{"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/multiple-object-recognition-with-visual","title":"Multiple Object Recognition with Visual Attention","arxiv_id":"1412.7755","date":"2014-12-24","proceeding":null,"authors":["Jimmy Ba","Volodymyr Mnih","Koray Kavukcuoglu"],"abstract":"We present an attention-based model for recognizing multiple objects in\nimages. The proposed model is a deep recurrent neural network trained with\nreinforcement learning to attend to the most relevant regions of the input\nimage. We show that the model learns to both localize and recognize multiple\nobjects despite being given only class labels during training. We evaluate the\nmodel on the challenging task of transcribing house number sequences from\nGoogle Street View images and show that it is both more accurate than the\nstate-of-the-art convolutional networks and uses fewer parameters and less\ncomputation.","url_abs":"http://arxiv.org/abs/1412.7755v2","url_pdf":"http://arxiv.org/pdf/1412.7755v2.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":"multiple-object-recognition-with-visual","repo_url":"https://github.com/Sooram/cnn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"multiple-object-recognition-with-visual","repo_url":"https://github.com/Sooram/stn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"multiple-object-recognition-with-visual","repo_url":"https://github.com/amobiny/Recurrent_Attention_Model","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"multiple-object-recognition-with-visual","repo_url":"https://github.com/mimikaan/Attention-Model","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"multiple-object-recognition-with-visual","repo_url":"https://github.com/tianyu-tristan/Visual-Attention-Model","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"object-recognition","task_name":"Object Recognition"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1412.7755","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1412.7755"}},"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/amobiny/Recurrent_Attention_Model","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Sooram/cnn","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tianyu-tristan/Visual-Attention-Model","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mimikaan/Attention-Model","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Sooram/stn","reach":{"status":"ok"}}],"summary":{"ran_honours":3},"by_repo_kind":{},"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":"dfdf1a70103e043b","entry":"mask_labels","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"dfdf1a70103e043b"}},{"code_sha256_prefix":"ee60170e008f8124","entry":"repair_labels","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"ee60170e008f8124"}},{"code_sha256_prefix":"58d0f0ae48e3212e","entry":"truncate_labels","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"58d0f0ae48e3212e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}