{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/end-to-end-video-captioning-with-multitask","title":"End-to-End Video Captioning with Multitask Reinforcement Learning","arxiv_id":"1803.07950","date":"2018-03-21","proceeding":null,"authors":["Lijun Li","Boqing Gong"],"abstract":"Although end-to-end (E2E) learning has led to impressive progress on a\nvariety of visual understanding tasks, it is often impeded by hardware\nconstraints (e.g., GPU memory) and is prone to overfitting. When it comes to\nvideo captioning, one of the most challenging benchmark tasks in computer\nvision, those limitations of E2E learning are especially amplified by the fact\nthat both the input videos and output captions are lengthy sequences. Indeed,\nstate-of-the-art methods for video captioning process video frames by\nconvolutional neural networks and generate captions by unrolling recurrent\nneural networks. If we connect them in an E2E manner, the resulting model is\nboth memory-consuming and data-hungry, making it extremely hard to train. In\nthis paper, we propose a multitask reinforcement learning approach to training\nan E2E video captioning model. The main idea is to mine and construct as many\neffective tasks (e.g., attributes, rewards, and the captions) as possible from\nthe human captioned videos such that they can jointly regulate the search space\nof the E2E neural network, from which an E2E video captioning model can be\nfound and generalized to the testing phase. To the best of our knowledge, this\nis the first video captioning model that is trained end-to-end from the raw\nvideo input to the caption output. Experimental results show that such a model\noutperforms existing ones to a large margin on two benchmark video captioning\ndatasets.","url_abs":"http://arxiv.org/abs/1803.07950v2","url_pdf":"http://arxiv.org/pdf/1803.07950v2.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":"end-to-end-video-captioning-with-multitask","repo_url":"https://github.com/adwardlee/multitask-end-to-end-video-captioning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":null,"task_name":"GPU"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"unrolling","task_name":"Rolling Shutter Correction"},{"task_slug":"video-captioning","task_name":"Video Captioning"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"arxiv_id_not_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"by_repo":[{"repo":"adwardlee/multitask-end-to-end-video-captioning","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"6d76fc9c7a2d565eec1d07411e7ea21a79945178c2d2da0745b4152bc0f42a8a","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}