Recall_ICCV_2017_paper.html

Past work focussed on predicting memorability of images and there is limited work on video memorability. We design a user study for collecting video recall data and develop a predictor for memorability based on video features such as motion, color, saliency and semantics. Experiments demonstrate the use of the predictor for creating memorable summaries of user-generated video content.

arXiv link

Bibtex:

@inproceedings{shekhar2017show,
  title={Show and Recall: Learning What Makes Videos Memorable},
  author={Shekhar, Sumit and Singal, Dhruv and Singh, Harvineet and Kedia, Manav and Shetty, Akhil},
  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
  pages={2730--2739},
  year={2017}
}