{"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/weakly-supervised-video-scene-graph","title":"Weakly Supervised Video Scene Graph Generation via Natural Language Supervision","arxiv_id":"2502.15370","date":"2025-02-21","proceeding":null,"authors":["Kibum Kim","Kanghoon Yoon","Yeonjun In","Jaehyeong Jeon","Jinyoung Moon","Donghyun Kim","Chanyoung Park"],"abstract":"Existing Video Scene Graph Generation (VidSGG) studies are trained in a fully supervised manner, which requires all frames in a video to be annotated, thereby incurring high annotation cost compared to Image Scene Graph Generation (ImgSGG). Although the annotation cost of VidSGG can be alleviated by adopting a weakly supervised approach commonly used for ImgSGG (WS-ImgSGG) that uses image captions, there are two key reasons that hinder such a naive adoption: 1) Temporality within video captions, i.e., unlike image captions, video captions include temporal markers (e.g., before, while, then, after) that indicate time related details, and 2) Variability in action duration, i.e., unlike human actions in image captions, human actions in video captions unfold over varying duration. To address these issues, we propose a Natural Language-based Video Scene Graph Generation (NL-VSGG) framework that only utilizes the readily available video captions for training a VidSGG model. NL-VSGG consists of two key modules: Temporality-aware Caption Segmentation (TCS) module and Action Duration Variability-aware caption-frame alignment (ADV) module. Specifically, TCS segments the video captions into multiple sentences in a temporal order based on a Large Language Model (LLM), and ADV aligns each segmented sentence with appropriate frames considering the variability in action duration. Our approach leads to a significant enhancement in performance compared to simply applying the WS-ImgSGG pipeline to VidSGG on the Action Genome dataset. As a further benefit of utilizing the video captions as weak supervision, we show that the VidSGG model trained by NL-VSGG is able to predict a broader range of action classes that are not included in the training data, which makes our framework practical in reality.","url_abs":"https://arxiv.org/abs/2502.15370v1","url_pdf":"https://arxiv.org/pdf/2502.15370v1.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":"weakly-supervised-video-scene-graph","repo_url":"https://github.com/rlqja1107/NL-VSGG","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"graph-generation","task_name":"Graph Generation"},{"task_slug":"image-captioning","task_name":"Image Captioning"},{"task_slug":"large-language-model","task_name":"Large Language Model"},{"task_slug":"scene-graph-generation","task_name":"Scene Graph Generation"},{"task_slug":"video-scene-graph-generation","task_name":"Video scene graph generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2502.15370","atlas_url":"https://app.syntology.ai/?focus=2502.15370","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.15370"}},"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/rlqja1107/NL-VSGG","reach":{"status":"ok"}}],"summary":{"ran_violates":1,"ran_fixture":1},"by_repo_kind":{"official":{"samples":2,"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":2,"samples":[{"code_sha256_prefix":"7aef2a8cb287a30b","entry":"str2bool","repo":"rlqja1107/nl-vsgg","repo_kind":"official","path":"tools/train_STTran.py","file_url":"https://github.com/rlqja1107/nl-vsgg/blob/HEAD/tools/train_STTran.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":2,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7aef2a8cb287a30b"}},{"code_sha256_prefix":"2737263692a07872","entry":"find_consecutive_numbers","repo":"rlqja1107/nl-vsgg","repo_kind":"official","path":"NL-VSGG/ADV.py","file_url":"https://github.com/rlqja1107/nl-vsgg/blob/HEAD/NL-VSGG/ADV.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2737263692a07872"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}