{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T11:40:49Z","timestamp":1786621249175,"version":"build-2736575974"},"reference-count":46,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computer Vision and Image Understanding"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1016\/j.cviu.2026.104853","type":"journal-article","created":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T16:41:48Z","timestamp":1781800908000},"page":"104853","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Semantic-Weighted Spatio-Temporal Graphs for Structured Video Understanding and Captioning"],"prefix":"10.1016","volume":"270","author":[{"given":"Vibhor","family":"Sharma","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3582-0319","authenticated-orcid":false,"given":"Anurag","family":"Singh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sabrina","family":"Gaito","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.cviu.2026.104853_b1","series-title":"ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"1","article-title":"Enhancing teacher classroom behavior descriptions: A spatio-temporal graph-based method for video captioning","author":"Cai","year":"2025"},{"key":"10.1016\/j.cviu.2026.104853_b2","unstructured":"Chen,\u00a0D., Dolan,\u00a0W.B., 2011. Collecting highly parallel data for paraphrase evaluation. In: Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies. pp. 190\u2013200."},{"key":"10.1016\/j.cviu.2026.104853_b3","series-title":"Asian Conference on Machine Learning","first-page":"847","article-title":"Tvt: Two-view transformer network for video captioning","author":"Chen","year":"2018"},{"issue":"1s","key":"10.1016\/j.cviu.2026.104853_b4","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3539225","article-title":"Retrieval augmented convolutional encoder-decoder networks for video captioning","volume":"19","author":"Chen","year":"2023","journal-title":"ACM Trans. Multimed. Comput. Commun. Appl."},{"issue":"10","key":"10.1016\/j.cviu.2026.104853_b5","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3679203","article-title":"Action-aware linguistic skeleton optimization network for non-autoregressive video captioning","volume":"20","author":"Chen","year":"2024","journal-title":"ACM Trans. Multimed. Comput. Commun. Appl."},{"key":"10.1016\/j.cviu.2026.104853_b6","series-title":"Diving deep into the motion representation of video-text models","author":"Devaraj","year":"2024"},{"issue":"2","key":"10.1016\/j.cviu.2026.104853_b7","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3550276","article-title":"Semantic embedding guided attention with explicit visual feature fusion for video captioning","volume":"19","author":"Dong","year":"2023","journal-title":"ACM Trans. Multimed. Comput. Commun. Appl."},{"key":"10.1016\/j.cviu.2026.104853_b8","doi-asserted-by":"crossref","unstructured":"Hu,\u00a0J., Guo,\u00a0D., Li,\u00a0K., Si,\u00a0Z., Yang,\u00a0X., Wang,\u00a0M., 2024. Maskable retentive network for video moment retrieval. In: Proceedings of the 32nd ACM International Conference on Multimedia. pp. 1476\u20131485.","DOI":"10.1145\/3664647.3680746"},{"key":"10.1016\/j.cviu.2026.104853_b9","article-title":"Memory-based augmentation network for video captioning","author":"Jing","year":"2023","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.cviu.2026.104853_b10","first-page":"1902","article-title":"Proposal-free video grounding with contextual pyramid network","volume":"vol. 35","author":"Li","year":"2021"},{"issue":"10","key":"10.1016\/j.cviu.2026.104853_b11","doi-asserted-by":"crossref","DOI":"10.1007\/s11432-022-3783-3","article-title":"ViGT: Proposal-free video grounding with a learnable token in the transformer","volume":"66","author":"Li","year":"2023","journal-title":"Sci. China Inf. Sci."},{"issue":"6","key":"10.1016\/j.cviu.2026.104853_b12","first-page":"1","article-title":"Transformer-based visual grounding with cross-modality interaction","volume":"19","author":"Li","year":"2023","journal-title":"ACM Trans. Multimed. Comput. Commun. Appl."},{"key":"10.1016\/j.cviu.2026.104853_b13","doi-asserted-by":"crossref","first-page":"3844","DOI":"10.1109\/TMM.2025.3535385","article-title":"Repetitive action counting with hybrid temporal relation modeling","volume":"27","author":"Li","year":"2025","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.cviu.2026.104853_b14","doi-asserted-by":"crossref","unstructured":"Li,\u00a0J., Vo,\u00a0D.M., Sugimoto,\u00a0A., Nakayama,\u00a0H., 2024. EVCap: Retrieval-Augmented Image Captioning with External Visual-Name Memory for Open-World Comprehension. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 13733\u201313742.","DOI":"10.1109\/CVPR52733.2024.01303"},{"key":"10.1016\/j.cviu.2026.104853_b15","article-title":"Learning hierarchical modular networks for video captioning","author":"Li","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.cviu.2026.104853_b16","doi-asserted-by":"crossref","unstructured":"Lin,\u00a0K., Li,\u00a0L., Lin,\u00a0C.-C., Ahmed,\u00a0F., Gan,\u00a0Z., Liu,\u00a0Z., Lu,\u00a0Y., Wang,\u00a0L., 2022. Swinbert: End-to-end transformers with sparse attention for video captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 17949\u201317958.","DOI":"10.1109\/CVPR52688.2022.01742"},{"key":"10.1016\/j.cviu.2026.104853_b17","series-title":"European Conference on Computer Vision","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"Lin","year":"2014"},{"key":"10.1016\/j.cviu.2026.104853_b18","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.109906","article-title":"Global semantic enhancement network for video captioning","volume":"145","author":"Luo","year":"2024","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.cviu.2026.104853_b19","series-title":"Subject-oriented video captioning","author":"Ma","year":"2023"},{"key":"10.1016\/j.cviu.2026.104853_b20","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.112258","article-title":"Style-aware two-stage learning framework for video captioning","volume":"301","author":"Ma","year":"2024","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.cviu.2026.104853_b21","doi-asserted-by":"crossref","unstructured":"Pan,\u00a0Y., Mei,\u00a0T., Yao,\u00a0T., Li,\u00a0H., Rui,\u00a0Y., 2016. Jointly modeling embedding and translation to bridge video and language. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 4594\u20134602.","DOI":"10.1109\/CVPR.2016.497"},{"key":"10.1016\/j.cviu.2026.104853_b22","doi-asserted-by":"crossref","DOI":"10.1016\/j.cviu.2023.103864","article-title":"CMGNet: Collaborative multi-modal graph network for video captioning","volume":"238","author":"Rao","year":"2024","journal-title":"Comput. Vis. Image Underst."},{"issue":"1","key":"10.1016\/j.cviu.2026.104853_b23","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1186\/s40649-016-0034-y","article-title":"An efficient method for link prediction in weighted multiplex networks","volume":"3","author":"Sharma","year":"2016","journal-title":"Comput. Soc. Netw."},{"key":"10.1016\/j.cviu.2026.104853_b24","series-title":"2024 IEEE International Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation (IATMSI)","first-page":"1","article-title":"Object centered video captioning using spatio-temporal graphs","author":"Sharma","year":"2024"},{"key":"10.1016\/j.cviu.2026.104853_b25","series-title":"2024 16th International Conference on COMmunication Systems & NETworkS","first-page":"424","article-title":"Video captioning using spatio-temporal graphs: An encoder-decoder approach","author":"Sharma","year":"2024"},{"key":"10.1016\/j.cviu.2026.104853_b26","series-title":"2025 17th International Conference on COMmunication Systems and NETworks (COMSNETS)","first-page":"802","article-title":"Indian sign language recognition and translation: an encoder-decoder approach","author":"Sharma","year":"2025"},{"issue":"7","key":"10.1016\/j.cviu.2026.104853_b27","doi-asserted-by":"crossref","first-page":"6662","DOI":"10.1109\/TCYB.2021.3079311","article-title":"Improving video temporal consistency via broad learning system","volume":"52","author":"Sheng","year":"2021","journal-title":"IEEE Trans. Cybern."},{"key":"10.1016\/j.cviu.2026.104853_b28","series-title":"2024 16th International Conference on COMmunication Systems & NETworkS (COMSNETS)","first-page":"273","article-title":"Palanam: a deep learning based childhood defense system","author":"Singh","year":"2024"},{"issue":"10","key":"10.1016\/j.cviu.2026.104853_b29","doi-asserted-by":"crossref","first-page":"3047","DOI":"10.1109\/TNNLS.2018.2851077","article-title":"From deterministic to generative: Multimodal stochastic RNNs for video captioning","volume":"30","author":"Song","year":"2018","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.cviu.2026.104853_b30","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110744","article-title":"Rethink video retrieval representation for video captioning","volume":"156","author":"Tian","year":"2024","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.cviu.2026.104853_b31","first-page":"1494","article-title":"Translating videos to natural language using deep recurrent neural networks","author":"Venugopalan","year":"2015","journal-title":"NAACL HLT 2015 - 2015 Conf. the North Am. Chapter of Assoc. Comput. Linguist.: Hum. Lang. Technol., Proc. Conf."},{"key":"10.1016\/j.cviu.2026.104853_b32","first-page":"8957","article-title":"Hierarchical attention network for image captioning","volume":"vol. 33","author":"Wang","year":"2019"},{"issue":"6","key":"10.1016\/j.cviu.2026.104853_b33","doi-asserted-by":"crossref","first-page":"509","DOI":"10.1016\/j.vrih.2023.06.003","article-title":"Learning adequate alignment and interaction for cross-modal retrieval","volume":"5","author":"Wang","year":"2023","journal-title":"Virtual Real. Intell. Hardw."},{"issue":"10","key":"10.1016\/j.cviu.2026.104853_b34","doi-asserted-by":"crossref","first-page":"4933","DOI":"10.1109\/TIP.2018.2846664","article-title":"Sequential Video VLAD: Training the Aggregation Locally and Temporally","volume":"27","author":"Xu","year":"2018","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.cviu.2026.104853_b35","doi-asserted-by":"crossref","unstructured":"Xu, J., Mei, T., Yao, T., Rui, Y., (2016).MSR-VTT: A Large Video Description Dataset for Bridging Video and Language - Microsoft Research.URL http:\/\/research.microsoft.com\/apps\/pubs\/default.aspx?id=264836.","DOI":"10.1109\/CVPR.2016.571"},{"issue":"1","key":"10.1016\/j.cviu.2026.104853_b36","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1109\/TMM.2019.2924576","article-title":"STAT: Spatial-temporal attention mechanism for video captioning","volume":"22","author":"Yan","year":"2019","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.cviu.2026.104853_b37","series-title":"Gl-rg: Global-local representation granularity for video captioning","author":"Yan","year":"2022"},{"key":"10.1016\/j.cviu.2026.104853_b38","doi-asserted-by":"crossref","unstructured":"Yao,\u00a0L., Torabi,\u00a0A., Cho,\u00a0K., Ballas,\u00a0N., Pal,\u00a0C., Larochelle,\u00a0H., Courville,\u00a0A., 2015. Describing videos by exploiting temporal structure. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 4507\u20134515.","DOI":"10.1109\/ICCV.2015.512"},{"key":"10.1016\/j.cviu.2026.104853_b39","doi-asserted-by":"crossref","unstructured":"Ye,\u00a0H., Li,\u00a0G., Qi,\u00a0Y., Wang,\u00a0S., Huang,\u00a0Q., Yang,\u00a0M.-H., 2022. Hierarchical modular network for video captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 17939\u201317948.","DOI":"10.1109\/CVPR52688.2022.01741"},{"key":"10.1016\/j.cviu.2026.104853_b40","doi-asserted-by":"crossref","unstructured":"Yu,\u00a0H., Wang,\u00a0J., Huang,\u00a0Z., Yang,\u00a0Y., Xu,\u00a0W., 2016. Video paragraph captioning using hierarchical recurrent neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 4584\u20134593.","DOI":"10.1109\/CVPR.2016.496"},{"key":"10.1016\/j.cviu.2026.104853_b41","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.111138","article-title":"Fully exploring object relation interaction and hidden state attention for video captioning","volume":"159","author":"Yuan","year":"2025","journal-title":"Pattern Recognit."},{"issue":"c","key":"10.1016\/j.cviu.2026.104853_b42","doi-asserted-by":"crossref","first-page":"6209","DOI":"10.1109\/TIP.2020.2988435","article-title":"Video Captioning with Object-Aware Spatio-Temporal Correlation and Aggregation","volume":"29","author":"Zhang","year":"2020","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.cviu.2026.104853_b43","doi-asserted-by":"crossref","unstructured":"Zheng,\u00a0Q., Wang,\u00a0C., Tao,\u00a0D., 2020. Syntax-aware action targeting for video captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 13096\u201313105.","DOI":"10.1109\/CVPR42600.2020.01311"},{"key":"10.1016\/j.cviu.2026.104853_b44","first-page":"1","article-title":"RESTHT: relation-enhanced spatial\u2013temporal hierarchical transformer for video captioning","author":"Zheng","year":"2024","journal-title":"Vis. Comput."},{"key":"10.1016\/j.cviu.2026.104853_b45","first-page":"3724","article-title":"Refined semantic enhancement towards frequency diffusion for video captioning","volume":"vol. 37","author":"Zhong","year":"2023"},{"key":"10.1016\/j.cviu.2026.104853_b46","series-title":"2019 Prognostics and System Health Management Conference (PHM-Qingdao)","first-page":"1","article-title":"A novel LSTM-GAN algorithm for time series anomaly detection","author":"Zhu","year":"2019"}],"container-title":["Computer Vision and Image Understanding"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1077314226002201?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1077314226002201?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T11:26:05Z","timestamp":1786620365000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1077314226002201"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":46,"alternative-id":["S1077314226002201"],"URL":"https:\/\/doi.org\/10.1016\/j.cviu.2026.104853","relation":{},"ISSN":["1077-3142"],"issn-type":[{"value":"1077-3142","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Semantic-Weighted Spatio-Temporal Graphs for Structured Video Understanding and Captioning","name":"articletitle","label":"Article Title"},{"value":"Computer Vision and Image Understanding","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.cviu.2026.104853","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"104853"}}