{"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/end-to-end-3d-dense-captioning-with-vote2cap","title":"End-to-End 3D Dense Captioning with Vote2Cap-DETR","arxiv_id":"2301.02508","date":"2023-01-06","proceeding":"CVPR 2023 1","authors":["Sijin Chen","Hongyuan Zhu","Xin Chen","Yinjie Lei","Tao Chen","Gang Yu"],"abstract":"3D dense captioning aims to generate multiple captions localized with their associated object regions. Existing methods follow a sophisticated ``detect-then-describe'' pipeline equipped with numerous hand-crafted components. However, these hand-crafted components would yield suboptimal performance given cluttered object spatial and class distributions among different scenes. In this paper, we propose a simple-yet-effective transformer framework Vote2Cap-DETR based on recent popular \\textbf{DE}tection \\textbf{TR}ansformer (DETR). Compared with prior arts, our framework has several appealing advantages: 1) Without resorting to numerous hand-crafted components, our method is based on a full transformer encoder-decoder architecture with a learnable vote query driven object decoder, and a caption decoder that produces the dense captions in a set-prediction manner. 2) In contrast to the two-stage scheme, our method can perform detection and captioning in one-stage. 3) Without bells and whistles, extensive experiments on two commonly used datasets, ScanRefer and Nr3D, demonstrate that our Vote2Cap-DETR surpasses current state-of-the-arts by 11.13\\% and 7.11\\% in CIDEr@0.5IoU, respectively. Codes will be released soon.","url_abs":"https://arxiv.org/abs/2301.02508v1","url_pdf":"https://arxiv.org/pdf/2301.02508v1.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":"end-to-end-3d-dense-captioning-with-vote2cap","repo_url":"https://github.com/ch3cook-fdu/vote2cap-detr","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"3d-dense-captioning","task_name":"3D dense captioning"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"dense-captioning","task_name":"Dense Captioning"},{"task_slug":"object","task_name":"Object"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-dense-captioning-on-nr3d","task":"3D dense captioning","dataset":"Nr3D","model":"Vote2Cap-DETR","rank_in_archive_order":4,"of":10,"metrics":{"BLEU-4":"26.68","CIDEr":"43.84","METEOR":"25.41","ROUGE-L":"54.43"},"uses_additional_data":false},{"leaderboard":"/sota/3d-dense-captioning-on-scanrefer-dataset","task":"3D dense captioning","dataset":"ScanRefer Dataset","model":"Vote2Cap-DETR","rank_in_archive_order":5,"of":12,"metrics":{"BLEU-4":"39.34","CIDEr":"71.45","METEOR":"28.25","ROUGE-L":"59.33"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2301.02508","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.02508"}},"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/ch3cook-fdu/vote2cap-detr","reach":null}],"summary":{"ran":1,"unverified":2},"by_repo_kind":{"official":{"samples":3,"ran":1,"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":"aadf68d34d59b540","entry":"PositionEmbeddingCoordsSine","repo":"ch3cook-fdu/vote2cap-detr","repo_kind":"official","path":"models/detector_Vote2Cap_DETR/detector.py","file_url":"https://github.com/ch3cook-fdu/vote2cap-detr/blob/HEAD/models/detector_Vote2Cap_DETR/detector.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":"aadf68d34d59b540"}},{"code_sha256_prefix":"0a88800a8a15a51f","entry":"Model_Vote2Cap_DETR","repo":"ch3cook-fdu/vote2cap-detr","repo_kind":"official","path":"models/detector_Vote2Cap_DETR/detector.py","file_url":"https://github.com/ch3cook-fdu/vote2cap-detr/blob/HEAD/models/detector_Vote2Cap_DETR/detector.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":"0a88800a8a15a51f"}},{"code_sha256_prefix":"86a9d885435719dc","entry":"VoteQuery","repo":"ch3cook-fdu/vote2cap-detr","repo_kind":"official","path":"models/detector_Vote2Cap_DETR/detector.py","file_url":"https://github.com/ch3cook-fdu/vote2cap-detr/blob/HEAD/models/detector_Vote2Cap_DETR/detector.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":"86a9d885435719dc"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}