{"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/delving-deeper-into-the-decoder-for-video","title":"Delving Deeper into the Decoder for Video Captioning","arxiv_id":"2001.05614","date":"2020-01-16","proceeding":null,"authors":["Haoran Chen","Jianmin Li","Xiaolin Hu"],"abstract":"Video captioning is an advanced multi-modal task which aims to describe a video clip using a natural language sentence. The encoder-decoder framework is the most popular paradigm for this task in recent years. However, there exist some problems in the decoder of a video captioning model. We make a thorough investigation into the decoder and adopt three techniques to improve the performance of the model. First of all, a combination of variational dropout and layer normalization is embedded into a recurrent unit to alleviate the problem of overfitting. Secondly, a new online method is proposed to evaluate the performance of a model on a validation set so as to select the best checkpoint for testing. Finally, a new training strategy called professional learning is proposed which uses the strengths of a captioning model and bypasses its weaknesses. It is demonstrated in the experiments on Microsoft Research Video Description Corpus (MSVD) and MSR-Video to Text (MSR-VTT) datasets that our model has achieved the best results evaluated by BLEU, CIDEr, METEOR and ROUGE-L metrics with significant gains of up to 18% on MSVD and 3.5% on MSR-VTT compared with the previous state-of-the-art models.","url_abs":"https://arxiv.org/abs/2001.05614v3","url_pdf":"https://arxiv.org/pdf/2001.05614v3.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":"delving-deeper-into-the-decoder-for-video","repo_url":"https://github.com/WingsBrokenAngel/delving-deeper-into-the-decoder-for-video-captioning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"video-captioning","task_name":"Video Captioning"},{"task_slug":"video-description","task_name":"Video Description"}],"methods":[{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"variational-dropout","method_name":"Variational Dropout"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2001.05614","atlas_url":"https://app.syntology.ai/?focus=2001.05614","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2001.05614"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/WingsBrokenAngel/delving-deeper-into-the-decoder-for-video-captioning","reach":null}],"summary":{"unverified":2},"by_repo_kind":{"official":{"samples":2,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"48102a8c5eac95bf","entry":"cal_metrics","repo":"WingsBrokenAngel/delving-deeper-into-the-decoder-for-video-captioning","repo_kind":"official","path":"msrvtt/train_model.py","file_url":"https://github.com/WingsBrokenAngel/delving-deeper-into-the-decoder-for-video-captioning/blob/HEAD/msrvtt/train_model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"48102a8c5eac95bf"}},{"code_sha256_prefix":"74b35ce6360835ab","entry":"cal_metrics","repo":"WingsBrokenAngel/delving-deeper-into-the-decoder-for-video-captioning","repo_kind":"official","path":"msvd/train_model.py","file_url":"https://github.com/WingsBrokenAngel/delving-deeper-into-the-decoder-for-video-captioning/blob/HEAD/msvd/train_model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"74b35ce6360835ab"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}