{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/image-to-text/papers/3","list_of":"/task/image-to-text","task":"Image to text","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":3,"pages_in_order":3,"rows_per_page":100,"rows":[201,246],"of":246,"counts":{"archive_papers_tagged":246,"with_a_code_link":103,"where_syntology_ran_a_sample":33,"not_listed_spam_title":0,"listed":246,"listed_where_code_ran":33,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":30,"every_run_a_failure_of_syntologys_instrument":3,"listed_with_a_run_with_no_instrument_failure":30,"listed_every_run_a_failure_of_syntologys_instrument":3,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/image-to-text","prev":"/task/image-to-text/papers/2","next":null,"papers":[{"url":null,"slug":"cobit-a-contrastive-bi-directional-image-text","title":"CoBIT: A Contrastive Bi-directional Image-Text Generation Model","date":"2023-03-23","arxiv_id":"2303.13455","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-table-structure-recognition-with","title":"Improving Table Structure Recognition with Visual-Alignment Sequential Coordinate Modeling","date":"2023-03-13","arxiv_id":"2303.06949","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-end-to-end-neural-network-for-image-to","title":"An End-to-End Neural Network for Image-to-Audio Transformation","date":"2023-03-10","arxiv_id":"2303.06078","repositories_listed":0,"syntology":null},{"url":null,"slug":"clip-rr-improved-clip-network-for-relation","title":"VITR: Augmenting Vision Transformers with Relation-Focused Learning for Cross-Modal Information Retrieval","date":"2023-02-13","arxiv_id":"2302.06350","repositories_listed":0,"syntology":null},{"url":null,"slug":"re-vilm-retrieval-augmented-visual-language","title":"Re-ViLM: Retrieval-Augmented Visual Language Model for Zero and Few-Shot Image Captioning","date":"2023-02-09","arxiv_id":"2302.04858","repositories_listed":0,"syntology":null},{"url":null,"slug":"slan-self-locator-aided-network-for-vision","title":"SLAN: Self-Locator Aided Network for Vision-Language Understanding","date":"2023-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"do-dall-e-and-flamingo-understand-each-other","title":"Do DALL-E and Flamingo Understand Each Other?","date":"2022-12-23","arxiv_id":"2212.12249","repositories_listed":0,"syntology":null},{"url":null,"slug":"when-are-lemons-purple-the-concept","title":"When are Lemons Purple? The Concept Association Bias of Vision-Language Models","date":"2022-12-22","arxiv_id":"2212.12043","repositories_listed":0,"syntology":null},{"url":null,"slug":"slan-self-locator-aided-network-for-cross","title":"SLAN: Self-Locator Aided Network for Cross-Modal Understanding","date":"2022-11-28","arxiv_id":"2211.16208","repositories_listed":0,"syntology":null},{"url":"/paper/retrieval-augmented-multimodal-language","slug":"retrieval-augmented-multimodal-language","title":"Retrieval-Augmented Multimodal Language Modeling","date":"2022-11-22","arxiv_id":"2211.12561","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-by-hallucinating-vision-language-pre","title":"Learning by Hallucinating: Vision-Language Pre-training with Weak Supervision","date":"2022-10-24","arxiv_id":"2210.13591","repositories_listed":0,"syntology":null},{"url":null,"slug":"image-semantic-relation-generation","title":"Image Semantic Relation Generation","date":"2022-10-19","arxiv_id":"2210.11253","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-modal-contrastive-attention-model-for","title":"Cross-modal Contrastive Attention Model for Medical Report Generation","date":"2022-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"every-picture-tells-a-story-image-grounded","title":"Every picture tells a story: Image-grounded controllable stylistic story generation","date":"2022-09-04","arxiv_id":"2209.01638","repositories_listed":0,"syntology":null},{"url":null,"slug":"discovering-bugs-in-vision-models-using-off","title":"Discovering Bugs in Vision Models using Off-the-shelf Image Generation and Captioning","date":"2022-08-18","arxiv_id":"2208.08831","repositories_listed":0,"syntology":null},{"url":null,"slug":"paired-cross-modal-data-augmentation-for-fine","title":"Paired Cross-Modal Data Augmentation for Fine-Grained Image-to-Text Retrieval","date":"2022-07-29","arxiv_id":"2207.14428","repositories_listed":0,"syntology":null},{"url":null,"slug":"srcb-at-semeval-2022-task-5-pretraining-based","title":"SRCB at SemEval-2022 Task 5: Pretraining Based Image to Text Late Sequential Fusion System for Multimodal Misogynous Meme Identification","date":"2022-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"multilingual-image-corpus-towards-a","title":"Multilingual Image Corpus – Towards a Multimodal and Multilingual Dataset","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"uncertainty-based-cross-modal-retrieval-with","title":"Uncertainty-based Cross-Modal Retrieval with Probabilistic Representations","date":"2022-04-20","arxiv_id":"2204.09268","repositories_listed":0,"syntology":null},{"url":"/paper/cots-collaborative-two-stream-vision-language","slug":"cots-collaborative-two-stream-vision-language","title":"COTS: Collaborative Two-Stream Vision-Language Pre-Training Model for Cross-Modal Retrieval","date":"2022-04-15","arxiv_id":"2204.07441","repositories_listed":0,"syntology":null},{"url":null,"slug":"two-stream-hierarchical-similarity-reasoning","title":"Two-stream Hierarchical Similarity Reasoning for Image-text Matching","date":"2022-03-10","arxiv_id":"2203.05349","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-thousand-words-are-worth-more-than-a","title":"A Thousand Words Are Worth More Than a Picture: Natural Language-Centric Outside-Knowledge Visual Question Answering","date":"2022-01-14","arxiv_id":"2201.05299","repositories_listed":0,"syntology":null},{"url":null,"slug":"ei-clip-entity-aware-interventional","title":"EI-CLIP: Entity-Aware Interventional Contrastive Learning for E-Commerce Cross-Modal Retrieval","date":"2022-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/transform-retrieve-generate-natural-language","slug":"transform-retrieve-generate-natural-language","title":"Transform-Retrieve-Generate: Natural Language-Centric Outside-Knowledge Visual Question Answering","date":"2022-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"utilizing-resource-rich-language-datasets-for","title":"Utilizing Resource-Rich Language Datasets for End-to-End Scene Text Recognition in Resource-Poor Languages","date":"2021-11-24","arxiv_id":"2111.12276","repositories_listed":0,"syntology":null},{"url":null,"slug":"contrastive-learning-of-visual-semantic","title":"Contrastive Learning of Visual-Semantic Embeddings","date":"2021-10-17","arxiv_id":"2110.08872","repositories_listed":0,"syntology":null},{"url":null,"slug":"survey-of-visual-semantic-embedding-methods","title":"Survey of Visual-Semantic Embedding Methods for Zero-Shot Image Retrieval","date":"2021-05-16","arxiv_id":"2105.07391","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-driven-description-synthesis-for","title":"Knowledge driven Description Synthesis for Floor Plan Interpretation","date":"2021-03-15","arxiv_id":"2103.08298","repositories_listed":0,"syntology":null},{"url":"/paper/hierarchical-gumbel-attention-network-for","slug":"hierarchical-gumbel-attention-network-for","title":"Hierarchical Gumbel Attention Network for Text-based Person Search","date":"2020-10-10","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-modal-alignment-with-mixture-experts","title":"Cross-Modal Alignment with Mixture Experts Neural Network for Intral-City Retail Recommendation","date":"2020-09-17","arxiv_id":"2009.09926","repositories_listed":0,"syntology":null},{"url":null,"slug":"development-of-a-new-image-to-text-conversion","title":"Development of a New Image-to-text Conversion System for Pashto, Farsi and Traditional Chinese","date":"2020-05-08","arxiv_id":"2005.08650","repositories_listed":0,"syntology":null},{"url":null,"slug":"multimodal-intelligence-representation","title":"Multimodal Intelligence: Representation Learning, Information Fusion, and Applications","date":"2019-11-10","arxiv_id":"1911.03977","repositories_listed":0,"syntology":null},{"url":null,"slug":"illegible-text-to-readable-text-an-image-to","title":"Illegible Text to Readable Text: An Image-to-Image Transformation using Conditional Sliced Wasserstein Adversarial Networks","date":"2019-10-11","arxiv_id":"1910.05425","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-image-to-text-in-sentiment-analysis-via","title":"From Image to Text in Sentiment Analysis via Regression and Deep Learning","date":"2019-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-aware-semantic-concept-expansion","title":"Knowledge Aware Semantic Concept Expansion for Image-Text Matching","date":"2019-08-10","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"canonical-correlation-analysis-for-misaligned","title":"Canonical Correlation Analysis for Misaligned Satellite Image Change Detection","date":"2018-12-21","arxiv_id":"1812.09280","repositories_listed":0,"syntology":null},{"url":null,"slug":"doc2im-document-to-image-conversion-through","title":"Doc2Im: document to image conversion through self-attentive embedding","date":"2018-11-08","arxiv_id":"1811.03291","repositories_listed":0,"syntology":null},{"url":null,"slug":"emojigan-learning-emojis-distributions-with-a","title":"EmojiGAN: learning emojis distributions with a generative model","date":"2018-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"deductron-a-recurrent-neural-network","title":"Deductron -- A Recurrent Neural Network","date":"2018-06-23","arxiv_id":"1806.09038","repositories_listed":0,"syntology":null},{"url":null,"slug":"using-inter-sentence-diverse-beam-search-to","title":"Using Inter-Sentence Diverse Beam Search to Reduce Redundancy in Visual Storytelling","date":"2018-05-30","arxiv_id":"1805.11867","repositories_listed":0,"syntology":null},{"url":null,"slug":"turbo-learning-for-captionbot-and-drawingbot","title":"Turbo Learning for Captionbot and Drawingbot","date":"2018-05-21","arxiv_id":"1805.08170","repositories_listed":0,"syntology":null},{"url":null,"slug":"synthesizing-novel-pairs-of-image-and-text","title":"Synthesizing Novel Pairs of Image and Text","date":"2017-12-18","arxiv_id":"1712.06682","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-image-to-text-classification-a-novel","title":"From Image to Text Classification: A Novel Approach based on Clustering Word Embeddings","date":"2017-07-25","arxiv_id":"1707.08098","repositories_listed":0,"syntology":null},{"url":null,"slug":"better-text-understanding-through-image-to","title":"Better Text Understanding Through Image-To-Text Transfer","date":"2017-05-23","arxiv_id":"1705.08386","repositories_listed":0,"syntology":null},{"url":null,"slug":"i2t2i-learning-text-to-image-synthesis-with","title":"I2T2I: Learning Text to Image Synthesis with Textual Data Augmentation","date":"2017-03-20","arxiv_id":"1703.06676","repositories_listed":0,"syntology":null},{"url":"/paper/learning-deep-structure-preserving-image-text","slug":"learning-deep-structure-preserving-image-text","title":"Learning Deep Structure-Preserving Image-Text Embeddings","date":"2015-11-19","arxiv_id":"1511.06078","repositories_listed":0,"syntology":null}],"record_sha256":"22818ca8835b8e9e4c43980225c336c04eaf15bb1aeaf861811dd40d244caf8a","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}