{"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/visual-commonsense-r-cnn","title":"Visual Commonsense R-CNN","arxiv_id":"2002.12204","date":"2020-02-27","proceeding":"CVPR 2020 6","authors":["Tan Wang","Jianqiang Huang","Hanwang Zhang","Qianru Sun"],"abstract":"We present a novel unsupervised feature representation learning method, Visual Commonsense Region-based Convolutional Neural Network (VC R-CNN), to serve as an improved visual region encoder for high-level tasks such as captioning and VQA. Given a set of detected object regions in an image (e.g., using Faster R-CNN), like any other unsupervised feature learning methods (e.g., word2vec), the proxy training objective of VC R-CNN is to predict the contextual objects of a region. However, they are fundamentally different: the prediction of VC R-CNN is by using causal intervention: P(Y|do(X)), while others are by using the conventional likelihood: P(Y|X). This is also the core reason why VC R-CNN can learn \"sense-making\" knowledge like chair can be sat -- while not just \"common\" co-occurrences such as chair is likely to exist if table is observed. We extensively apply VC R-CNN features in prevailing models of three popular tasks: Image Captioning, VQA, and VCR, and observe consistent performance boosts across them, achieving many new state-of-the-arts. Code and feature are available at https://github.com/Wangt-CN/VC-R-CNN.","url_abs":"https://arxiv.org/abs/2002.12204v3","url_pdf":"https://arxiv.org/pdf/2002.12204v3.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":"visual-commonsense-r-cnn","repo_url":"https://github.com/Wangt-CN/VC-R-CNN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"image-captioning","task_name":"Image Captioning"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"}],"methods":[{"method_slug":"vc-r-cnn","method_name":"VC R-CNN"}],"datasets_introduced":[],"methods_introduced":[{"slug":"vc-r-cnn","name":"VC R-CNN","full_name":"Visual Commonsense Region-based Convolutional Neural Network"}],"results":[{"leaderboard":"/sota/image-captioning-on-coco-captions","task":"Image Captioning","dataset":"COCO Captions","model":"AoANet + VC","rank_in_archive_order":23,"of":41,"metrics":{"BLEU-4":"39.5","METEOR":"29.3","ROUGE-L":"59.3"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-vqa-v2-test-dev","task":"Visual Question Answering (VQA)","dataset":"VQA v2 test-dev","model":"MCAN+VC","rank_in_archive_order":26,"of":56,"metrics":{"Accuracy":"71.21"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-vqa-v2-test-std","task":"Visual Question Answering (VQA)","dataset":"VQA v2 test-std","model":"MCAN+VC","rank_in_archive_order":23,"of":38,"metrics":{"overall":"71.49"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2002.12204","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.12204"}},"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/Wangt-CN/VC-R-CNN","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1,"unverified":3},"by_repo_kind":{"official":{"samples":4,"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":"c42eaa8eb1b704cd","entry":"sigmoid_focal_loss_cpu","repo":"Wangt-CN/VC-R-CNN","repo_kind":"official","path":"vc_rcnn/layers/sigmoid_focal_loss.py","file_url":"https://github.com/Wangt-CN/VC-R-CNN/blob/HEAD/vc_rcnn/layers/sigmoid_focal_loss.py","link_basis":"harvester_set","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":"c42eaa8eb1b704cd"}},{"code_sha256_prefix":"0a4de8f498e3e70c","entry":"count_bad","repo":"Wangt-CN/VC-R-CNN","repo_kind":"official","path":"downstream/AoANet_VC/eval_utils.py","file_url":"https://github.com/Wangt-CN/VC-R-CNN/blob/HEAD/downstream/AoANet_VC/eval_utils.py","link_basis":"harvester_set","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":"0a4de8f498e3e70c"}},{"code_sha256_prefix":"2902bf4410253ff7","entry":"interpolate","repo":"Wangt-CN/VC-R-CNN","repo_kind":"official","path":"vc_rcnn/layers/misc.py","file_url":"https://github.com/Wangt-CN/VC-R-CNN/blob/HEAD/vc_rcnn/layers/misc.py","link_basis":"harvester_set","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":"2902bf4410253ff7"}},{"code_sha256_prefix":"06b72839dcd7433f","entry":"language_eval","repo":"Wangt-CN/VC-R-CNN","repo_kind":"official","path":"downstream/AoANet_VC/eval_utils.py","file_url":"https://github.com/Wangt-CN/VC-R-CNN/blob/HEAD/downstream/AoANet_VC/eval_utils.py","link_basis":"harvester_set","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":"06b72839dcd7433f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}