{"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/deep-visual-semantic-alignments-for","title":"Deep Visual-Semantic Alignments for Generating Image Descriptions","arxiv_id":"1412.2306","date":"2014-12-07","proceeding":"CVPR 2015 6","authors":["Andrej Karpathy","Li Fei-Fei"],"abstract":"We present a model that generates natural language descriptions of images and\ntheir regions. Our approach leverages datasets of images and their sentence\ndescriptions to learn about the inter-modal correspondences between language\nand visual data. Our alignment model is based on a novel combination of\nConvolutional Neural Networks over image regions, bidirectional Recurrent\nNeural Networks over sentences, and a structured objective that aligns the two\nmodalities through a multimodal embedding. We then describe a Multimodal\nRecurrent Neural Network architecture that uses the inferred alignments to\nlearn to generate novel descriptions of image regions. We demonstrate that our\nalignment model produces state of the art results in retrieval experiments on\nFlickr8K, Flickr30K and MSCOCO datasets. We then show that the generated\ndescriptions significantly outperform retrieval baselines on both full images\nand on a new dataset of region-level annotations.","url_abs":"http://arxiv.org/abs/1412.2306v2","url_pdf":"http://arxiv.org/pdf/1412.2306v2.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":"deep-visual-semantic-alignments-for","repo_url":"https://github.com/IzabelaKrupinska/PROJBAD","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"deep-visual-semantic-alignments-for","repo_url":"https://github.com/Lieberk/Paddle-AoA-Captioning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"paddle","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"deep-visual-semantic-alignments-for","repo_url":"https://github.com/VinitSR7/Image-Caption-Generation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"deep-visual-semantic-alignments-for","repo_url":"https://github.com/souvikshanku/digit-captioning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"cross-modal-retrieval","task_name":"Cross-Modal Retrieval"},{"task_slug":"image-captioning","task_name":"Image Captioning"},{"task_slug":"image-to-text-retrieval","task_name":"Image-to-Text Retrieval"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/cross-modal-retrieval-on-coco-2014","task":"Cross-Modal Retrieval","dataset":"COCO 2014","model":"Dual-Path (ResNet)","rank_in_archive_order":35,"of":36,"metrics":{"Image-to-text R@1":"41.2","Image-to-text R@10":"81.1","Image-to-text R@5":"70.5","Text-to-image R@1":"25.3","Text-to-image R@10":"66.4","Text-to-image R@5":"53.4"},"uses_additional_data":false},{"leaderboard":"/sota/image-captioning-on-flickr30k-captions-test","task":"Image Captioning","dataset":"Flickr30k Captions test","model":"BRNN","rank_in_archive_order":3,"of":7,"metrics":{"BLEU-4":"15.7","CIDEr":"24.7","METEOR":"15.3","SPICE":"-"},"uses_additional_data":false},{"leaderboard":"/sota/image-retrieval-on-flickr30k-1k-test","task":"Image Retrieval","dataset":"Flickr30K 1K test","model":"DVSA (R-CNN, AlexNet)","rank_in_archive_order":18,"of":18,"metrics":{"R@1":"15.2","R@10":"50.5"},"uses_additional_data":false},{"leaderboard":"/sota/image-to-text-retrieval-on-coco","task":"Image-to-Text Retrieval","dataset":"COCO (Common Objects in Context)","model":"DVSA","rank_in_archive_order":9,"of":9,"metrics":{"Recall@10":"74.8"},"uses_additional_data":false},{"leaderboard":"/sota/question-generation-on-coco-visual-question","task":"Question Generation","dataset":"COCO Visual Question Answering (VQA) real images 1.0 open ended","model":"coco-Caption [[Karpathy and Li2014]]","rank_in_archive_order":2,"of":4,"metrics":{"BLEU-1":"62.5"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1412.2306","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1412.2306"}},"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/IzabelaKrupinska/PROJBAD","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/souvikshanku/digit-captioning","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/VinitSR7/Image-Caption-Generation","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Lieberk/Paddle-AoA-Captioning","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":1},"by_repo_kind":{"listed":{"samples":1,"ran":0,"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":"be3ec3d0242fc483","entry":"get_caption","repo":"souvikshanku/digit-captioning","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/souvikshanku/digit-captioning/blob/HEAD/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":"be3ec3d0242fc483"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}