{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/a-read-write-memory-network-for-movie-story","title":"A Read-Write Memory Network for Movie Story Understanding","arxiv_id":"1709.09345","date":"2017-09-27","proceeding":"ICCV 2017 10","authors":["Seil Na","Sang-ho Lee","Ji-Sung Kim","Gunhee Kim"],"abstract":"We propose a novel memory network model named Read-Write Memory Network\n(RWMN) to perform question and answering tasks for large-scale, multimodal\nmovie story understanding. The key focus of our RWMN model is to design the\nread network and the write network that consist of multiple convolutional\nlayers, which enable memory read and write operations to have high capacity and\nflexibility. While existing memory-augmented network models treat each memory\nslot as an independent block, our use of multi-layered CNNs allows the model to\nread and write sequential memory cells as chunks, which is more reasonable to\nrepresent a sequential story because adjacent memory blocks often have strong\ncorrelations. For evaluation, we apply our model to all the six tasks of the\nMovieQA benchmark, and achieve the best accuracies on several tasks, especially\non the visual QA task. Our model shows a potential to better understand not\nonly the content in the story, but also more abstract information, such as\nrelationships between characters and the reasons for their actions.","url_abs":"http://arxiv.org/abs/1709.09345v4","url_pdf":"http://arxiv.org/pdf/1709.09345v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"a-read-write-memory-network-for-movie-story","repo_url":"https://github.com/seilna/RWMN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"video-story-qa","task_name":"Video Story QA"}],"methods":[{"method_slug":"memory-network","method_name":"Memory Network"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-story-qa-on-movieqa","task":"Video Story QA","dataset":"MovieQA","model":"RWMN","rank_in_archive_order":3,"of":3,"metrics":{"Accuracy":"36.25"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1709.09345","atlas_url":"https://app.syntology.ai/?focus=1709.09345","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}