{"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/7","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":7,"pages_in_order":19,"rows_per_page":100,"rows":[601,700],"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/6","next":"/task/image-captioning/papers/8","papers":[{"url":"/paper/image-caption-generation-for-news-articles","slug":"image-caption-generation-for-news-articles","title":"Image Caption Generation for News Articles","date":"2020-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/language-driven-region-pointer-advancement","slug":"language-driven-region-pointer-advancement","title":"Language-Driven Region Pointer Advancement for Controllable Image Captioning","date":"2020-11-30","arxiv_id":"2011.14901","repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-learning-for-hateful-memes","slug":"multimodal-learning-for-hateful-memes","title":"Multimodal Learning for Hateful Memes Detection","date":"2020-11-25","arxiv_id":"2011.12870","repositories_listed":1,"syntology":null},{"url":"/paper/capwap-captioning-with-a-purpose","slug":"capwap-captioning-with-a-purpose","title":"CapWAP: Captioning with a Purpose","date":"2020-11-09","arxiv_id":"2011.04264","repositories_listed":1,"syntology":null},{"url":"/paper/generating-image-descriptions-via-sequential","slug":"generating-image-descriptions-via-sequential","title":"Generating Image Descriptions via Sequential Cross-Modal Alignment Guided by Human Gaze","date":"2020-11-09","arxiv_id":"2011.04592","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/generating-image-descriptions-via-sequential#ran","syntology_url":"https://syntology.ai/paper/2011.04592","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.04592"}},"official":{"repos":["dmg-illc/didec-seq-gen"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/diverse-image-captioning-with-context-object","slug":"diverse-image-captioning-with-context-object","title":"Diverse Image Captioning with Context-Object Split Latent Spaces","date":"2020-11-02","arxiv_id":"2011.00966","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":1,"n_ran_checked":1,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/diverse-image-captioning-with-context-object#ran","syntology_url":"https://syntology.ai/paper/2011.00966","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.00966"}},"official":{"repos":["visinf/cos-cvae"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/vilbertscore-evaluating-image-caption-using","slug":"vilbertscore-evaluating-image-caption-using","title":"ViLBERTScore: Evaluating Image Caption Using Vision-and-Language BERT","date":"2020-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/a-caption-is-worth-a-thousand-images","slug":"a-caption-is-worth-a-thousand-images","title":"Can images help recognize entities? A study of the role of images for Multimodal NER","date":"2020-10-23","arxiv_id":"2010.12712","repositories_listed":1,"syntology":null},{"url":"/paper/wavetransformer-a-novel-architecture-for","slug":"wavetransformer-a-novel-architecture-for","title":"WaveTransformer: A Novel Architecture for Audio Captioning Based on Learning Temporal and Time-Frequency Information","date":"2020-10-21","arxiv_id":"2010.11098","repositories_listed":1,"syntology":null},{"url":"/paper/bayesian-attention-modules","slug":"bayesian-attention-modules","title":"Bayesian Attention Modules","date":"2020-10-20","arxiv_id":"2010.10604","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/bayesian-attention-modules#ran","syntology_url":"https://syntology.ai/paper/2010.10604","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.10604"}},"official":{"repos":["zhougroup/BAM"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/vokenization-improving-language-understanding","slug":"vokenization-improving-language-understanding","title":"Vokenization: Improving Language Understanding with Contextualized, Visual-Grounded Supervision","date":"2020-10-14","arxiv_id":"2010.06775","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/vokenization-improving-language-understanding#ran","syntology_url":"https://syntology.ai/paper/2010.06775","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.06775"}},"official":{"repos":["airsplay/vokenization"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/dense-relational-image-captioning-via-multi","slug":"dense-relational-image-captioning-via-multi","title":"Dense Relational Image Captioning via Multi-task Triple-Stream Networks","date":"2020-10-08","arxiv_id":"2010.03855","repositories_listed":1,"syntology":null},{"url":"/paper/visualnews-a-large-multi-source-news-image","slug":"visualnews-a-large-multi-source-news-image","title":"Visual News: Benchmark and Challenges in News Image Captioning","date":"2020-10-08","arxiv_id":"2010.03743","repositories_listed":1,"syntology":null},{"url":"/paper/pix2prof-fast-extraction-of-sequential","slug":"pix2prof-fast-extraction-of-sequential","title":"Pix2Prof: fast extraction of sequential information from galaxy imagery via a deep natural language 'captioning' model","date":"2020-10-01","arxiv_id":"2010.00622","repositories_listed":1,"syntology":null},{"url":"/paper/neural-twins-talk","slug":"neural-twins-talk","title":"Neural Twins Talk","date":"2020-09-26","arxiv_id":"2009.12524","repositories_listed":1,"syntology":null},{"url":"/paper/are-scene-graphs-good-enough-to-improve-image","slug":"are-scene-graphs-good-enough-to-improve-image","title":"Are scene graphs good enough to improve Image Captioning?","date":"2020-09-25","arxiv_id":"2009.12313","repositories_listed":1,"syntology":null},{"url":"/paper/image-captioning-with-attention-for-smart","slug":"image-captioning-with-attention-for-smart","title":"Image Captioning with Attention for Smart Local Tourism using EfficientNet","date":"2020-09-18","arxiv_id":"2009.08899","repositories_listed":1,"syntology":null},{"url":"/paper/towards-unique-and-informative-captioning-of-1","slug":"towards-unique-and-informative-captioning-of-1","title":"Towards Unique and Informative Captioning of Images","date":"2020-09-08","arxiv_id":"2009.03949","repositories_listed":1,"syntology":null},{"url":"/paper/structure-aware-generation-network-for-recipe","slug":"structure-aware-generation-network-for-recipe","title":"Structure-Aware Generation Network for Recipe Generation from Images","date":"2020-09-02","arxiv_id":"2009.00944","repositories_listed":1,"syntology":null},{"url":"/paper/protect-show-attend-and-tell-image-captioning","slug":"protect-show-attend-and-tell-image-captioning","title":"Protect, Show, Attend and Tell: Empowering Image Captioning Models with Ownership Protection","date":"2020-08-25","arxiv_id":"2008.11009","repositories_listed":1,"syntology":null},{"url":"/paper/text-as-neural-operator-image-manipulation-by","slug":"text-as-neural-operator-image-manipulation-by","title":"Text as Neural Operator: Image Manipulation by Text Instruction","date":"2020-08-11","arxiv_id":"2008.04556","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/text-as-neural-operator-image-manipulation-by#ran","syntology_url":"https://syntology.ai/paper/2008.04556","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.04556"}},"official":{"repos":["google/tim-gan"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/describe-what-to-change-a-text-guided","slug":"describe-what-to-change-a-text-guided","title":"Describe What to Change: A Text-guided Unsupervised Image-to-Image Translation Approach","date":"2020-08-10","arxiv_id":"2008.04200","repositories_listed":1,"syntology":null},{"url":"/paper/textual-description-for-mathematical","slug":"textual-description-for-mathematical","title":"Textual Description for Mathematical Equations","date":"2020-08-07","arxiv_id":"2008.02980","repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-generate-grounded-visual-captions","slug":"learning-to-generate-grounded-visual-captions","title":"Learning to Generate Grounded Visual Captions without Localization Supervision","date":"2020-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/recurrent-image-annotation-with-explicit","slug":"recurrent-image-annotation-with-explicit","title":"Recurrent Image Annotation With Explicit Inter-Label Dependencies","date":"2020-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/comprehensive-image-captioning-via-scene","slug":"comprehensive-image-captioning-via-scene","title":"Comprehensive Image Captioning via Scene Graph Decomposition","date":"2020-07-23","arxiv_id":"2007.11731","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/comprehensive-image-captioning-via-scene#ran","syntology_url":"https://syntology.ai/paper/2007.11731","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.11731"}},"official":null}},{"url":"/paper/fine-grained-image-captioning-with-global","slug":"fine-grained-image-captioning-with-global","title":"Fine-Grained Image Captioning with Global-Local Discriminative Objective","date":"2020-07-21","arxiv_id":"2007.10662","repositories_listed":1,"syntology":null},{"url":"/paper/length-controllable-image-captioning","slug":"length-controllable-image-captioning","title":"Length-Controllable Image Captioning","date":"2020-07-19","arxiv_id":"2007.09580","repositories_listed":1,"syntology":null},{"url":"/paper/consensus-aware-visual-semantic-embedding-for","slug":"consensus-aware-visual-semantic-embedding-for","title":"Consensus-Aware Visual-Semantic Embedding for Image-Text Matching","date":"2020-07-17","arxiv_id":"2007.08883","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/consensus-aware-visual-semantic-embedding-for#ran","syntology_url":"https://syntology.ai/paper/2007.08883","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.08883"}},"official":{"repos":["BruceW91/CVSE"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/evaluating-and-interpreting-caption","slug":"evaluating-and-interpreting-caption","title":"Evaluating and interpreting caption prediction for histopathology images","date":"2020-07-08","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/diverse-and-styled-image-captioning-using-svd","slug":"diverse-and-styled-image-captioning-using-svd","title":"Diverse and Styled Image Captioning Using SVD-Based Mixture of Recurrent Experts","date":"2020-07-07","arxiv_id":"2007.03338","repositories_listed":1,"syntology":null},{"url":"/paper/edsl-an-encoder-decoder-architecture-with","slug":"edsl-an-encoder-decoder-architecture-with","title":"EDSL: An Encoder-Decoder Architecture with Symbol-Level Features for Printed Mathematical Expression Recognition","date":"2020-07-06","arxiv_id":"2007.02517","repositories_listed":1,"syntology":null},{"url":"/paper/graph-optimal-transport-for-cross-domain","slug":"graph-optimal-transport-for-cross-domain","title":"Graph Optimal Transport for Cross-Domain Alignment","date":"2020-06-26","arxiv_id":"2006.14744","repositories_listed":1,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":2,"n_no_contract":6,"n_pointer_only":3,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 2 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/graph-optimal-transport-for-cross-domain#ran","syntology_url":"https://syntology.ai/paper/2006.14744","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.14744"}},"official":{"repos":["LiqunChen0606/Graph-Optimal-Transport"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/improving-image-captioning-with-better-use-of-1","slug":"improving-image-captioning-with-better-use-of-1","title":"Improving Image Captioning with Better Use of Captions","date":"2020-06-21","arxiv_id":"2006.11807","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/improving-image-captioning-with-better-use-of-1#ran","syntology_url":"https://syntology.ai/paper/2006.11807","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.11807"}},"official":{"repos":["Gitsamshi/WeakVRD-Captioning"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/mitigating-gender-bias-in-captioning-systems","slug":"mitigating-gender-bias-in-captioning-systems","title":"Mitigating Gender Bias in Captioning Systems","date":"2020-06-15","arxiv_id":"2006.08315","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mitigating-gender-bias-in-captioning-systems#ran","syntology_url":"https://syntology.ai/paper/2006.08315","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.08315"}},"official":{"repos":["datamllab/Mitigating_Gender_Bias_In_Captioning_System"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/demystifying-self-supervised-learning-an","slug":"demystifying-self-supervised-learning-an","title":"Self-supervised Learning from a Multi-view Perspective","date":"2020-06-10","arxiv_id":"2006.05576","repositories_listed":1,"syntology":{"n":15,"n_ran":11,"n_constructed":0,"n_ran_checked":10,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":1,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/demystifying-self-supervised-learning-an#ran","syntology_url":"https://syntology.ai/paper/2006.05576","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.05576"}},"official":{"repos":["yaohungt/Demystifying_Self_Supervised_Learning"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/pick-object-attack-type-specific-adversarial","slug":"pick-object-attack-type-specific-adversarial","title":"Pick-Object-Attack: Type-Specific Adversarial Attack for Object Detection","date":"2020-06-05","arxiv_id":"2006.03184","repositories_listed":1,"syntology":null},{"url":"/paper/m3p-learning-universal-representations-via","slug":"m3p-learning-universal-representations-via","title":"M3P: Learning Universal Representations via Multitask Multilingual Multimodal Pre-training","date":"2020-06-04","arxiv_id":"2006.02635","repositories_listed":1,"syntology":null},{"url":"/paper/controlling-length-in-image-captioning","slug":"controlling-length-in-image-captioning","title":"Controlling Length in Image Captioning","date":"2020-05-29","arxiv_id":"2005.14386","repositories_listed":1,"syntology":null},{"url":"/paper/dense-caption-matching-and-frame-selection","slug":"dense-caption-matching-and-frame-selection","title":"Dense-Caption Matching and Frame-Selection Gating for Temporal Localization in VideoQA","date":"2020-05-13","arxiv_id":"2005.06409","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":6,"n_ran_checked":8,"n_instrument":1,"n_unverified":3,"n_honours":2,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"phrase":"9 ran (of which 6 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/dense-caption-matching-and-frame-selection#ran","syntology_url":"https://syntology.ai/paper/2005.06409","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.06409"}},"official":{"repos":["hyounghk/VideoQADenseCapFrameGate-ACL2020"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":6,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/cobra-contrastive-bi-modal-representation","slug":"cobra-contrastive-bi-modal-representation","title":"COBRA: Contrastive Bi-Modal Representation Algorithm","date":"2020-05-07","arxiv_id":"2005.03687","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/cobra-contrastive-bi-modal-representation#ran","syntology_url":"https://syntology.ai/paper/2005.03687","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.03687"}},"official":{"repos":["ovshake/cobra"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/a-girl-has-a-name-detecting-authorship","slug":"a-girl-has-a-name-detecting-authorship","title":"A Girl Has A Name: Detecting Authorship Obfuscation","date":"2020-05-02","arxiv_id":"2005.00702","repositories_listed":1,"syntology":null},{"url":"/paper/nubia-neural-based-interchangeability","slug":"nubia-neural-based-interchangeability","title":"NUBIA: NeUral Based Interchangeability Assessor for Text Generation","date":"2020-04-30","arxiv_id":"2004.14667","repositories_listed":1,"syntology":null},{"url":"/paper/pragmatic-issue-sensitive-image-captioning","slug":"pragmatic-issue-sensitive-image-captioning","title":"Pragmatic Issue-Sensitive Image Captioning","date":"2020-04-29","arxiv_id":"2004.14451","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/pragmatic-issue-sensitive-image-captioning#ran","syntology_url":"https://syntology.ai/paper/2004.14451","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.14451"}},"official":{"repos":["windweller/Pragmatic-ISIC"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/transform-and-tell-entity-aware-news-image","slug":"transform-and-tell-entity-aware-news-image","title":"Transform and Tell: Entity-Aware News Image Captioning","date":"2020-04-17","arxiv_id":"2004.08070","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/transform-and-tell-entity-aware-news-image#ran","syntology_url":"https://syntology.ai/paper/2004.08070","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.08070"}},"official":{"repos":["alasdairtran/transform-and-tell"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/evaluating-multimodal-representations-on-1","slug":"evaluating-multimodal-representations-on-1","title":"Evaluating Multimodal Representations on Visual Semantic Textual Similarity","date":"2020-04-04","arxiv_id":"2004.01894","repositories_listed":1,"syntology":null},{"url":"/paper/memcap-memorizing-style-knowledge-for-image","slug":"memcap-memorizing-style-knowledge-for-image","title":"MemCap: Memorizing Style Knowledge for Image Captioning","date":"2020-04-03","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/more-grounded-image-captioning-by-distilling","slug":"more-grounded-image-captioning-by-distilling","title":"More Grounded Image Captioning by Distilling Image-Text Matching Model","date":"2020-04-01","arxiv_id":"2004.00390","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/more-grounded-image-captioning-by-distilling#ran","syntology_url":"https://syntology.ai/paper/2004.00390","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.00390"}},"official":{"repos":["YuanEZhou/Grounded-Image-Captioning"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/a-better-variant-of-self-critical-sequence","slug":"a-better-variant-of-self-critical-sequence","title":"A Better Variant of Self-Critical Sequence Training","date":"2020-03-22","arxiv_id":"2003.09971","repositories_listed":1,"syntology":null},{"url":"/paper/show-edit-and-tell-a-framework-for-editing-1","slug":"show-edit-and-tell-a-framework-for-editing-1","title":"Show, Edit and Tell: A Framework for Editing Image Captions","date":"2020-03-06","arxiv_id":"2003.03107","repositories_listed":1,"syntology":null},{"url":"/paper/say-as-you-wish-fine-grained-control-of-image","slug":"say-as-you-wish-fine-grained-control-of-image","title":"Say As You Wish: Fine-grained Control of Image Caption Generation with Abstract Scene Graphs","date":"2020-03-01","arxiv_id":"2003.00387","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/say-as-you-wish-fine-grained-control-of-image#ran","syntology_url":"https://syntology.ai/paper/2003.00387","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.00387"}},"official":null}},{"url":"/paper/visual-commonsense-r-cnn","slug":"visual-commonsense-r-cnn","title":"Visual Commonsense R-CNN","date":"2020-02-27","arxiv_id":"2002.12204","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/visual-commonsense-r-cnn#ran","syntology_url":"https://syntology.ai/paper/2002.12204","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.12204"}},"official":{"repos":["Wangt-CN/VC-R-CNN"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/latent-normalizing-flows-for-many-to-many-1","slug":"latent-normalizing-flows-for-many-to-many-1","title":"Latent Normalizing Flows for Many-to-Many Cross-Domain Mappings","date":"2020-02-16","arxiv_id":"2002.06661","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/latent-normalizing-flows-for-many-to-many-1#ran","syntology_url":"https://syntology.ai/paper/2002.06661","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.06661"}},"official":{"repos":["visinf/lnfmm"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/sparse-and-structured-visual-attention-1","slug":"sparse-and-structured-visual-attention-1","title":"Sparse and Structured Visual Attention","date":"2020-02-13","arxiv_id":"2002.05556","repositories_listed":1,"syntology":null},{"url":"/paper/adapting-grad-cam-for-embedding-networks","slug":"adapting-grad-cam-for-embedding-networks","title":"Adapting Grad-CAM for Embedding Networks","date":"2020-01-17","arxiv_id":"2001.06538","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/adapting-grad-cam-for-embedding-networks#ran","syntology_url":"https://syntology.ai/paper/2001.06538","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2001.06538"}},"official":null}},{"url":"/paper/mhsan-multi-head-self-attention-network-for","slug":"mhsan-multi-head-self-attention-network-for","title":"MHSAN: Multi-Head Self-Attention Network for Visual Semantic Embedding","date":"2020-01-11","arxiv_id":"2001.03712","repositories_listed":1,"syntology":null},{"url":"/paper/understanding-image-captioning-models-beyond","slug":"understanding-image-captioning-models-beyond","title":"Explain and Improve: LRP-Inference Fine-Tuning for Image Captioning Models","date":"2020-01-04","arxiv_id":"2001.01037","repositories_listed":1,"syntology":null},{"url":"/paper/adaptive-correlated-monte-carlo-for-1","slug":"adaptive-correlated-monte-carlo-for-1","title":"Adaptive Correlated Monte Carlo for Contextual Categorical Sequence Generation","date":"2019-12-31","arxiv_id":"1912.13151","repositories_listed":1,"syntology":null},{"url":"/paper/connecting-vision-and-language-with-localized","slug":"connecting-vision-and-language-with-localized","title":"Connecting Vision and Language with Localized Narratives","date":"2019-12-06","arxiv_id":"1912.03098","repositories_listed":1,"syntology":null},{"url":"/paper/scratch-that-an-evolution-based-adversarial","slug":"scratch-that-an-evolution-based-adversarial","title":"Scratch that! An Evolution-based Adversarial Attack against Neural Networks","date":"2019-12-05","arxiv_id":"1912.02316","repositories_listed":1,"syntology":null},{"url":"/paper/sequence-modeling-with-unconstrained","slug":"sequence-modeling-with-unconstrained","title":"Sequence Modeling with Unconstrained Generation Order","date":"2019-11-01","arxiv_id":"1911.00176","repositories_listed":1,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":9,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/sequence-modeling-with-unconstrained#ran","syntology_url":"https://syntology.ai/paper/1911.00176","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.00176"}},"official":{"repos":["TIXFeniks/neurips2019_intrus"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/can-adversarial-training-learn-image","slug":"can-adversarial-training-learn-image","title":"Can adversarial training learn image captioning ?","date":"2019-10-31","arxiv_id":"1910.14609","repositories_listed":1,"syntology":null},{"url":"/paper/adaptively-aligned-image-captioning-via","slug":"adaptively-aligned-image-captioning-via","title":"Adaptively Aligned Image Captioning via Adaptive Attention Time","date":"2019-09-19","arxiv_id":"1909.09060","repositories_listed":1,"syntology":null},{"url":"/paper/contcap-a-comprehensive-framework-for","slug":"contcap-a-comprehensive-framework-for","title":"ContCap: A scalable framework for continual image captioning","date":"2019-09-19","arxiv_id":"1909.08745","repositories_listed":1,"syntology":null},{"url":"/paper/vizseq-a-visual-analysis-toolkit-for-text","slug":"vizseq-a-visual-analysis-toolkit-for-text","title":"VizSeq: A Visual Analysis Toolkit for Text Generation Tasks","date":"2019-09-12","arxiv_id":"1909.05424","repositories_listed":1,"syntology":null},{"url":"/paper/compositional-generalization-in-image","slug":"compositional-generalization-in-image","title":"Compositional Generalization in Image Captioning","date":"2019-09-10","arxiv_id":"1909.04402","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":3,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/compositional-generalization-in-image#ran","syntology_url":"https://syntology.ai/paper/1909.04402","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.04402"}},"official":{"repos":["mitjanikolaus/compositional-image-captioning"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/quality-estimation-for-image-captions-based","slug":"quality-estimation-for-image-captions-based","title":"Quality Estimation for Image Captions Based on Large-scale Human Evaluations","date":"2019-09-08","arxiv_id":"1909.03396","repositories_listed":1,"syntology":null},{"url":"/paper/look-and-modify-modification-networks-for","slug":"look-and-modify-modification-networks-for","title":"Look and Modify: Modification Networks for Image Captioning","date":"2019-09-07","arxiv_id":"1909.03169","repositories_listed":1,"syntology":null},{"url":"/paper/reo-relevance-extraness-omission-a-fine","slug":"reo-relevance-extraness-omission-a-fine","title":"REO-Relevance, Extraness, Omission: A Fine-grained Evaluation for Image Captioning","date":"2019-09-05","arxiv_id":"1909.02217","repositories_listed":1,"syntology":null},{"url":"/paper/tiger-text-to-image-grounding-for-image","slug":"tiger-text-to-image-grounding-for-image","title":"TIGEr: Text-to-Image Grounding for Image Caption Evaluation","date":"2019-09-04","arxiv_id":"1909.02050","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/tiger-text-to-image-grounding-for-image#ran","syntology_url":"https://syntology.ai/paper/1909.02050","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.02050"}},"official":{"repos":["SeleenaJM/CapEval"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/aesthetic-image-captioning-from-weakly","slug":"aesthetic-image-captioning-from-weakly","title":"Aesthetic Image Captioning From Weakly-Labelled Photographs","date":"2019-08-29","arxiv_id":"1908.11310","repositories_listed":1,"syntology":null},{"url":"/paper/image-captioning-with-sparse-recurrent-neural","slug":"image-captioning-with-sparse-recurrent-neural","title":"Image Captioning with Sparse Recurrent Neural Network","date":"2019-08-28","arxiv_id":"1908.10797","repositories_listed":1,"syntology":null},{"url":"/paper/towards-diverse-and-accurate-image-captions","slug":"towards-diverse-and-accurate-image-captions","title":"Towards Diverse and Accurate Image Captions via Reinforcing Determinantal Point Process","date":"2019-08-14","arxiv_id":"1908.04919","repositories_listed":1,"syntology":null},{"url":"/paper/aligning-linguistic-words-and-visual-semantic","slug":"aligning-linguistic-words-and-visual-semantic","title":"Aligning Linguistic Words and Visual Semantic Units for Image Captioning","date":"2019-08-06","arxiv_id":"1908.02127","repositories_listed":1,"syntology":null},{"url":"/paper/cascaded-revision-network-for-novel-object","slug":"cascaded-revision-network-for-novel-object","title":"Cascaded Revision Network for Novel Object Captioning","date":"2019-08-06","arxiv_id":"1908.02726","repositories_listed":1,"syntology":null},{"url":"/paper/bridging-by-word-image-grounded-vocabulary","slug":"bridging-by-word-image-grounded-vocabulary","title":"Bridging by Word: Image Grounded Vocabulary Construction for Visual Captioning","date":"2019-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/expressing-visual-relationships-via-language","slug":"expressing-visual-relationships-via-language","title":"Expressing Visual Relationships via Language","date":"2019-06-18","arxiv_id":"1906.07689","repositories_listed":1,"syntology":null},{"url":"/paper/mimic-and-fool-a-task-agnostic-adversarial","slug":"mimic-and-fool-a-task-agnostic-adversarial","title":"Mimic and Fool: A Task Agnostic Adversarial Attack","date":"2019-06-11","arxiv_id":"1906.04606","repositories_listed":1,"syntology":null},{"url":"/paper/context-aware-visual-policy-network-for-fine","slug":"context-aware-visual-policy-network-for-fine","title":"Context-Aware Visual Policy Network for Fine-Grained Image Captioning","date":"2019-06-06","arxiv_id":"1906.02365","repositories_listed":1,"syntology":null},{"url":"/paper/towards-interpretable-reinforcement-learning","slug":"towards-interpretable-reinforcement-learning","title":"Towards Interpretable Reinforcement Learning Using Attention Augmented Agents","date":"2019-06-06","arxiv_id":"1906.02500","repositories_listed":1,"syntology":null},{"url":"/paper/on-measuring-gender-bias-in-translation-of","slug":"on-measuring-gender-bias-in-translation-of","title":"On Measuring Gender Bias in Translation of Gender-neutral Pronouns","date":"2019-05-28","arxiv_id":"1905.11684","repositories_listed":1,"syntology":null},{"url":"/paper/aligning-visual-regions-and-textual-concepts","slug":"aligning-visual-regions-and-textual-concepts","title":"Aligning Visual Regions and Textual Concepts for Semantic-Grounded Image Representations","date":"2019-05-15","arxiv_id":"1905.06139","repositories_listed":1,"syntology":null},{"url":"/paper/exact-adversarial-attack-to-image-captioning","slug":"exact-adversarial-attack-to-image-captioning","title":"Exact Adversarial Attack to Image Captioning via Structured Output Learning with Latent Variables","date":"2019-05-10","arxiv_id":"1905.04016","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/exact-adversarial-attack-to-image-captioning#ran","syntology_url":"https://syntology.ai/paper/1905.04016","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.04016"}},"official":null}},{"url":"/paper/image-captioning-with-clause-focused-metrics","slug":"image-captioning-with-clause-focused-metrics","title":"Image Captioning with Clause-Focused Metrics in a Multi-Modal Setting for Marketing","date":"2019-05-06","arxiv_id":"1905.01919","repositories_listed":1,"syntology":null},{"url":"/paper/deep-metric-learning-beyond-binary","slug":"deep-metric-learning-beyond-binary","title":"Deep Metric Learning Beyond Binary Supervision","date":"2019-04-21","arxiv_id":"1904.09626","repositories_listed":1,"syntology":null},{"url":"/paper/big-but-imperceptible-adversarial","slug":"big-but-imperceptible-adversarial","title":"Unrestricted Adversarial Examples via Semantic Manipulation","date":"2019-04-12","arxiv_id":"1904.06347","repositories_listed":1,"syntology":null},{"url":"/paper/good-news-everyone-context-driven-entity","slug":"good-news-everyone-context-driven-entity","title":"Good News, Everyone! Context driven entity-aware captioning for news images","date":"2019-04-02","arxiv_id":"1904.01475","repositories_listed":1,"syntology":null},{"url":"/paper/describing-like-humans-on-diversity-in-image","slug":"describing-like-humans-on-diversity-in-image","title":"Describing like humans: on diversity in image captioning","date":"2019-03-28","arxiv_id":"1903.12020","repositories_listed":1,"syntology":null},{"url":"/paper/alphax-exploring-neural-architectures-with-1","slug":"alphax-exploring-neural-architectures-with-1","title":"AlphaX: eXploring Neural Architectures with Deep Neural Networks and Monte Carlo Tree Search","date":"2019-03-26","arxiv_id":"1903.11059","repositories_listed":1,"syntology":null},{"url":"/paper/evaluating-sequence-to-sequence-models-for","slug":"evaluating-sequence-to-sequence-models-for","title":"Evaluating Sequence-to-Sequence Models for Handwritten Text Recognition","date":"2019-03-18","arxiv_id":"1903.07377","repositories_listed":1,"syntology":null},{"url":"/paper/dense-relational-captioning-triple-stream","slug":"dense-relational-captioning-triple-stream","title":"Dense Relational Captioning: Triple-Stream Networks for Relationship-Based Captioning","date":"2019-03-14","arxiv_id":"1903.05942","repositories_listed":1,"syntology":null},{"url":"/paper/show-translate-and-tell","slug":"show-translate-and-tell","title":"Show, Translate and Tell","date":"2019-03-14","arxiv_id":"1903.06275","repositories_listed":1,"syntology":null},{"url":"/paper/wasserstein-barycenter-model-ensembling-1","slug":"wasserstein-barycenter-model-ensembling-1","title":"Wasserstein Barycenter Model Ensembling","date":"2019-02-13","arxiv_id":"1902.04999","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/wasserstein-barycenter-model-ensembling-1#ran","syntology_url":"https://syntology.ai/paper/1902.04999","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.04999"}},"official":null}},{"url":"/paper/generating-diverse-and-meaningful-captions","slug":"generating-diverse-and-meaningful-captions","title":"Generating Diverse and Meaningful Captions","date":"2018-12-19","arxiv_id":"1812.08126","repositories_listed":1,"syntology":null},{"url":"/paper/adversarial-inference-for-multi-sentence","slug":"adversarial-inference-for-multi-sentence","title":"Adversarial Inference for Multi-Sentence Video Description","date":"2018-12-13","arxiv_id":"1812.05634","repositories_listed":1,"syntology":null},{"url":"/paper/lifelong-learning-for-image-captioning-by","slug":"lifelong-learning-for-image-captioning-by","title":"Learning to Caption Images through a Lifetime by Asking Questions","date":"2018-12-01","arxiv_id":"1812.00235","repositories_listed":1,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/lifelong-learning-for-image-captioning-by#ran","syntology_url":"https://syntology.ai/paper/1812.00235","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.00235"}},"official":{"repos":["shenkev/Caption-Lifetime-by-Asking-Questions"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/unsupervised-image-captioning","slug":"unsupervised-image-captioning","title":"Unsupervised Image Captioning","date":"2018-11-27","arxiv_id":"1811.10787","repositories_listed":1,"syntology":{"n":9,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/unsupervised-image-captioning#ran","syntology_url":"https://syntology.ai/paper/1811.10787","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.10787"}},"official":null}},{"url":"/paper/show-control-and-tell-a-framework-for","slug":"show-control-and-tell-a-framework-for","title":"Show, Control and Tell: A Framework for Generating Controllable and Grounded Captions","date":"2018-11-26","arxiv_id":"1811.10652","repositories_listed":1,"syntology":null},{"url":"/paper/end-to-end-image-captioning-exploits","slug":"end-to-end-image-captioning-exploits","title":"End-to-end Image Captioning Exploits Distributional Similarity in Multimodal Space","date":"2018-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/gated-hierarchical-attention-for-image","slug":"gated-hierarchical-attention-for-image","title":"Gated Hierarchical Attention for Image Captioning","date":"2018-10-30","arxiv_id":"1810.12535","repositories_listed":1,"syntology":null}],"record_sha256":"9632a72aab8587fe59e06ab13a396cf26e303674b328dd07715a539c466f53fc","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}