{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T15:40:22Z","timestamp":1792597222384,"version":"4.5.0"},"reference-count":44,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2023A1515012853"],"award-info":[{"award-number":["2023A1515012853"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61976231"],"award-info":[{"award-number":["61976231"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neurocomputing"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.neucom.2026.134769","type":"journal-article","created":{"date-parts":[[2026,8,8]],"date-time":"2026-08-08T22:22:28Z","timestamp":1786227748000},"page":"134769","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Elevating descriptive excellence: Object-centric dense video captioning"],"prefix":"10.1016","volume":"703","author":[{"given":"Zehua","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6729-4176","authenticated-orcid":false,"given":"Huicheng","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yun","family":"Lan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neucom.2026.134769_bib0005","series-title":"Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization","first-page":"65","article-title":"METEOR: an automatic metric for MT evaluation with improved correlation with human judgments","author":"Banerjee","year":"2005"},{"key":"10.1016\/j.neucom.2026.134769_bib0010","series-title":"IEEE International Conference on Multimedia and Expo","first-page":"2615","article-title":"MRCap: multi-modal and multi-level relationship-based dense video captioning","author":"Chen","year":"2023"},{"key":"10.1016\/j.neucom.2026.134769_bib0015","series-title":"Proceedings of the Association for Computational Linguistics","first-page":"2978","article-title":"Transformer-XL: attentive language models beyond a fixed-length context","author":"Dai","year":"2019"},{"key":"10.1016\/j.neucom.2026.134769_bib0020","series-title":"Proceedings of the Computer Vision and Pattern Recognition","first-page":"234","article-title":"Sketch, ground, and refine: top-down dense video captioning","author":"Deng","year":"2021"},{"key":"10.1016\/j.neucom.2026.134769_bib0025","series-title":"Proceedings of the International Conference on Learning Representations","first-page":"1","article-title":"Adam: a method for stochastic optimization","author":"Diederik P. Kingma","year":"2015"},{"key":"10.1016\/j.neucom.2026.134769_bib0030","series-title":"Proceedings of the European Conference on Computer Vision","first-page":"517","article-title":"SODA: story-oriented dense video captioning evaluation framework","author":"Fujita","year":"2020"},{"key":"10.1016\/j.neucom.2026.134769_bib0035","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.neucom.2026.134769_bib0040","series-title":"Proceedings of the ACM International Conference on Multimedia","first-page":"774","article-title":"Hierarchical global-local temporal modeling for video captioning","author":"Hu","year":"2019"},{"key":"10.1016\/j.neucom.2026.134769_bib0045","series-title":"British Machine Vision Conference","first-page":"1","article-title":"A better use of audio-visual cues: dense video captioning with bi-modal transformer","author":"Iashin","year":"2020"},{"key":"10.1016\/j.neucom.2026.134769_bib0050","series-title":"Proceedings of the Computer Vision and Pattern Recognition Workshops","first-page":"4117","article-title":"Multi-modal dense video captioning","author":"Iashin","year":"2020"},{"key":"10.1016\/j.neucom.2026.134769_bib0055","series-title":"Proceedings of the Computer Vision and Pattern Recognition","first-page":"13894","article-title":"Do you remember? Dense video captioning with cross-modal memory retrieval","author":"Kim","year":"2024"},{"key":"10.1016\/j.neucom.2026.134769_bib0060","series-title":"Proceedings of the Computer Vision and Pattern Recognition","first-page":"706","article-title":"Dense-captioning events in videos","author":"Krishna","year":"2017"},{"key":"10.1016\/j.neucom.2026.134769_bib0065","series-title":"Proceedings of the Association for Computational Linguistics","first-page":"2603","article-title":"MART: memory-augmented recurrent transformer for coherent video paragraph captioning","author":"Lei","year":"2020"},{"key":"10.1016\/j.neucom.2026.134769_bib0070","series-title":"Proceedings of the Computer Vision and Pattern Recognition","first-page":"7492","article-title":"Jointly localizing and describing events for dense video captioning","author":"Li","year":"2018"},{"key":"10.1016\/j.neucom.2026.134769_bib0075","series-title":"Proceedings of the Computer Vision and Pattern Recognition","first-page":"2999","article-title":"Focal loss for dense object detection","author":"Lin","year":"2017"},{"key":"10.1016\/j.neucom.2026.134769_bib0080","series-title":"Proceedings of the Computer Vision and Pattern Recognition","first-page":"6588","article-title":"Streamlined dense video captioning","author":"Mun","year":"2019"},{"key":"10.1016\/j.neucom.2026.134769_bib0085","series-title":"Proceedings of the Annual Meeting of the Association for Computational Linguistics","first-page":"311","article-title":"BLEU: a method for automatic evaluation of machine translation","author":"Papineni","year":"2002"},{"key":"10.1016\/j.neucom.2026.134769_bib0090","series-title":"Proceedings of the Computer Vision and Pattern Recognition","first-page":"18699","article-title":"Adversarial inference for multi-sentence video description","author":"Park","year":"2019"},{"key":"10.1016\/j.neucom.2026.134769_bib0095","series-title":"Proceedings of International Conference on Machine Learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.neucom.2026.134769_bib0100","series-title":"Proceedings of the Computer Vision and Pattern Recognition","first-page":"658","article-title":"Generalized intersection over Union: a metric and a loss for bounding box regression","author":"Rezatofighi","year":"2019"},{"key":"10.1016\/j.neucom.2026.134769_bib0105","series-title":"Proceedings of the International Conference on Computer Vision","first-page":"4489","article-title":"Learning spatiotemporal features with 3D convolutional networks","author":"Tran","year":"2015"},{"key":"10.1016\/j.neucom.2026.134769_bib0110","series-title":"Proceedings of the Computer Vision and Pattern Recognition","first-page":"4566","article-title":"CIDEr: consensus-based image description evaluation","author":"Vedantam","year":"2015"},{"key":"10.1016\/j.neucom.2026.134769_bib0115","series-title":"Proceedings of the International Conference on Computer Vision","first-page":"4534","article-title":"Sequence to sequence \u2013 video to text","author":"Venugopalan","year":"2015"},{"key":"10.1016\/j.neucom.2026.134769_bib0120","series-title":"Proceedings of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","first-page":"1494","article-title":"Translating videos to natural language using deep recurrent neural networks","author":"Venugopalan","year":"2015"},{"key":"10.1016\/j.neucom.2026.134769_bib0125","series-title":"Proceedings of the Computer Vision and Pattern Recognition","first-page":"7190","article-title":"Bidirectional attentive fusion with context gating for dense video captioning","author":"Wang","year":"2018"},{"key":"10.1016\/j.neucom.2026.134769_bib0130","doi-asserted-by":"crossref","first-page":"2740","DOI":"10.1109\/TPAMI.2018.2868668","article-title":"Temporal segment networks for action recognition in videos","volume":"41","author":"Wang","year":"2019","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.neucom.2026.134769_bib0135","series-title":"Proceedings of the International Conference on Computer Vision","first-page":"6847","article-title":"End-to-end dense video captioning with parallel decoding","author":"Wang","year":"2021"},{"key":"10.1016\/j.neucom.2026.134769_bib0140","doi-asserted-by":"crossref","first-page":"1890","DOI":"10.1109\/TCSVT.2020.3014606","article-title":"Event-centric hierarchical representation for dense video captioning","volume":"31","author":"Wang","year":"2021","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.neucom.2026.134769_bib0145","series-title":"Proceedings of the Computer Vision and Pattern Recognition","first-page":"18699","article-title":"DIBS: enhancing dense video captioning with unlabeled videos via pseudo boundary enrichment and online refinement","author":"Wu","year":"2024"},{"key":"10.1016\/j.neucom.2026.134769_bib0150","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"8417","article-title":"Event-equalized dense video captioning","author":"Wu","year":"2025"},{"key":"10.1016\/j.neucom.2026.134769_bib0155","series-title":"Proceedings of the European Conference on Computer Vision","first-page":"468","article-title":"Move forward and tell: a progressive generator of video descriptions","author":"Xiong","year":"2018"},{"key":"10.1016\/j.neucom.2026.134769_bib0160","series-title":"Proceedings of the Computer Vision and Pattern Recognition","first-page":"10714","article-title":"Vid2Seq: large-scale pretraining of a visual language model for dense video captioning","author":"Yang","year":"2023"},{"key":"10.1016\/j.neucom.2026.134769_bib0165","series-title":"Proceedings of the IEEE International Conference on Image Processing","first-page":"1288","article-title":"Hierarchical context encoding for events captioning in videos","author":"Yang","year":"2018"},{"key":"10.1016\/j.neucom.2026.134769_bib0170","series-title":"Proceedings of the Computer Vision and Pattern Recognition","first-page":"4507","article-title":"Describing videos by exploiting temporal structure","author":"Yao","year":"2015"},{"key":"10.1016\/j.neucom.2026.134769_bib0175","series-title":"Proceedings of the Computer Vision and Pattern Recognition","first-page":"4584","article-title":"Video paragraph captioning using hierarchical recurrent neural networks","author":"Yu","year":"2016"},{"key":"10.1016\/j.neucom.2026.134769_bib0180","series-title":"Proceedings of the International Joint Conference on Neural Networks","first-page":"1","article-title":"Dense video captioning with hierarchical attention-based encoder-decoder networks","author":"Yu","year":"2021"},{"key":"10.1016\/j.neucom.2026.134769_bib0185","series-title":"Proceedings of the European Conference on Computer Vision","first-page":"374","article-title":"Cross-modal and hierarchical modeling of video and text","author":"Zhang","year":"2018"},{"key":"10.1016\/j.neucom.2026.134769_bib0190","series-title":"Proceedings of the Computer Vision and Pattern Recognition","first-page":"8319","article-title":"Object-aware aggregation with bidirectional temporal graph for video captioning","author":"Zhang","year":"2019"},{"key":"10.1016\/j.neucom.2026.134769_bib0195","series-title":"Proceedings of the European Conference on Computer Vision","first-page":"363","article-title":"Unifying event detection and captioning as sequence generation via pre-training","author":"Zhang","year":"2022"},{"key":"10.1016\/j.neucom.2026.134769_bib0200","series-title":"Proceedings of the Computer Vision and Pattern Recognition","first-page":"13275","article-title":"Object relational graph with teacher-recommended learning for video captioning","author":"Zhang","year":"2020"},{"key":"10.1016\/j.neucom.2026.134769_bib0205","series-title":"Proceedings of the Computer Vision and Pattern Recognition","first-page":"18699","article-title":"Grounded video description","author":"Zhou","year":"2019"},{"key":"10.1016\/j.neucom.2026.134769_bib0210","series-title":"Proceedings of the Association for the Advancement of Artificial Intelligence","first-page":"7590","article-title":"Towards automatic learning of procedures from web instructional videos","author":"Zhou","year":"2018"},{"key":"10.1016\/j.neucom.2026.134769_bib0215","series-title":"Proceedings of the Computer Vision and Pattern Recognition","first-page":"8739","article-title":"End-to-end dense video captioning with masked transformer","author":"Zhou","year":"2018"},{"key":"10.1016\/j.neucom.2026.134769_bib0220","series-title":"Proceedings of the International Conference on Learning Representations","first-page":"1","article-title":"Deformable DETR: deformable transformers for end-to-end object detection","author":"Zhu","year":"2021"}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226021673?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226021673?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T14:43:53Z","timestamp":1792593833000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231226021673"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":44,"alternative-id":["S0925231226021673"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134769","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Elevating descriptive excellence: Object-centric dense video captioning","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134769","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"134769"}}