{"id":23,"date":"2025-05-09T21:25:52","date_gmt":"2025-05-09T21:25:52","guid":{"rendered":"https:\/\/mscvprojects.ri.cmu.edu\/2025team17\/?page_id=23"},"modified":"2025-12-12T19:00:37","modified_gmt":"2025-12-12T19:00:37","slug":"related-work","status":"publish","type":"page","link":"https:\/\/mscvprojects.ri.cmu.edu\/2025team17\/related-work\/","title":{"rendered":"Related work"},"content":{"rendered":"\n

From Local to Global: A Graph RAG Approach to Query-Focused Summarization<\/h2>\n\n\n\n

Key Idea<\/strong>: GraphRAG targets global QA by extracting an entity\u2013relation graph from the corpus, clustering it into communities, and generating hierarchical community summaries that are combined via a map-reduce answering step. It\u2019s evaluated on podcast\/news corpora with LLM-based rubrics (e.g., comprehensiveness\/diversity) and shows large context-token reductions at higher summary levels while outperforming a vector-RAG baseline on those global QA metrics in their setup.<\/p>\n\n\n\n

Video ReCap: Recursive Captioning of Hour-Long Videos<\/h2>\n\n\n\n

Key Idea<\/strong>: Introduces a hierarchical approach to video captioning via recursive temporal summarization.<\/p>\n\n\n\n

Relevance<\/strong>: Shows the power of hierarchical modeling for long-form video understanding.<\/p>\n\n\n\n

Limitation<\/strong>: Designed for caption generation, not structured reasoning or graph-based representation.<\/p>\n\n\n\n

<\/p>\n\n\n\n

GraphVQA: Language-Guided Graph Neural Networks for Scene Graph Question Answering<\/h2>\n\n\n\n

Key Idea<\/strong>: Uses question-guided graph neural networks to perform reasoning over scene graphs for visual question answering.
Relevance<\/strong>: Highlights the benefits of structured, interpretable reasoning using scene graphs aligned with language.
Limitation<\/strong>: Focuses on static graphs without modeling temporal changes or multi-scale event structures.<\/p>\n\n\n\n

<\/p>\n\n\n\n

References<\/h2>\n\n\n\n

[1] Edge et al. (2025). From Local to Global: A Graph RAG Approach to Query-Focused Summarization<\/em>. arXiv:2404.16130 [cs.CL]. https:\/\/arxiv.org\/abs\/2404.16130<\/a><\/p>\n\n\n\n

[2] Islam, Md Mohaiminul, et al. “Video recap: Recursive captioning of hour-long videos.” Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition<\/em>. 2024.<\/p>\n\n\n\n

[3] Liang, Weixin, Yanhao Jiang, and Zixuan Liu. “GraghVQA: Language-guided graph neural networks for graph-based visual question answering.” arXiv preprint arXiv:2104.10283<\/em> (2021).[6] Nag, Sayak, et al. “Unbiased scene graph generation in videos.” Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition<\/em>. 2023.<\/p>\n","protected":false},"excerpt":{"rendered":"

From Local to Global: A Graph RAG Approach to Query-Focused Summarization Key Idea: GraphRAG targets global QA by extracting an entity\u2013relation graph from the corpus, clustering it into communities, and generating hierarchical community summaries that are combined via a map-reduce answering step. It\u2019s evaluated on podcast\/news corpora with LLM-based rubrics (e.g., comprehensiveness\/diversity) and shows large … <\/p>\n

Continue reading “Related work”<\/span><\/a><\/p>\n","protected":false},"author":239,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-23","page","type-page","status-publish","hentry"],"yoast_head":"\nRelated work - Temporally Hierarchical Scene Graph Generation for Video Question Answering\u200b<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/mscvprojects.ri.cmu.edu\/2025team17\/related-work\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Related work - Temporally Hierarchical Scene Graph Generation for Video Question Answering\u200b\" \/>\n<meta property=\"og:description\" content=\"From Local to Global: A Graph RAG Approach to Query-Focused Summarization Key Idea: GraphRAG targets global QA by extracting an entity\u2013relation graph from the corpus, clustering it into communities, and generating hierarchical community summaries that are combined via a map-reduce answering step. It\u2019s evaluated on podcast\/news corpora with LLM-based rubrics (e.g., comprehensiveness\/diversity) and shows large … Continue reading "Related work"\" \/>\n<meta property=\"og:url\" content=\"https:\/\/mscvprojects.ri.cmu.edu\/2025team17\/related-work\/\" \/>\n<meta property=\"og:site_name\" content=\"Temporally Hierarchical Scene Graph Generation for Video Question Answering\u200b\" \/>\n<meta property=\"article:modified_time\" content=\"2025-12-12T19:00:37+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/lh7-rt.googleusercontent.com\/slidesz\/AGV_vUcwX_4xMwgdF_sKO2oF_lOEEidrZ9ByfoSae9JX0Jfacbl4crEWleYHHPo4Yd59MNhmRvcFuNWbJ_Lgnjkmr_Cov4BUzhLrn6k6758gXh0o-vYaHY-HAspcydEqybJQ_uk7JYn_WqJR29LcSDFcpxk=s2048?key=6psAIB2t9kn9gt6s8GRJFdIQ\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data1\" content=\"2 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team17\\\/related-work\\\/\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team17\\\/related-work\\\/\",\"name\":\"Related work - Temporally Hierarchical Scene Graph Generation for Video Question Answering\u200b\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team17\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team17\\\/related-work\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team17\\\/related-work\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/lh7-rt.googleusercontent.com\\\/slidesz\\\/AGV_vUcwX_4xMwgdF_sKO2oF_lOEEidrZ9ByfoSae9JX0Jfacbl4crEWleYHHPo4Yd59MNhmRvcFuNWbJ_Lgnjkmr_Cov4BUzhLrn6k6758gXh0o-vYaHY-HAspcydEqybJQ_uk7JYn_WqJR29LcSDFcpxk=s2048?key=6psAIB2t9kn9gt6s8GRJFdIQ\",\"datePublished\":\"2025-05-09T21:25:52+00:00\",\"dateModified\":\"2025-12-12T19:00:37+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team17\\\/related-work\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team17\\\/related-work\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team17\\\/related-work\\\/#primaryimage\",\"url\":\"https:\\\/\\\/lh7-rt.googleusercontent.com\\\/slidesz\\\/AGV_vUcwX_4xMwgdF_sKO2oF_lOEEidrZ9ByfoSae9JX0Jfacbl4crEWleYHHPo4Yd59MNhmRvcFuNWbJ_Lgnjkmr_Cov4BUzhLrn6k6758gXh0o-vYaHY-HAspcydEqybJQ_uk7JYn_WqJR29LcSDFcpxk=s2048?key=6psAIB2t9kn9gt6s8GRJFdIQ\",\"contentUrl\":\"https:\\\/\\\/lh7-rt.googleusercontent.com\\\/slidesz\\\/AGV_vUcwX_4xMwgdF_sKO2oF_lOEEidrZ9ByfoSae9JX0Jfacbl4crEWleYHHPo4Yd59MNhmRvcFuNWbJ_Lgnjkmr_Cov4BUzhLrn6k6758gXh0o-vYaHY-HAspcydEqybJQ_uk7JYn_WqJR29LcSDFcpxk=s2048?key=6psAIB2t9kn9gt6s8GRJFdIQ\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team17\\\/related-work\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team17\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Related work\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team17\\\/#website\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team17\\\/\",\"name\":\"Temporally Hierarchical Scene Graph Generation for Video Question Answering\u200b\",\"description\":\"\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2025team17\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Related work - Temporally Hierarchical Scene Graph Generation for Video Question Answering\u200b","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/mscvprojects.ri.cmu.edu\/2025team17\/related-work\/","og_locale":"en_US","og_type":"article","og_title":"Related work - Temporally Hierarchical Scene Graph Generation for Video Question Answering\u200b","og_description":"From Local to Global: A Graph RAG Approach to Query-Focused Summarization Key Idea: GraphRAG targets global QA by extracting an entity\u2013relation graph from the corpus, clustering it into communities, and generating hierarchical community summaries that are combined via a map-reduce answering step. It\u2019s evaluated on podcast\/news corpora with LLM-based rubrics (e.g., comprehensiveness\/diversity) and shows large … Continue reading \"Related work\"","og_url":"https:\/\/mscvprojects.ri.cmu.edu\/2025team17\/related-work\/","og_site_name":"Temporally Hierarchical Scene Graph Generation for Video Question Answering\u200b","article_modified_time":"2025-12-12T19:00:37+00:00","og_image":[{"url":"https:\/\/lh7-rt.googleusercontent.com\/slidesz\/AGV_vUcwX_4xMwgdF_sKO2oF_lOEEidrZ9ByfoSae9JX0Jfacbl4crEWleYHHPo4Yd59MNhmRvcFuNWbJ_Lgnjkmr_Cov4BUzhLrn6k6758gXh0o-vYaHY-HAspcydEqybJQ_uk7JYn_WqJR29LcSDFcpxk=s2048?key=6psAIB2t9kn9gt6s8GRJFdIQ","type":"","width":"","height":""}],"twitter_card":"summary_large_image","twitter_misc":{"Est. reading time":"2 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2025team17\/related-work\/","url":"https:\/\/mscvprojects.ri.cmu.edu\/2025team17\/related-work\/","name":"Related work - Temporally Hierarchical Scene Graph Generation for Video Question Answering\u200b","isPartOf":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2025team17\/#website"},"primaryImageOfPage":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2025team17\/related-work\/#primaryimage"},"image":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2025team17\/related-work\/#primaryimage"},"thumbnailUrl":"https:\/\/lh7-rt.googleusercontent.com\/slidesz\/AGV_vUcwX_4xMwgdF_sKO2oF_lOEEidrZ9ByfoSae9JX0Jfacbl4crEWleYHHPo4Yd59MNhmRvcFuNWbJ_Lgnjkmr_Cov4BUzhLrn6k6758gXh0o-vYaHY-HAspcydEqybJQ_uk7JYn_WqJR29LcSDFcpxk=s2048?key=6psAIB2t9kn9gt6s8GRJFdIQ","datePublished":"2025-05-09T21:25:52+00:00","dateModified":"2025-12-12T19:00:37+00:00","breadcrumb":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2025team17\/related-work\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/mscvprojects.ri.cmu.edu\/2025team17\/related-work\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2025team17\/related-work\/#primaryimage","url":"https:\/\/lh7-rt.googleusercontent.com\/slidesz\/AGV_vUcwX_4xMwgdF_sKO2oF_lOEEidrZ9ByfoSae9JX0Jfacbl4crEWleYHHPo4Yd59MNhmRvcFuNWbJ_Lgnjkmr_Cov4BUzhLrn6k6758gXh0o-vYaHY-HAspcydEqybJQ_uk7JYn_WqJR29LcSDFcpxk=s2048?key=6psAIB2t9kn9gt6s8GRJFdIQ","contentUrl":"https:\/\/lh7-rt.googleusercontent.com\/slidesz\/AGV_vUcwX_4xMwgdF_sKO2oF_lOEEidrZ9ByfoSae9JX0Jfacbl4crEWleYHHPo4Yd59MNhmRvcFuNWbJ_Lgnjkmr_Cov4BUzhLrn6k6758gXh0o-vYaHY-HAspcydEqybJQ_uk7JYn_WqJR29LcSDFcpxk=s2048?key=6psAIB2t9kn9gt6s8GRJFdIQ"},{"@type":"BreadcrumbList","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2025team17\/related-work\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/mscvprojects.ri.cmu.edu\/2025team17\/"},{"@type":"ListItem","position":2,"name":"Related work"}]},{"@type":"WebSite","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2025team17\/#website","url":"https:\/\/mscvprojects.ri.cmu.edu\/2025team17\/","name":"Temporally Hierarchical Scene Graph Generation for Video Question Answering\u200b","description":"","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/mscvprojects.ri.cmu.edu\/2025team17\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"}]}},"_links":{"self":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2025team17\/wp-json\/wp\/v2\/pages\/23","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2025team17\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2025team17\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2025team17\/wp-json\/wp\/v2\/users\/239"}],"replies":[{"embeddable":true,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2025team17\/wp-json\/wp\/v2\/comments?post=23"}],"version-history":[{"count":4,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2025team17\/wp-json\/wp\/v2\/pages\/23\/revisions"}],"predecessor-version":[{"id":71,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2025team17\/wp-json\/wp\/v2\/pages\/23\/revisions\/71"}],"wp:attachment":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2025team17\/wp-json\/wp\/v2\/media?parent=23"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}