{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T20:56:46Z","timestamp":1771880206596,"version":"3.50.1"},"reference-count":71,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62371343"],"award-info":[{"award-number":["62371343"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003399","name":"Shanghai Municipality Science and Technology Commission","doi-asserted-by":"publisher","award":["2021SHZDZX0100"],"award-info":[{"award-number":["2021SHZDZX0100"]}],"id":[{"id":"10.13039\/501100003399","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1016\/j.neunet.2025.108523","type":"journal-article","created":{"date-parts":[[2025,12,25]],"date-time":"2025-12-25T00:11:00Z","timestamp":1766621460000},"page":"108523","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Visual dialog with semantic consistency: An external knowledge-driven approach"],"prefix":"10.1016","volume":"197","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1048-4574","authenticated-orcid":false,"given":"Shanshan","family":"Du","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9999-4871","authenticated-orcid":false,"given":"Hanli","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2025.108523_bib0001","series-title":"Proceedings of the IEEE\/CVF winter conference on applications of computer vision (WACV)","first-page":"5805","article-title":"Vd-gr: Boosting visual dialog with cascaded spatial-temporal multi-modal graphs","author":"Abdessaied","year":"2024"},{"key":"10.1016\/j.neunet.2025.108523_bib0002","series-title":"Proceedings of the 58th annual meeting of the association for computational linguistics","first-page":"8182","article-title":"History for visual dialog: Do we really need it?","author":"Agarwal","year":"2020"},{"key":"10.1016\/j.neunet.2025.108523_bib0003","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"2425","article-title":"Vqa: Visual question answering","author":"Antol","year":"2015"},{"key":"10.1016\/j.neunet.2025.108523_bib0004","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"18103","article-title":"UTC: A unified transformer with inter-task contrastive learning for visual dialog","author":"Chen","year":"2022"},{"key":"10.1016\/j.neunet.2025.108523_bib0005","series-title":"Proceedings of the 59th annual meeting of the association for computational linguistics and the 11th international joint conference on natural language processing","first-page":"230","article-title":"GoG: Relation-aware graph-over-graph network for visual dialog","author":"Chen","year":"2021"},{"key":"10.1016\/j.neunet.2025.108523_bib0006","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"326","article-title":"Visual dialog","author":"Das","year":"2017"},{"key":"10.1016\/j.neunet.2025.108523_bib0007","doi-asserted-by":"crossref","first-page":"9095","DOI":"10.1109\/TMM.2024.3385997","article-title":"Hybrid graph reasoning with dynamic interaction for visual dialog","volume":"26","author":"Du","year":"2024","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.1016\/j.neunet.2025.108523_bib0008","series-title":"Proceedings of the british machine vision conference 2018","first-page":"1","article-title":"Vse++: Improving visual-semantic embeddings with hard negatives","author":"Faghri","year":"2018"},{"key":"10.1016\/j.neunet.2025.108523_bib0009","series-title":"Proceedings of the 57th annual meeting of the association for computational linguistics","first-page":"6463","article-title":"Multi-step reasoning via recurrent dual attention for visual dialog","author":"Gan","year":"2019"},{"key":"10.1016\/j.neunet.2025.108523_bib0010","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1007\/978-3-642-24797-2_4","article-title":"Long short-term memory","volume":"385","author":"Graves","year":"2012","journal-title":"Supervised Sequence Labelling with Recurrent Neural Networks"},{"key":"10.1016\/j.neunet.2025.108523_bib0011","series-title":"Proceedings of the twenty-eighth international joint conference on artificial intelligence","first-page":"4989","article-title":"Dual visual attention network for visual dialog","author":"Guo","year":"2019"},{"key":"10.1016\/j.neunet.2025.108523_bib0012","doi-asserted-by":"crossref","first-page":"6655","DOI":"10.1109\/TIP.2020.2992888","article-title":"Textual-visual reference-aware attention network for visual dialog","volume":"29","author":"Guo","year":"2020","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.1016\/j.neunet.2025.108523_bib0013","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"10055","article-title":"Iterative context-aware graph inference for visual dialog","author":"Guo","year":"2020"},{"key":"10.1016\/j.neunet.2025.108523_bib0014","doi-asserted-by":"crossref","first-page":"10924","DOI":"10.1109\/TMM.2024.3416669","article-title":"Efficient cross-modal video retrieval with meta-optimized frames","volume":"26","author":"Han","year":"2024","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.1016\/j.neunet.2025.108523_bib0015","series-title":"Proceedings of the 58th annual meeting of the association for computational linguistics","first-page":"1874","article-title":"Visual-textual alignment for graph inference in visual dialog","author":"Jiang","year":"2020"},{"key":"10.1016\/j.neunet.2025.108523_bib0016","series-title":"Proceedings of the 28th ACM international conference on multimedia","first-page":"1265","article-title":"Kbgn: Knowledge-bridge graph network for adaptive vision-text reasoning in visual dialogue","author":"Jiang","year":"2020"},{"key":"10.1016\/j.neunet.2025.108523_bib0017","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"11125","article-title":"Dualvd: An adaptive dual encoding model for deep visual understanding in visual dialogue","author":"Jiang","year":"2020"},{"key":"10.1016\/j.neunet.2025.108523_bib0018","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"3668","article-title":"Image retrieval using scene graphs","author":"Johnson","year":"2015"},{"key":"10.1016\/j.neunet.2025.108523_bib0019","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"6746","article-title":"The dialog must go on: Improving visual dialog via generative self-training","author":"Kang","year":"2023"},{"key":"10.1016\/j.neunet.2025.108523_bib0020","series-title":"Proceedings of the 2019 conference on empirical methods in natural language processing and the 9th international joint conference on natural language processing","first-page":"2024","article-title":"Dual attention networks for visual reference resolution in visual dialog","author":"Kang","year":"2019"},{"key":"10.1016\/j.neunet.2025.108523_bib0021","series-title":"Proceedings of the 2019 conference of the north american chapter of the association for computational linguistics: human language technologies","first-page":"4171","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Kenton","year":"2019"},{"key":"10.1016\/j.neunet.2025.108523_bib0022","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"18381","article-title":"Bok-vqa: Bilingual outside knowledge-based visual question answering via graph representation pretraining","volume":"vol. 38","author":"Kim","year":"2024"},{"key":"10.1016\/j.neunet.2025.108523_bib0023","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"13193","article-title":"Structure-aware multimodal sequential learning for visual dialog","volume":"vol. 38","author":"Kim","year":"2024"},{"key":"10.1016\/j.neunet.2025.108523_bib0024","series-title":"Proceedings of the 3rd international conference on learning representations","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2015"},{"key":"10.1016\/j.neunet.2025.108523_bib0025","series-title":"Proceedings of the 5th international conference on learning representations","article-title":"Semi-supervised classification with graph convolutional networks","author":"Kipf","year":"2017"},{"key":"10.1016\/j.neunet.2025.108523_bib0026","series-title":"Proceedings of the european conference on computer vision","first-page":"153","article-title":"Visual coreference resolution in visual dialog using neural module networks","author":"Kottur","year":"2018"},{"issue":"1","key":"10.1016\/j.neunet.2025.108523_bib0027","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","article-title":"Visual genome: Connecting language and vision using crowdsourced dense image annotations","volume":"123","author":"Krishna","year":"2017","journal-title":"International Journal of Computer Vision"},{"issue":"9","key":"10.1016\/j.neunet.2025.108523_bib0028","doi-asserted-by":"crossref","first-page":"4245","DOI":"10.1109\/TKDE.2020.3038670","article-title":"Few-shot named entity recognition via meta-learning","volume":"34","author":"Li","year":"2020","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"issue":"10","key":"10.1016\/j.neunet.2025.108523_bib0029","doi-asserted-by":"crossref","first-page":"14396","DOI":"10.1109\/TNNLS.2023.3278938","article-title":"Few-shot relation extraction with dual graph neural network interaction","volume":"35","author":"Li","year":"2023","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"issue":"3","key":"10.1016\/j.neunet.2025.108523_bib0030","first-page":"3072","article-title":"Sequence labeling with meta-learning","volume":"35","author":"Li","year":"2021","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"issue":"7","key":"10.1016\/j.neunet.2025.108523_bib0031","doi-asserted-by":"crossref","first-page":"8634","DOI":"10.1109\/TPAMI.2022.3230934","article-title":"Knowledge-enriched attention network with group-wise semantic for visual storytelling","volume":"45","author":"Li","year":"2023","journal-title":"IEEE Transactions on Pattern Analysis And Machine Intelligence"},{"key":"10.1016\/j.neunet.2025.108523_bib0032","doi-asserted-by":"crossref","first-page":"1867","DOI":"10.1109\/TMM.2023.3289753","article-title":"Commonsense-guided semantic and relational consistencies for image-text retrieval","volume":"26","author":"Li","year":"2023","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.1016\/j.neunet.2025.108523_bib0033","doi-asserted-by":"crossref","first-page":"1639","DOI":"10.1109\/TMM.2023.3284594","article-title":"Counterfactual visual dialog: Robust commonsense knowledge learning from unbiased training","volume":"26","author":"Liu","year":"2023","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.1016\/j.neunet.2025.108523_bib0034","doi-asserted-by":"crossref","first-page":"1639","DOI":"10.1109\/TMM.2023.3284594","article-title":"Counterfactual visual dialog: Robust commonsense knowledge learning from unbiased training","volume":"26","author":"Liu","year":"2023","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.1016\/j.neunet.2025.108523_bib0035","series-title":"Proceedings of the 33rd international conference on neural information processing systems","first-page":"1","article-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","author":"Lu","year":"2019"},{"key":"10.1016\/j.neunet.2025.108523_bib0036","series-title":"Proceedings of the 31st international conference on neural information processing systems","first-page":"314","article-title":"Best of both worlds: Transferring knowledge from discriminative learning to a generative visual dialog model","author":"Lu","year":"2017"},{"key":"10.1016\/j.neunet.2025.108523_bib0037","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"24741","article-title":"Knowledge editing with dynamic knowledge graphs for multi-hop question answering","volume":"vol. 39","author":"Lu","year":"2025"},{"key":"10.1016\/j.neunet.2025.108523_bib0038","series-title":"Proceedings of the european conference on computer vision","first-page":"336","article-title":"Large-scale pretraining for visual dialog: A simple state-of-the-art baseline","author":"Murahari","year":"2020"},{"key":"10.1016\/j.neunet.2025.108523_bib0039","series-title":"Proceedings of the European conference on computer vision","first-page":"223","article-title":"Efficient attention mechanism for visual dialog that can handle all the interactions between multiple inputs","author":"Nguyen","year":"2020"},{"key":"10.1016\/j.neunet.2025.108523_bib0040","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"6679","article-title":"Recursive visual attention in visual dialog","author":"Niu","year":"2019"},{"key":"10.1016\/j.neunet.2025.108523_bib0041","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"4640","article-title":"SelfgraphVQA: A self-supervised graph neural network for scene-based question answering","author":"de Oliveira Souza","year":"2023"},{"key":"10.1016\/j.neunet.2025.108523_bib0042","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106560","article-title":"Robust visual question answering via polarity enhancement and contrast","volume":"179","author":"Peng","year":"2024","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2025.108523_bib0043","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"10860","article-title":"Two causal principles for improving visual dialog","author":"Qi","year":"2020"},{"issue":"6","key":"10.1016\/j.neunet.2025.108523_bib0044","doi-asserted-by":"crossref","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume":"39","author":"Ren","year":"2017","journal-title":"IEEE Transactions on Pattern Analysis And Machine Intelligence"},{"key":"10.1016\/j.neunet.2025.108523_bib0045","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"2039","article-title":"Factor graph attention","author":"Schwartz","year":"2019"},{"key":"10.1016\/j.neunet.2025.108523_bib0046","series-title":"Proceedings of the 31st international conference on neural information processing systems","first-page":"3722","article-title":"Visual reference resolution using attention memory for visual dialog","author":"Seo","year":"2017"},{"key":"10.1016\/j.neunet.2025.108523_bib0047","series-title":"Proceedings of the 56th annual meeting of the association for computational linguistics","first-page":"2556","article-title":"Conceptual captions: A cleaned, hypernymed, image alt-text dataset for automatic image captioning","author":"Sharma","year":"2018"},{"issue":"11","key":"10.1016\/j.neunet.2025.108523_bib0048","doi-asserted-by":"crossref","first-page":"6962","DOI":"10.1109\/TKDE.2024.3399746","article-title":"Scene-driven multimodal knowledge graph construction for embodied AI","volume":"36","author":"Song","year":"2024","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"10.1016\/j.neunet.2025.108523_bib0049","series-title":"Proceedings of the AAAI conference on artificial intelligence","article-title":"Conceptnet 5.5: An open multilingual graph of general knowledge","volume":"vol. 31","author":"Speer","year":"2017"},{"key":"10.1016\/j.neunet.2025.108523_bib0050","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2023.111251","article-title":"Sdgin: Structure-aware dual-level graph interactive network with semantic roles for visual dialog","volume":"286","author":"Sun","year":"2024","journal-title":"Knowledge-Based Systems"},{"key":"10.1016\/j.neunet.2025.108523_bib0051","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"3716","article-title":"Unbiased scene graph generation from biased training","author":"Tang","year":"2020"},{"key":"10.1016\/j.neunet.2025.108523_bib0052","unstructured":"G. Team, Mesnard, T., Hardin, C., Dadashi, R., Bhupatiraju, S., Pathak, S., Sifre, L., Rivi\u00e8re, M., Kale, M. S., Love, J. et al. (2024). Gemma: Open models based on gemini research and technology. arXiv: 2403.08295."},{"key":"10.1016\/j.neunet.2025.108523_bib0053","doi-asserted-by":"crossref","first-page":"8609","DOI":"10.1109\/TMM.2024.3380259","article-title":"Cross modality bias in visual question answering: A causal view with possible worlds VQA","volume":"26","author":"Vosoughi","year":"2024","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.1016\/j.neunet.2025.108523_bib0054","series-title":"Proceedings of the 2023 IEEE international conference on multimedia and expo","first-page":"138","article-title":"Scene graph based fusion network for image-text retrieval","author":"Wang","year":"2023"},{"key":"10.1016\/j.neunet.2025.108523_bib0055","unstructured":"Wang, P., Bai, S., Tan, S., Wang, S., Fan, Z., Bai, J., Chen, K., Liu, X., Wang, J., Ge, W. et al. (2024). Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution. arXiv: 2409.12191."},{"key":"10.1016\/j.neunet.2025.108523_bib0056","unstructured":"Wang, S., Meng, Y., Li, X., Sun, X., Ouyang, R., & Li, J. (2021). Openvidial 2.0: A larger-scale, open-domain dialogue generation dataset with visual contexts. arXiv: 2109.12761."},{"key":"10.1016\/j.neunet.2025.108523_bib0057","series-title":"Proceedings of the 2020 conference on empirical methods in natural language processing","first-page":"3325","article-title":"VD-BERT: A unified vision and dialog transformer with bert","author":"Wang","year":"2020"},{"key":"10.1016\/j.neunet.2025.108523_bib0058","series-title":"Proceedings of the 30th ACM international conference on multimedi","first-page":"4625","article-title":"Unified multimodal model with unlikelihood training for visual dialog","author":"Wang","year":"2022"},{"key":"10.1016\/j.neunet.2025.108523_bib0059","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106519","article-title":"Mining core information by evaluating semantic importance for unpaired image captioning","volume":"179","author":"Wei","year":"2024","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2025.108523_bib0060","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"6609","article-title":"Unified visual-semantic embeddings: Bridging vision and language with structured meaning representations","author":"Wu","year":"2019"},{"key":"10.1016\/j.neunet.2025.108523_bib0061","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"6106","article-title":"Are you talking to me? reasoned visual dialog generation through adversarial learning","author":"Wu","year":"2018"},{"key":"10.1016\/j.neunet.2025.108523_bib0062","series-title":"Proceedings of the 31st ACM international conference on multimedia","first-page":"5330","article-title":"External knowledge dynamic modeling for image-text retrieval","author":"Yang","year":"2023"},{"key":"10.1016\/j.neunet.2025.108523_bib0063","doi-asserted-by":"crossref","first-page":"220","DOI":"10.1109\/TIP.2020.3034494","article-title":"Learning dual encoding model for adaptive visual understanding in visual dialogue","volume":"30","author":"Yu","year":"2020","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.1016\/j.neunet.2025.108523_bib0064","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"5831","article-title":"Neural motifs: Scene graph parsing with global context","author":"Zellers","year":"2018"},{"key":"10.1016\/j.neunet.2025.108523_bib0065","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106744","article-title":"Center-enhanced video captioning model with multimodal semantic alignment","volume":"180","author":"Zhang","year":"2024","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2025.108523_bib0066","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"4600","article-title":"Reasoning with multi-structure commonsense knowledge in visual dialog","author":"Zhang","year":"2022"},{"key":"10.1016\/j.neunet.2025.108523_bib0067","series-title":"Proceedings of the 2023 ACM international conference on multimedia retrieval","first-page":"253","article-title":"Knowledge-aware causal inference network for visual dialog","author":"Zhang","year":"2023"},{"issue":"2","key":"10.1016\/j.neunet.2025.108523_bib0068","doi-asserted-by":"crossref","first-page":"861","DOI":"10.1109\/TCSVT.2022.3207228","article-title":"Heterogeneous knowledge network for visual dialog","volume":"33","author":"Zhao","year":"2023","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10.1016\/j.neunet.2025.108523_bib0069","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1016\/j.neucom.2021.10.121","article-title":"You should know more: Learning external knowledge for visual dialog","volume":"488","author":"Zhao","year":"2022","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neunet.2025.108523_bib0070","series-title":"Proceedings of the 35th IEEE international conference on tools with artificial intelligence","first-page":"805","article-title":"Modeling intra-and inter-modal alignment with optimal transport for visual dialog","author":"Zheng","year":"2023"},{"key":"10.1016\/j.neunet.2025.108523_bib0071","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"6669","article-title":"Reasoning visual dialogs with structural and partial observations","author":"Zheng","year":"2019"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608025014042?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608025014042?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T19:56:41Z","timestamp":1771876601000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608025014042"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":71,"alternative-id":["S0893608025014042"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2025.108523","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2026,5]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Visual dialog with semantic consistency: An external knowledge-driven approach","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2025.108523","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"108523"}}