{"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/panoptic-video-scene-graph-generation-1","title":"Panoptic Video Scene Graph Generation","arxiv_id":"2311.17058","date":"2023-11-28","proceeding":"CVPR 2023 1","authors":["Jingkang Yang","Wenxuan Peng","Xiangtai Li","Zujin Guo","Liangyu Chen","Bo Li","Zheng Ma","Kaiyang Zhou","Wayne Zhang","Chen Change Loy","Ziwei Liu"],"abstract":"Towards building comprehensive real-world visual perception systems, we propose and study a new problem called panoptic scene graph generation (PVSG). PVSG relates to the existing video scene graph generation (VidSGG) problem, which focuses on temporal interactions between humans and objects grounded with bounding boxes in videos. However, the limitation of bounding boxes in detecting non-rigid objects and backgrounds often causes VidSGG to miss key details crucial for comprehensive video understanding. In contrast, PVSG requires nodes in scene graphs to be grounded by more precise, pixel-level segmentation masks, which facilitate holistic scene understanding. To advance research in this new area, we contribute the PVSG dataset, which consists of 400 videos (289 third-person + 111 egocentric videos) with a total of 150K frames labeled with panoptic segmentation masks as well as fine, temporal scene graphs. We also provide a variety of baseline methods and share useful design practices for future work.","url_abs":"https://arxiv.org/abs/2311.17058v1","url_pdf":"https://arxiv.org/pdf/2311.17058v1.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":"panoptic-video-scene-graph-generation-1","repo_url":"https://github.com/jingkang50/openpvsg","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"panoptic-video-scene-graph-generation-1","repo_url":"https://github.com/lilydaytoy/openpvsg","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"panoptic-video-scene-graph-generation-1","repo_url":"https://github.com/lilydaytoy/pvsgannotation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"graph-generation","task_name":"Graph Generation"},{"task_slug":"panoptic-scene-graph-generation","task_name":"Panoptic Scene Graph Generation"},{"task_slug":"panoptic-segmentation","task_name":"Panoptic Segmentation"},{"task_slug":"scene-graph-generation","task_name":"Scene Graph Generation"},{"task_slug":"scene-understanding","task_name":"Scene Understanding"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"video-understanding","task_name":"Video Understanding"},{"task_slug":"video-scene-graph-generation","task_name":"Video scene graph generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2311.17058","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.17058"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/lilydaytoy/openpvsg","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jingkang50/openpvsg","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lilydaytoy/pvsgannotation","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/Jingkang50/OpenPVSG","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran":11},"by_repo_kind":{"official":{"samples":11,"ran":11,"repositories":3}},"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":3,"samples":[{"code_sha256_prefix":"b95785cc82d9f984","entry":"PositionalEncoding","repo":"Jingkang50/OpenPVSG","repo_kind":"official","path":"models/relation_head/transformer.py","file_url":"https://github.com/Jingkang50/OpenPVSG/blob/HEAD/models/relation_head/transformer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"b95785cc82d9f984"}},{"code_sha256_prefix":"fb45c2faa0f143c9","entry":"TemporalTransformer","repo":"Jingkang50/OpenPVSG","repo_kind":"official","path":"models/relation_head/transformer.py","file_url":"https://github.com/Jingkang50/OpenPVSG/blob/HEAD/models/relation_head/transformer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"fb45c2faa0f143c9"}},{"code_sha256_prefix":"38a50154b10bd119","entry":"change","repo":"lilydaytoy/pvsgannotation","repo_kind":"official","path":"programs/replace_id.py","file_url":"https://github.com/lilydaytoy/pvsgannotation/blob/HEAD/programs/replace_id.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"38a50154b10bd119"}},{"code_sha256_prefix":"3311f1b80773be4a","entry":"decompose_string","repo":"lilydaytoy/pvsgannotation","repo_kind":"official","path":"programs/replace_id.py","file_url":"https://github.com/lilydaytoy/pvsgannotation/blob/HEAD/programs/replace_id.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3311f1b80773be4a"}},{"code_sha256_prefix":"eeccef779d19f4b8","entry":"get_color_by_luminance","repo":"lilydaytoy/pvsgannotation","repo_kind":"official","path":"programs/generate_rel_chart.py","file_url":"https://github.com/lilydaytoy/pvsgannotation/blob/HEAD/programs/generate_rel_chart.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"eeccef779d19f4b8"}},{"code_sha256_prefix":"ca586d1e88ea819a","entry":"get_video_metadata","repo":"lilydaytoy/pvsgannotation","repo_kind":"official","path":"programs/pvsg_data_parsing.py","file_url":"https://github.com/lilydaytoy/pvsgannotation/blob/HEAD/programs/pvsg_data_parsing.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ca586d1e88ea819a"}},{"code_sha256_prefix":"3d553264c1369157","entry":"get_video_metadata","repo":"lilydaytoy/pvsgannotation","repo_kind":"official","path":"programs/pvsg_vps_parsing.py","file_url":"https://github.com/lilydaytoy/pvsgannotation/blob/HEAD/programs/pvsg_vps_parsing.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3d553264c1369157"}},{"code_sha256_prefix":"a8a7d6ec1d225dd8","entry":"instance_decode","repo":"lilydaytoy/pvsgannotation","repo_kind":"official","path":"programs/pvsg_data_parsing.py","file_url":"https://github.com/lilydaytoy/pvsgannotation/blob/HEAD/programs/pvsg_data_parsing.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a8a7d6ec1d225dd8"}},{"code_sha256_prefix":"b6fdea56d2bc5ad4","entry":"normalize_rgb","repo":"lilydaytoy/pvsgannotation","repo_kind":"official","path":"programs/generate_rel_chart.py","file_url":"https://github.com/lilydaytoy/pvsgannotation/blob/HEAD/programs/generate_rel_chart.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b6fdea56d2bc5ad4"}},{"code_sha256_prefix":"b446b2f8b8d6488b","entry":"overlay","repo":"lilydaytoy/pvsgannotation","repo_kind":"official","path":"programs/img2video_overlay_mask.py","file_url":"https://github.com/lilydaytoy/pvsgannotation/blob/HEAD/programs/img2video_overlay_mask.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b446b2f8b8d6488b"}},{"code_sha256_prefix":"9fc317bb1ed0030e","entry":"preprocess_panoptic_gt_split_th_st","repo":"lilydaytoy/openpvsg","repo_kind":"official","path":"models/mask2former/mask2former_head_split_focal.py","file_url":"https://github.com/lilydaytoy/openpvsg/blob/HEAD/models/mask2former/mask2former_head_split_focal.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9fc317bb1ed0030e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}