{"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-neural-multi-sequence-alignment-technique","title":"A Neural Multi-sequence Alignment TeCHnique (NeuMATCH)","arxiv_id":"1803.00057","date":"2018-02-19","proceeding":"CVPR 2018 6","authors":["Pelin Dogan","Boyang Li","Leonid Sigal","Markus Gross"],"abstract":"The alignment of heterogeneous sequential data (video to text) is an\nimportant and challenging problem. Standard techniques for this task, including\nDynamic Time Warping (DTW) and Conditional Random Fields (CRFs), suffer from\ninherent drawbacks. Mainly, the Markov assumption implies that, given the\nimmediate past, future alignment decisions are independent of further history.\nThe separation between similarity computation and alignment decision also\nprevents end-to-end training. In this paper, we propose an end-to-end neural\narchitecture where alignment actions are implemented as moving data between\nstacks of Long Short-term Memory (LSTM) blocks. This flexible architecture\nsupports a large variety of alignment tasks, including one-to-one, one-to-many,\nskipping unmatched elements, and (with extensions) non-monotonic alignment.\nExtensive experiments on semi-synthetic and real datasets show that our\nalgorithm outperforms state-of-the-art baselines.","url_abs":"http://arxiv.org/abs/1803.00057v2","url_pdf":"http://arxiv.org/pdf/1803.00057v2.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-neural-multi-sequence-alignment-technique","repo_url":"https://github.com/pelindogan/NeuMATCH","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"dynamic-time-warping","task_name":"Dynamic Time Warping"}],"methods":[],"datasets_introduced":[{"slug":"youtube-movie-summaries","name":"YouTube Movie Summaries","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1803.00057","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}