{"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/gl-rg-global-local-representation-granularity","title":"GL-RG: Global-Local Representation Granularity for Video Captioning","arxiv_id":"2205.10706","date":"2022-05-22","proceeding":null,"authors":["Liqi Yan","Qifan Wang","Yiming Cui","Fuli Feng","Xiaojun Quan","Xiangyu Zhang","Dongfang Liu"],"abstract":"Video captioning is a challenging task as it needs to accurately transform visual understanding into natural language description. To date, state-of-the-art methods inadequately model global-local representation across video frames for caption generation, leaving plenty of room for improvement. In this work, we approach the video captioning task from a new perspective and propose a GL-RG framework for video captioning, namely a \\textbf{G}lobal-\\textbf{L}ocal \\textbf{R}epresentation \\textbf{G}ranularity. Our GL-RG demonstrates three advantages over the prior efforts: 1) we explicitly exploit extensive visual representations from different video ranges to improve linguistic expression; 2) we devise a novel global-local encoder to produce rich semantic vocabulary to obtain a descriptive granularity of video contents across frames; 3) we develop an incremental training strategy which organizes model learning in an incremental fashion to incur an optimal captioning behavior. Experimental results on the challenging MSR-VTT and MSVD datasets show that our DL-RG outperforms recent state-of-the-art methods by a significant margin. Code is available at \\url{https://github.com/ylqi/GL-RG}.","url_abs":"https://arxiv.org/abs/2205.10706v2","url_pdf":"https://arxiv.org/pdf/2205.10706v2.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":"gl-rg-global-local-representation-granularity","repo_url":"https://github.com/ylqi/gl-rg","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"caption-generation","task_name":"Caption Generation"},{"task_slug":"descriptive","task_name":"Descriptive"},{"task_slug":"video-captioning","task_name":"Video Captioning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2205.10706","atlas_url":"https://app.syntology.ai/?focus=2205.10706","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.10706"}},"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":"deterministic:regex_extraction","url":"https://github.com/ylqi/GL-RG","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":2,"unverified":3},"by_repo_kind":{"official":{"samples":5,"ran":2,"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":"df8307aa9ed79f6d","entry":"FeatExpander","repo":"ylqi/GL-RG","repo_kind":"official","path":"model.py","file_url":"https://github.com/ylqi/GL-RG/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"df8307aa9ed79f6d"}},{"code_sha256_prefix":"81209e447439383d","entry":"FeatPool","repo":"ylqi/GL-RG","repo_kind":"official","path":"model.py","file_url":"https://github.com/ylqi/GL-RG/blob/HEAD/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"81209e447439383d"}},{"code_sha256_prefix":"f12494bc8def5516","entry":"CaptionModel","repo":"ylqi/GL-RG","repo_kind":"official","path":"model.py","file_url":"https://github.com/ylqi/GL-RG/blob/HEAD/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":"f12494bc8def5516"}},{"code_sha256_prefix":"2e0c1b0b72a384f7","entry":"MANet","repo":"ylqi/GL-RG","repo_kind":"official","path":"model.py","file_url":"https://github.com/ylqi/GL-RG/blob/HEAD/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":"2e0c1b0b72a384f7"}},{"code_sha256_prefix":"46ab935a0e7a21fe","entry":"RNNUnit","repo":"ylqi/GL-RG","repo_kind":"official","path":"model.py","file_url":"https://github.com/ylqi/GL-RG/blob/HEAD/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":"46ab935a0e7a21fe"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}