{"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/video-captioning/papers/5","list_of":"/task/video-captioning","task":"Video 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":5,"pages_in_order":5,"rows_per_page":100,"rows":[401,473],"of":473,"counts":{"archive_papers_tagged":473,"with_a_code_link":211,"where_syntology_ran_a_sample":64,"not_listed_spam_title":0,"listed":473,"listed_where_code_ran":64,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":56,"every_run_a_failure_of_syntologys_instrument":8,"listed_with_a_run_with_no_instrument_failure":56,"listed_every_run_a_failure_of_syntologys_instrument":8,"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/video-captioning","prev":"/task/video-captioning/papers/4","next":null,"papers":[{"url":null,"slug":"learning-actions-from-human-demonstration","title":"Learning Actions from Human Demonstration Video for Robotic Manipulation","date":"2019-09-10","arxiv_id":"1909.04312","repositories_listed":0,"syntology":null},{"url":null,"slug":"captioning-near-future-activity-sequences","title":"Prediction and Description of Near-Future Activities in Video","date":"2019-08-02","arxiv_id":"1908.00943","repositories_listed":0,"syntology":null},{"url":null,"slug":"watch-it-twice-video-captioning-with-a","title":"Watch It Twice: Video Captioning with a Refocused Video Encoder","date":"2019-07-21","arxiv_id":"1907.12905","repositories_listed":0,"syntology":null},{"url":null,"slug":"activitynet-2019-task-3-exploring-contexts","title":"Activitynet 2019 Task 3: Exploring Contexts for Dense Captioning Events in Videos","date":"2019-07-11","arxiv_id":"1907.05092","repositories_listed":0,"syntology":null},{"url":null,"slug":"contrastive-bidirectional-transformer-for","title":"Learning Video Representations using Contrastive Bidirectional Transformer","date":"2019-06-13","arxiv_id":"1906.05743","repositories_listed":0,"syntology":null},{"url":null,"slug":"object-aware-aggregation-with-bidirectional-1","title":"Object-aware Aggregation with Bidirectional Temporal Graph for Video Captioning","date":"2019-06-11","arxiv_id":"1906.04375","repositories_listed":0,"syntology":null},{"url":null,"slug":"attention-is-all-you-need-for-videos-self","title":"Attention is all you need for Videos: Self-attention based Video Summarization using Universal Transformers","date":"2019-06-06","arxiv_id":"1906.02792","repositories_listed":0,"syntology":null},{"url":null,"slug":"relational-reasoning-using-prior-knowledge","title":"Relational Reasoning using Prior Knowledge for Visual Captioning","date":"2019-06-04","arxiv_id":"1906.01290","repositories_listed":0,"syntology":null},{"url":null,"slug":"reconstruct-and-represent-video-contents-for","title":"Reconstruct and Represent Video Contents for Captioning via Reinforcement Learning","date":"2019-06-03","arxiv_id":"1906.01452","repositories_listed":0,"syntology":null},{"url":null,"slug":"interactive-predictive-neural-multimodal","title":"Interactive-predictive neural multimodal systems","date":"2019-05-30","arxiv_id":"1905.12980","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-flow-profile-image-for-video","title":"On Flow Profile Image for Video Representation","date":"2019-05-12","arxiv_id":"1905.04668","repositories_listed":0,"syntology":null},{"url":null,"slug":"multimodal-semantic-attention-network-for","title":"Multimodal Semantic Attention Network for Video Captioning","date":"2019-05-08","arxiv_id":"1905.02963","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-recurrent-neural-network-for-2","title":"Hierarchical Recurrent Neural Network for Video Summarization","date":"2019-04-28","arxiv_id":"1904.12251","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-end-to-end-baseline-for-video-captioning","title":"End-to-End Video Captioning","date":"2019-04-04","arxiv_id":"1904.02628","repositories_listed":0,"syntology":null},{"url":null,"slug":"spatio-temporal-dynamics-and-semantic","title":"Spatio-Temporal Dynamics and Semantic Attribute Enriched Visual Encoding for Video Captioning","date":"2019-02-27","arxiv_id":"1902.10322","repositories_listed":0,"syntology":null},{"url":null,"slug":"not-all-words-are-equal-video-specific","title":"Not All Words are Equal: Video-specific Information Loss for Video Captioning","date":"2019-01-01","arxiv_id":"1901.00097","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-lstms-with-adaptive-attention","title":"Hierarchical LSTMs with Adaptive Attention for Visual Captioning","date":"2018-12-26","arxiv_id":"1812.11004","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-attempt-towards-interpretable-audio-visual","title":"An Attempt towards Interpretable Audio-Visual Video Captioning","date":"2018-12-07","arxiv_id":"1812.02872","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-compose-topic-aware-mixture-of","title":"Learning to Compose Topic-Aware Mixture of Experts for Zero-Shot Video Captioning","date":"2018-11-07","arxiv_id":"1811.02765","repositories_listed":0,"syntology":null},{"url":null,"slug":"middle-out-decoding","title":"Middle-Out Decoding","date":"2018-10-28","arxiv_id":"1810.11735","repositories_listed":0,"syntology":null},{"url":null,"slug":"image-to-video-person-re-identification-by","title":"Image-to-Video Person Re-Identification by Reusing Cross-modal Embeddings","date":"2018-10-04","arxiv_id":"1810.03989","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-dataset-for-telling-the-stories-of-social","title":"A Dataset for Telling the Stories of Social Media Videos","date":"2018-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"incorporating-background-knowledge-into-video","title":"Incorporating Background Knowledge into Video Description Generation","date":"2018-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"temporally-grounding-natural-sentence-in","title":"Temporally Grounding Natural Sentence in Video","date":"2018-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"vector-learning-for-cross-domain","title":"Vector Learning for Cross Domain Representations","date":"2018-09-27","arxiv_id":"1809.10312","repositories_listed":0,"syntology":null},{"url":null,"slug":"bridge-video-and-text-with-cascade-syntactic","title":"Bridge Video and Text with Cascade Syntactic Structure","date":"2018-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"move-forward-and-tell-a-progressive-generator","title":"Move Forward and Tell: A Progressive Generator of Video Descriptions","date":"2018-07-26","arxiv_id":"1807.10018","repositories_listed":0,"syntology":null},{"url":null,"slug":"video-captioning-with-boundary-aware","title":"Video Captioning with Boundary-aware Hierarchical Language Decoding and Joint Video Prediction","date":"2018-07-08","arxiv_id":"1807.03658","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-reinforcement-learning-for-nlp","title":"Deep Reinforcement Learning for NLP","date":"2018-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"best-vision-technologies-submission-to","title":"Best Vision Technologies Submission to ActivityNet Challenge 2018-Task: Dense-Captioning Events in Videos","date":"2018-06-25","arxiv_id":"1806.09278","repositories_listed":0,"syntology":null},{"url":null,"slug":"ruccmu-system-report-for-dense-captioning","title":"RUC+CMU: System Report for Dense Captioning Events in Videos","date":"2018-06-22","arxiv_id":"1806.08854","repositories_listed":0,"syntology":null},{"url":null,"slug":"fine-grained-video-captioning-for-sports","title":"Fine-Grained Video Captioning for Sports Narrative","date":"2018-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"interpretable-video-captioning-via-trajectory","title":"Interpretable Video Captioning via Trajectory Structured Localization","date":"2018-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"m3-multimodal-memory-modelling-for-video","title":"M3: Multimodal Memory Modelling for Video Captioning","date":"2018-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"amortized-context-vector-inference-for","title":"Amortized Context Vector Inference for Sequence-to-Sequence Networks","date":"2018-05-23","arxiv_id":"1805.09039","repositories_listed":0,"syntology":null},{"url":null,"slug":"jointly-localizing-and-describing-events-for","title":"Jointly Localizing and Describing Events for Dense Video Captioning","date":"2018-04-23","arxiv_id":"1804.08274","repositories_listed":0,"syntology":null},{"url":null,"slug":"less-is-more-picking-informative-frames-for","title":"Less Is More: Picking Informative Frames for Video Captioning","date":"2018-03-05","arxiv_id":"1803.01457","repositories_listed":0,"syntology":null},{"url":null,"slug":"consensus-based-sequence-training-for-video","title":"Consensus-based Sequence Training for Video Captioning","date":"2017-12-27","arxiv_id":"1712.09532","repositories_listed":0,"syntology":null},{"url":null,"slug":"video-captioning-via-hierarchical","title":"Video Captioning via Hierarchical Reinforcement Learning","date":"2017-11-29","arxiv_id":"1711.11135","repositories_listed":0,"syntology":null},{"url":null,"slug":"attend-and-interact-higher-order-object","title":"Attend and Interact: Higher-Order Object Interactions for Video Understanding","date":"2017-11-16","arxiv_id":"1711.06330","repositories_listed":0,"syntology":null},{"url":null,"slug":"grounded-objects-and-interactions-for-video","title":"Grounded Objects and Interactions for Video Captioning","date":"2017-11-16","arxiv_id":"1711.06354","repositories_listed":0,"syntology":null},{"url":null,"slug":"procedural-text-generation-from-an-execution","title":"Procedural Text Generation from an Execution Video","date":"2017-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluation-of-automatic-video-captioning","title":"Evaluation of Automatic Video Captioning Using Direct Assessment","date":"2017-10-29","arxiv_id":"1710.10586","repositories_listed":0,"syntology":null},{"url":null,"slug":"generating-video-descriptions-with-topic","title":"Generating Video Descriptions with Topic Guidance","date":"2017-08-31","arxiv_id":"1708.09666","repositories_listed":0,"syntology":null},{"url":null,"slug":"video-captioning-with-guidance-of-multimodal","title":"Video Captioning with Guidance of Multimodal Latent Topics","date":"2017-08-31","arxiv_id":"1708.09667","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-deterministic-to-generative-multi-modal","title":"From Deterministic to Generative: Multi-Modal Stochastic RNNs for Video Captioning","date":"2017-08-08","arxiv_id":"1708.02478","repositories_listed":0,"syntology":null},{"url":null,"slug":"reinforced-video-captioning-with-entailment","title":"Reinforced Video Captioning with Entailment Rewards","date":"2017-08-07","arxiv_id":"1708.02300","repositories_listed":0,"syntology":null},{"url":null,"slug":"supervising-neural-attention-models-for-video","title":"Supervising Neural Attention Models for Video Captioning by Human Gaze Data","date":"2017-07-19","arxiv_id":"1707.06029","repositories_listed":0,"syntology":null},{"url":null,"slug":"multimodal-machine-learning-integrating","title":"Multimodal Machine Learning: Integrating Language, Vision and Speech","date":"2017-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"task-driven-dynamic-fusion-reducing-ambiguity","title":"Task-Driven Dynamic Fusion: Reducing Ambiguity in Video Description","date":"2017-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-lstm-with-adjusted-temporal","title":"Hierarchical LSTM with Adjusted Temporal Attention for Video Captioning","date":"2017-06-05","arxiv_id":"1706.01231","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-task-video-captioning-with-video-and","title":"Multi-Task Video Captioning with Video and Entailment Generation","date":"2017-04-24","arxiv_id":"1704.07489","repositories_listed":0,"syntology":null},{"url":null,"slug":"weakly-supervised-dense-video-captioning","title":"Weakly Supervised Dense Video Captioning","date":"2017-04-05","arxiv_id":"1704.01502","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-interpretability-of-deep-neural","title":"Improving Interpretability of Deep Neural Networks with Semantic Information","date":"2017-03-12","arxiv_id":"1703.04096","repositories_listed":0,"syntology":null},{"url":null,"slug":"video-captioning-with-multi-faceted-attention","title":"Video Captioning with Multi-Faceted Attention","date":"2016-12-01","arxiv_id":"1612.00234","repositories_listed":0,"syntology":null},{"url":null,"slug":"bidirectional-multirate-reconstruction-for","title":"Bidirectional Multirate Reconstruction for Temporal Modeling in Videos","date":"2016-11-28","arxiv_id":"1611.09053","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-boundary-aware-neural-encoder","title":"Hierarchical Boundary-Aware Neural Encoder for Video Captioning","date":"2016-11-28","arxiv_id":"1611.09312","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-feature-abstraction-for-translating","title":"Adaptive Feature Abstraction for Translating Video to Text","date":"2016-11-23","arxiv_id":"1611.07837","repositories_listed":0,"syntology":null},{"url":null,"slug":"video-captioning-with-transferred-semantic","title":"Video Captioning with Transferred Semantic Attributes","date":"2016-11-23","arxiv_id":"1611.07675","repositories_listed":0,"syntology":null},{"url":null,"slug":"recurrent-memory-addressing-for-describing","title":"Recurrent Memory Addressing for describing videos","date":"2016-11-20","arxiv_id":"1611.06492","repositories_listed":0,"syntology":null},{"url":null,"slug":"multimodal-memory-modelling-for-video","title":"Multimodal Memory Modelling for Video Captioning","date":"2016-11-17","arxiv_id":"1611.05592","repositories_listed":0,"syntology":null},{"url":null,"slug":"spatio-temporal-attention-models-for-grounded","title":"Spatio-Temporal Attention Models for Grounded Video Captioning","date":"2016-10-17","arxiv_id":"1610.04997","repositories_listed":0,"syntology":null},{"url":"/paper/end-to-end-concept-word-detection-for-video","slug":"end-to-end-concept-word-detection-for-video","title":"End-to-end Concept Word Detection for Video Captioning, Retrieval, and Question Answering","date":"2016-10-10","arxiv_id":"1610.02947","repositories_listed":0,"syntology":null},{"url":null,"slug":"title-generation-for-user-generated-videos","title":"Title Generation for User Generated Videos","date":"2016-08-25","arxiv_id":"1608.07068","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-shared-task-on-multimodal-machine","title":"A Shared Task on Multimodal Machine Translation and Crosslingual Image Description","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":"bidirectional-long-short-term-memory-for","title":"Bidirectional Long-Short Term Memory for Video Description","date":"2016-06-15","arxiv_id":"1606.04631","repositories_listed":0,"syntology":null},{"url":null,"slug":"storytelling-of-photo-stream-with","title":"Storytelling of Photo Stream with Bidirectional Multi-thread Recurrent Neural Network","date":"2016-06-02","arxiv_id":"1606.00625","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":"a-restricted-visual-turing-test-for-deep","title":"A Restricted Visual Turing Test for Deep Scene and Event Understanding","date":"2015-12-06","arxiv_id":"1512.01715","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-recurrent-neural-encoder-for","title":"Hierarchical Recurrent Neural Encoder for Video Representation with Application to Captioning","date":"2015-11-11","arxiv_id":"1511.03476","repositories_listed":0,"syntology":null},{"url":null,"slug":"video-paragraph-captioning-using-hierarchical","title":"Video Paragraph Captioning Using Hierarchical Recurrent Neural Networks","date":"2015-10-26","arxiv_id":"1510.07712","repositories_listed":0,"syntology":null},{"url":null,"slug":"chinese-whispers-cooperative-paraphrase","title":"Chinese Whispers: Cooperative Paraphrase Acquisition","date":"2012-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"record_sha256":"d3a16f15b6314435b5cc5d28cc14142ffd50af84c6e3101a43f742929156e99d","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}