{"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/stories-for-images-in-sequence-by-using","title":"Stories for Images-in-Sequence by using Visual and Narrative Components","arxiv_id":"1805.05622","date":"2018-05-15","proceeding":null,"authors":["Marko Smilevski","Ilija Lalkovski","Gjorgji Madjarov"],"abstract":"Recent research in AI is focusing towards generating narrative stories about\nvisual scenes. It has the potential to achieve more human-like understanding\nthan just basic description generation of images- in-sequence. In this work, we\npropose a solution for generating stories for images-in-sequence that is based\non the Sequence to Sequence model. As a novelty, our encoder model is composed\nof two separate encoders, one that models the behaviour of the image sequence\nand other that models the sentence-story generated for the previous image in\nthe sequence of images. By using the image sequence encoder we capture the\ntemporal dependencies between the image sequence and the sentence-story and by\nusing the previous sentence-story encoder we achieve a better story flow. Our\nsolution generates long human-like stories that not only describe the visual\ncontext of the image sequence but also contains narrative and evaluative\nlanguage. The obtained results were confirmed by manual human evaluation.","url_abs":"http://arxiv.org/abs/1805.05622v3","url_pdf":"http://arxiv.org/pdf/1805.05622v3.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":"stories-for-images-in-sequence-by-using","repo_url":"https://github.com/Pendulibrium/ai-visual-storytelling-seq2seq","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"sentence","task_name":"Sentence"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1805.05622","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}