{"doi":"10.1109/cvpr.2018.00443","title":"Video Captioning via Hierarchical Reinforcement Learning","abstract":null,"journal":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition","year":2018,"id":626595,"datarank":0.8430601298575726,"base_score":5.62040086571715,"endowment":5.62040086571715,"self_citation_contribution":0.8430601298575726,"citation_network_contribution":0.0,"self_endowment_contribution":0.8430601298575726,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":275,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":null,"is_data_producer":false,"deposit_databanks":null,"is_oa":false,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":null,"fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":1620875,"name":"Wenhu Chen","orcid":null,"position":1,"is_corresponding":false},{"id":539140,"name":"Jiawei Wu","orcid":null,"position":2,"is_corresponding":false},{"id":961184,"name":"Yuan-Fang Wang","orcid":"0009-0004-8390-0561","position":3,"is_corresponding":false},{"id":1175847,"name":"William Yang Wang","orcid":"0000-0002-0878-1257","position":4,"is_corresponding":false},{"id":332093,"name":"Xin Wang","orcid":"0000-0003-1680-599X","position":0,"is_corresponding":false}],"reference_count":0,"raw_metadata":{"has_enrichment":true,"resolved":true,"title":"Video Captioning via Hierarchical Reinforcement Learning","abstract":"Video captioning is the task of automatically generating a textual description of the actions in a video. Although previous work (e.g. sequence-to-sequence model) has shown promising results in abstracting a coarse description of a short video, it is still very challenging to caption a video containing multiple fine-grained actions with a detailed description. This paper aims to address the challenge by proposing a novel hierarchical reinforcement learning framework for video captioning, where a high-level Manager module learns to design sub-goals and a low-level Worker module recognizes the primitive actions to fulfill the sub-goal. With this compositional framework to reinforce video captioning at different levels, our approach significantly outperforms all the baseline methods on a newly introduced large-scale dataset for fine-grained video captioning. Furthermore, our non-ensemble model has already achieved the state-of-the-art results on the widely-used MSR-VTT dataset.","is_dataset_classified":null,"base_score":5.62040086571715,"endowment":5.62040086571715,"datacite_reuse_total":0,"file_count":0,"downloads":0,"views":0,"has_version_chain":false,"is_dataset":false,"is_oa":false,"pmid":"19767382","pmcid":null,"openalex_id":"https://openalex.org/W2963177403","authors":[],"funders":[],"total_grants":0,"fwci":12.2451,"citation_percentile":0.98633527,"influential_citations":0,"citation_trend":[{"year":2012,"count":1},{"year":2018,"count":12},{"year":2019,"count":57},{"year":2020,"count":49},{"year":2021,"count":43},{"year":2022,"count":37},{"year":2023,"count":33},{"year":2024,"count":20},{"year":2025,"count":20},{"year":2026,"count":3}],"oa_status":"closed","license":null,"oa_locations":[{"url":"http://xplorestaging.ieee.org/ielx7/8576498/8578098/08578541.pdf?arnumber=8578541","host_type":"publisher"},{"url":"https://doi.org/10.1109/cvpr.2018.00443","host_type":""}],"fields_of_study":["Multimodal Machine Learning Applications","Human Pose and Action Recognition","Video Analysis and Summarization"],"mesh_terms":[],"keywords":["Closed captioning","Computer science","Reinforcement learning","Task (project management)","Sequence (biology)","Artificial intelligence","Baseline (sea)","Task analysis","Scale (ratio)","Natural language processing","Image (mathematics)"],"sdg_mappings":[],"linked_datasets":[],"clinical_trials":[],"software_tools":[],"database_accessions":[],"source":"live","citation_network_status":"fetched"},"created_at":"2026-08-04T14:26:45.225504Z","pmid":null,"pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}