{"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-captioning/papers/19","list_of":"/task/image-captioning","task":"Image Captioning","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":19,"pages_in_order":19,"rows_per_page":100,"rows":[1801,1878],"of":1878,"counts":{"archive_papers_tagged":1878,"with_a_code_link":774,"where_syntology_ran_a_sample":243,"not_listed_spam_title":0,"listed":1878,"listed_where_code_ran":243,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":201,"every_run_a_failure_of_syntologys_instrument":42,"listed_with_a_run_with_no_instrument_failure":201,"listed_every_run_a_failure_of_syntologys_instrument":42,"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-captioning","prev":"/task/image-captioning/papers/18","next":null,"papers":[{"url":null,"slug":"vip-cnn-visual-phrase-guided-convolutional","title":"ViP-CNN: Visual Phrase Guided Convolutional Neural Network","date":"2017-02-23","arxiv_id":"1702.07191","repositories_listed":0,"syntology":null},{"url":null,"slug":"mat-a-multimodal-attentive-translator-for","title":"MAT: A Multimodal Attentive Translator for Image Captioning","date":"2017-02-18","arxiv_id":"1702.05658","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-network-guided-proof-search","title":"Deep Network Guided Proof Search","date":"2017-01-24","arxiv_id":"1701.06972","repositories_listed":0,"syntology":null},{"url":null,"slug":"vision-and-language-integration-moving-beyond","title":"Vision and Language Integration: Moving beyond Objects","date":"2017-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"re-evaluating-automatic-metrics-for-image","title":"Re-evaluating Automatic Metrics for Image Captioning","date":"2016-12-22","arxiv_id":"1612.07600","repositories_listed":0,"syntology":null},{"url":"/paper/understanding-image-and-text-simultaneously-a","slug":"understanding-image-and-text-simultaneously-a","title":"Understanding Image and Text Simultaneously: a Dual Vision-Language Machine Comprehension Task","date":"2016-12-22","arxiv_id":"1612.07833","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-holistic-object-recognition-enriching","title":"Beyond Holistic Object Recognition: Enriching Image Understanding with Part States","date":"2016-12-15","arxiv_id":"1612.07310","repositories_listed":0,"syntology":null},{"url":null,"slug":"recurrent-image-captioner-describing-images","title":"Recurrent Image Captioner: Describing Images with Spatial-Invariant Transformation and Attention Filtering","date":"2016-12-15","arxiv_id":"1612.04949","repositories_listed":0,"syntology":null},{"url":null,"slug":"spatial-pyramid-convolutional-neural-network","title":"Spatial Pyramid Convolutional Neural Network for Social Event Detection in Static Image","date":"2016-12-13","arxiv_id":"1612.04062","repositories_listed":0,"syntology":null},{"url":null,"slug":"areas-of-attention-for-image-captioning","title":"Areas of Attention for Image Captioning","date":"2016-12-03","arxiv_id":"1612.01033","repositories_listed":0,"syntology":null},{"url":null,"slug":"video-event-detection-by-exploiting-word","title":"Video Event Detection by Exploiting Word Dependencies from Image Captions","date":"2016-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"on-human-intellect-and-machine-failures","title":"On Human Intellect and Machine Failures: Troubleshooting Integrative Machine Learning Systems","date":"2016-11-24","arxiv_id":"1611.08309","repositories_listed":0,"syntology":null},{"url":null,"slug":"semantic-regularisation-for-recurrent-image","title":"Semantic Regularisation for Recurrent Image Annotation","date":"2016-11-16","arxiv_id":"1611.05490","repositories_listed":0,"syntology":null},{"url":null,"slug":"boosting-image-captioning-with-attributes","title":"Boosting Image Captioning with Attributes","date":"2016-11-05","arxiv_id":"1611.01646","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-headline-generation-on-abstract","title":"Neural Headline Generation on Abstract Meaning Representation","date":"2016-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"generating-captions-without-looking-beyond","title":"Generating captions without looking beyond objects","date":"2016-10-12","arxiv_id":"1610.03708","repositories_listed":0,"syntology":null},{"url":null,"slug":"effect-of-data-annotation-feature-selection","title":"Effect of Data Annotation, Feature Selection and Model Choice on Spatial Description Generation in French","date":"2016-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"sketch-to-text-generation-toward-contextual","title":"Sketch-to-Text Generation: Toward Contextual, Creative, and Coherent Composition","date":"2016-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"measuring-machine-intelligence-through-visual","title":"Measuring Machine Intelligence Through Visual Question Answering","date":"2016-08-31","arxiv_id":"1608.08716","repositories_listed":0,"syntology":null},{"url":null,"slug":"utilizing-large-scale-vision-and-text","title":"Utilizing Large Scale Vision and Text Datasets for Image Segmentation from Referring Expressions","date":"2016-08-30","arxiv_id":"1608.08305","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-generalize-to-new-compositions-in","title":"Learning to generalize to new compositions in image understanding","date":"2016-08-27","arxiv_id":"1608.07639","repositories_listed":0,"syntology":null},{"url":null,"slug":"phi-lstm-a-phrase-based-hierarchical-lstm","title":"phi-LSTM: A Phrase-based Hierarchical LSTM Model for Image Captioning","date":"2016-08-20","arxiv_id":"1608.05813","repositories_listed":0,"syntology":null},{"url":null,"slug":"seeing-with-humans-gaze-assisted-neural-image","title":"Seeing with Humans: Gaze-Assisted Neural Image Captioning","date":"2016-08-18","arxiv_id":"1608.05203","repositories_listed":0,"syntology":null},{"url":null,"slug":"attention-based-multimodal-neural-machine","title":"Attention-based Multimodal Neural Machine Translation","date":"2016-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-lingual-image-caption-generation","title":"Cross-Lingual Image Caption Generation","date":"2016-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"focused-evaluation-for-image-description-with","title":"Focused Evaluation for Image Description with Binary Forced-Choice Tasks","date":"2016-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"generating-natural-language-descriptions-for","title":"Generating Natural Language Descriptions for Semantic Representations of Human Brain Activity","date":"2016-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"improved-semantic-parsers-for-if-then","title":"Improved Semantic Parsers For If-Then Statements","date":"2016-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"mutt-metric-unit-testing-for-language","title":"MUTT: Metric Unit TesTing for Language Generation Tasks","date":"2016-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"wmt-2016-multimodal-translation-system","title":"WMT 2016 Multimodal Translation System Description based on Bidirectional Recurrent Neural Networks with Double-Embeddings","date":"2016-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"automated-image-captioning-for-rapid","title":"Automated Image Captioning for Rapid Prototyping and Resource Constrained Environments","date":"2016-06-04","arxiv_id":"1606.01393","repositories_listed":0,"syntology":null},{"url":null,"slug":"fbk-hlt-nlp-at-semeval-2016-task-2-a","title":"FBK-HLT-NLP at SemEval-2016 Task 2: A Multitask, Deep Learning Approach for Interpretable Semantic Textual Similarity","date":"2016-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"incorporating-side-information-into-recurrent","title":"Incorporating Side Information into Recurrent Neural Network Language Models","date":"2016-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/msr-vtt-a-large-video-description-dataset-for","slug":"msr-vtt-a-large-video-description-dataset-for","title":"MSR-VTT: A Large Video Description Dataset for Bridging Video and Language","date":"2016-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"semeval-2016-task-2-interpretable-semantic","title":"SemEval-2016 Task 2: Interpretable Semantic Textual Similarity","date":"2016-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"attention-correctness-in-neural-image","title":"Attention Correctness in Neural Image Captioning","date":"2016-05-31","arxiv_id":"1605.09553","repositories_listed":0,"syntology":null},{"url":null,"slug":"review-networks-for-caption-generation","title":"Review Networks for Caption Generation","date":"2016-05-25","arxiv_id":"1605.07912","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-caption-to-narrative-video-captioning","title":"Beyond Caption To Narrative: Video Captioning With Multiple Sentences","date":"2016-05-18","arxiv_id":"1605.05440","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-image-captioning-by-concept-based","title":"Improving Image Captioning by Concept-based Sentence Reranking","date":"2016-05-03","arxiv_id":"1605.00855","repositories_listed":0,"syntology":null},{"url":null,"slug":"1-million-captioned-dutch-newspaper-images","title":"1 Million Captioned Dutch Newspaper Images","date":"2016-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"scan-attend-and-read-end-to-end-handwritten","title":"Scan, Attend and Read: End-to-End Handwritten Paragraph Recognition with MDLSTM Attention","date":"2016-04-12","arxiv_id":"1604.03286","repositories_listed":0,"syntology":null},{"url":null,"slug":"dense-image-representation-with-spatial","title":"Dense Image Representation with Spatial Pyramid VLAD Coding of CNN for Locally Robust Captioning","date":"2016-03-30","arxiv_id":"1603.09046","repositories_listed":0,"syntology":null},{"url":null,"slug":"rich-image-captioning-in-the-wild","title":"Rich Image Captioning in the Wild","date":"2016-03-30","arxiv_id":"1603.09016","repositories_listed":0,"syntology":null},{"url":null,"slug":"image-captioning-with-semantic-attention","title":"Image Captioning with Semantic Attention","date":"2016-03-12","arxiv_id":"1603.03925","repositories_listed":0,"syntology":null},{"url":"/paper/image-captioning-and-visual-question","slug":"image-captioning-and-visual-question","title":"Image Captioning and Visual Question Answering Based on Attributes and External Knowledge","date":"2016-03-09","arxiv_id":"1603.02814","repositories_listed":0,"syntology":null},{"url":null,"slug":"implicit-distortion-and-fertility-models-for","title":"Implicit Distortion and Fertility Models for Attention-based Encoder-Decoder NMT Model","date":"2016-01-13","arxiv_id":"1601.03317","repositories_listed":0,"syntology":null},{"url":null,"slug":"event-specific-multimodal-pattern-mining-with","title":"Event Specific Multimodal Pattern Mining with Image-Caption Pairs","date":"2015-12-31","arxiv_id":"1601.00022","repositories_listed":0,"syntology":null},{"url":null,"slug":"seeing-through-the-human-reporting-bias","title":"Seeing through the Human Reporting Bias: Visual Classifiers from Noisy Human-Centric Labels","date":"2015-12-22","arxiv_id":"1512.06974","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-mathematical-theory-of-deep-convolutional","title":"A Mathematical Theory of Deep Convolutional Neural Networks for Feature Extraction","date":"2015-12-19","arxiv_id":"1512.06293","repositories_listed":0,"syntology":null},{"url":null,"slug":"mapping-images-to-sentiment-adjective-noun","title":"Mapping Images to Sentiment Adjective Noun Pairs with Factorized Neural Nets","date":"2015-11-21","arxiv_id":"1511.06838","repositories_listed":0,"syntology":null},{"url":"/paper/senticap-generating-image-descriptions-with","slug":"senticap-generating-image-descriptions-with","title":"SentiCap: Generating Image Descriptions with Sentiments","date":"2015-10-06","arxiv_id":"1510.01431","repositories_listed":0,"syntology":null},{"url":null,"slug":"defining-visually-descriptive-language","title":"Defining Visually Descriptive Language","date":"2015-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"semantic-tuples-for-evaluation-of-image-to","title":"Semantic Tuples for Evaluation of Image to Sentence Generation","date":"2015-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"visual-classifier-prediction-by","title":"Visual Classifier Prediction by Distributional Semantic Embedding of Text Descriptions","date":"2015-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"image-representations-and-new-domains-in","title":"Image Representations and New Domains in Neural Image Captioning","date":"2015-08-09","arxiv_id":"1508.02091","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-distributed-representation-based-query","title":"A Distributed Representation Based Query Expansion Approach for Image Captioning","date":"2015-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"technical-report-image-captioning-with","title":"Technical Report: Image Captioning with Semantically Similar Images","date":"2015-06-12","arxiv_id":"1506.03995","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-long-short-story-of-movie-description","title":"The Long-Short Story of Movie Description","date":"2015-06-04","arxiv_id":"1506.01698","repositories_listed":0,"syntology":null},{"url":null,"slug":"azmat-sentence-similarity-using-associative","title":"AZMAT: Sentence Similarity Using Associative Matrices","date":"2015-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-topic-modeling-for-short-texts","title":"Unsupervised Topic Modeling for Short Texts Using Distributed Representations of Words","date":"2015-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"sequence-to-sequence-neural-net-models-for","title":"Sequence-to-Sequence Neural Net Models for Grapheme-to-Phoneme Conversion","date":"2015-05-31","arxiv_id":"1506.00196","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-models-for-image-captioning-the","title":"Language Models for Image Captioning: The Quirks and What Works","date":"2015-05-07","arxiv_id":"1505.01809","repositories_listed":0,"syntology":null},{"url":null,"slug":"deja-image-captions-a-corpus-of-expressive","title":"Déjà Image-Captions: A Corpus of Expressive Descriptions in Repetition","date":"2015-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"phrase-based-image-captioning","title":"Phrase-based Image Captioning","date":"2015-02-12","arxiv_id":"1502.03671","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-layered-image-representation-for-image","title":"Multi-layered Image Representation for Image Interpretation","date":"2014-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-succinct-and-relevant-image","title":"Towards Succinct and Relevant Image Descriptions","date":"2014-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"domain-specific-image-captioning","title":"Domain-Specific Image Captioning","date":"2014-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"nonparametric-method-for-data-driven-image","title":"Nonparametric Method for Data-driven Image Captioning","date":"2014-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"image-annotation-with-iso-space","title":"Image Annotation with ISO-Space: Distinguishing Content from Structure","date":"2014-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"treetalk-composition-and-compression-of-trees","title":"TreeTalk: Composition and Compression of Trees for Image Descriptions","date":"2014-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"generalizing-image-captions-for-image-text","title":"Generalizing Image Captions for Image-Text Parallel Corpus","date":"2013-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"annotation-of-online-shopping-images-without","title":"Annotation of Online Shopping Images without Labeled Training Examples","date":"2013-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"domain-independent-captioning-of-domain","title":"Domain-Independent Captioning of Domain-Specific Images","date":"2013-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"takelab-systems-for-measuring-semantic-text","title":"TakeLab: Systems for Measuring Semantic Text Similarity","date":"2012-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-disambiguation-of-image-captions","title":"Unsupervised Disambiguation of Image Captions","date":"2012-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"correlation-between-similarity-measures-for","title":"Correlation between Similarity Measures for Inter-Language Linked Wikipedia Articles","date":"2012-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"ttt-a-tree-transduction-language-for","title":"TTT: A Tree Transduction Language for Syntactic and Semantic Processing","date":"2012-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/im2text-describing-images-using-1-million","slug":"im2text-describing-images-using-1-million","title":"Im2Text: Describing Images Using 1 Million Captioned Photographs","date":"2011-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"record_sha256":"0c46a24697016b61846455f7d3c8a454cc12db0e45969b93d0672df88904c58a","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}