{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T22:13:42Z","timestamp":1757628822690,"version":"3.44.0"},"reference-count":69,"publisher":"Springer Science and Business Media LLC","issue":"29","license":[{"start":{"date-parts":[[2025,1,28]],"date-time":"2025-01-28T00:00:00Z","timestamp":1738022400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,28]],"date-time":"2025-01-28T00:00:00Z","timestamp":1738022400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"No funding","award":["0000-0002-7988-3349"],"award-info":[{"award-number":["0000-0002-7988-3349"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"DOI":"10.1007\/s11042-024-20235-6","type":"journal-article","created":{"date-parts":[[2025,1,28]],"date-time":"2025-01-28T01:43:32Z","timestamp":1738028612000},"page":"35727-35759","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Leveraging ensemble deep models and llm for visual polysemy and word sense disambiguation"],"prefix":"10.1007","volume":"84","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7988-3349","authenticated-orcid":false,"given":"Insaf","family":"Setitra","sequence":"first","affiliation":[]},{"given":"Praboda","family":"Rajapaksha","sequence":"additional","affiliation":[]},{"given":"Aung Kaung","family":"Myat","sequence":"additional","affiliation":[]},{"given":"Noel","family":"Crespi","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,1,28]]},"reference":[{"key":"20235_CR1","unstructured":"Kiros R, Salakhutdinov R, Zemel R (2014) Multimodal neural language models. In: Xing EP, Jebara T (eds.) Proceedings of the 31st International Conference on Machine Learning. Proceed Machine Learn Res vol 32, pp 595\u2013603. PMLR, Bejing, China"},{"key":"20235_CR2","doi-asserted-by":"crossref","unstructured":"Mnih A, Hinton G (2007) Three new graphical models for statistical language modelling. In: Proceedings of the 24th International Conference on Machine Learning. ICML \u201907, pp 641\u2013648. Associate Comput Machinery, New York, NY, USA","DOI":"10.1145\/1273496.1273577"},{"key":"20235_CR3","unstructured":"Grubinger M, Clough PD, M\u00fcller H, Deselaers T (2006) The iapr tc-12 benchmark: A new evaluation resource for visual information systems"},{"key":"20235_CR4","doi-asserted-by":"crossref","unstructured":"Berg T, Berg A, Shih J (2010) Automatic attribute discovery and characterization from noisy web data 6311:663\u2013676","DOI":"10.1007\/978-3-642-15549-9_48"},{"key":"20235_CR5","unstructured":"Ordonez V, Kulkarni G, Berg TL (2011) Im2text: Describing images using 1 million captioned photographs. In: Neural Information Processing Systems (NIPS)"},{"key":"20235_CR6","doi-asserted-by":"publisher","unstructured":"Vinyals O, Toshev A, Bengio S, Erhan D (2015) Show and tell: A neural image caption generator, pp 3156\u20133164 . https:\/\/doi.org\/10.1109\/CVPR.2015.7298935","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"20235_CR7","unstructured":"Xu K, Ba JL, Kiros R, Cho K, Courville A, Salakhutdinov R, Zemel RS, Bengio Y (2015) Show, attend and tell: Neural image caption generation with visual attention. In: Proceedings of the 32nd International Conference on International Conference on Machine Learning - Volume 37. ICML\u201915, pp 2048\u20132057. JMLR.org, ???"},{"issue":"1","key":"20235_CR8","first-page":"853","volume":"47","author":"M Hodosh","year":"2013","unstructured":"Hodosh M, Young P, Hockenmaier J (2013) Framing image description as a ranking task: Data, models and evaluation metrics. J Artif Int Res 47(1):853\u2013899","journal-title":"J Artif Int Res"},{"key":"20235_CR9","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1162\/tacl_a_00166","volume":"2","author":"P Young","year":"2014","unstructured":"Young P, Lai A, Hodosh M, Hockenmaier J (2014) From image descriptions to visual denotations: New similarity metrics for semantic inference over event descriptions. Trans Associate Comput Linguis 2:67\u201378","journal-title":"Trans Associate Comput Linguis"},{"key":"20235_CR10","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision - ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin T-Y, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Doll\u00e1r P, Zitnick CL (2014) Microsoft coco: Common objects in context. In: Fleet D, Pajdla T, Schiele B, Tuytelaars T (eds) Computer Vision - ECCV 2014. Springer, Cham, pp 740\u2013755"},{"key":"20235_CR11","doi-asserted-by":"crossref","unstructured":"Denkowski M, Lavie A (2014) Meteor universal: Language specific translation evaluation for any target language. In: Proceedings of the Ninth Workshop on Statistical Machine Translation, pp 376\u2013380. Associate Comput Linguis, Baltimore, Maryland, USA","DOI":"10.3115\/v1\/W14-3348"},{"key":"20235_CR12","doi-asserted-by":"crossref","unstructured":"Johnson J, Karpathy A, Fei-Fei L (2016) Densecap: Fully convolutional localization networks for dense captioning. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 4565\u20134574. IEEE Comp Society, Los Alamitos, CA, USA","DOI":"10.1109\/CVPR.2016.494"},{"key":"20235_CR13","unstructured":"Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition, Comput Biologic Learn Society, ??? pp 1\u201314"},{"key":"20235_CR14","unstructured":"Ren S, He K, Girshick R, Sun J (2015) Faster r-cnn: Towards real-time object detection with region proposal networks. In: Cortes, C., Lawrence, N., Lee, D., Sugiyama, M., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol 28. Curran Associates, Inc., ???"},{"key":"20235_CR15","doi-asserted-by":"publisher","unstructured":"Girshick R (2015) Fast r-cnn. In: 2015 IEEE International Conference on Computer Vision (ICCV), pp 1440\u20131448 . https:\/\/doi.org\/10.1109\/ICCV.2015.169","DOI":"10.1109\/ICCV.2015.169"},{"key":"20235_CR16","unstructured":"Gregor K, Danihelka I, Graves A, Rezende DJ, Wierstra D (2015) Draw: A recurrent neural network for image generation. arXiv:1502.04623"},{"issue":"1","key":"20235_CR17","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","volume":"123","author":"R Krishna","year":"2017","unstructured":"Krishna R, Zhu Y, Groth O, Johnson J, Hata K, Kravitz J, Chen S, Kalantidis Y, Li L-J, Shamma DA, Bernstein MS, Fei-Fei L (2017) Visual genome: Connecting language and vision using crowdsourced dense image annotations. Int J Comput Vision 123(1):32\u201373. https:\/\/doi.org\/10.1007\/s11263-016-0981-7","journal-title":"Int J Comput Vision"},{"key":"20235_CR18","doi-asserted-by":"publisher","unstructured":"You Q, Jin H, Wang Z, Fang C, Luo J (2016) Image captioning with semantic attention. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 4651\u20134659. IEEE Comput Society, Los Alamitos, CA, USA . https:\/\/doi.org\/10.1109\/CVPR.2016.503","DOI":"10.1109\/CVPR.2016.503"},{"key":"20235_CR19","unstructured":"Chen X, Fang H, Lin T-Y, Vedantam R, Gupta S, Dollar P, Zitnick C (2015) Microsoft coco captions: Data collection and evaluation server"},{"key":"20235_CR20","doi-asserted-by":"publisher","unstructured":"Yan S, Xie Y, Wu F, Smith JS, Lu W, Zhang B (2020) Image captioning via hierarchical attention mechanism and policy gradient optimization. Signal Process 167(C) https:\/\/doi.org\/10.1016\/j.sigpro.2019.107329","DOI":"10.1016\/j.sigpro.2019.107329"},{"key":"20235_CR21","doi-asserted-by":"crossref","unstructured":"Song Z, Zhou X, Mao Z, Tan J (2020) Image captioning with context-aware auxiliary guidance. In: AAAI Conference on Artificial Intelligence","DOI":"10.1609\/aaai.v35i3.16361"},{"key":"20235_CR22","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1007\/978-3-031-20059-5_10","volume-title":"Computer Vision - ECCV 2022","author":"V-Q Nguyen","year":"2022","unstructured":"Nguyen V-Q, Suganuma M, Okatani T (2022) Grit: Faster and better image captioning transformer using dual visual features. In: Avidan S, Brostow G, Ciss\u00e9 M, Farinella GM, Hassner T (eds) Computer Vision - ECCV 2022. Springer, Cham, pp 167\u2013184"},{"key":"20235_CR23","doi-asserted-by":"publisher","unstructured":"Zhu X, Su W, Lu L, Li B, Wang X, Dai J (2020) Deformable DETR: Deformable Transformers for End-to-End Object Detection. arXiv e-prints, 2010\u201304159. https:\/\/doi.org\/10.48550\/arXiv.2010.04159arXiv:2010.04159","DOI":"10.48550\/arXiv.2010.04159"},{"key":"20235_CR24","doi-asserted-by":"publisher","unstructured":"Liu Z, Lin Y, Cao Y, Hu H, Wei Y, Zhang Z, Lin S, Guo B (2021) Swin transformer: Hierarchical vision transformer using shifted windows. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV). IEEE Computer Society, Los Alamitos, CA, USA . https:\/\/doi.org\/10.1109\/ICCV48922.2021.00986","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"20235_CR25","unstructured":"Alabduljabbar GM, Benhidour H, Kerrache S (2022) Image captioning based on feature refinement and reflective decoding. arXiv:2206.07986"},{"key":"20235_CR26","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2015) Deep residual learning for image recognition. 2016 IEEE Conf Comp Vision and Pattern Recog (CVPR), 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"20235_CR27","doi-asserted-by":"crossref","unstructured":"Anderson P, He X, Buehler C, Teney D, Johnson M, Gould S, Zhang L (2017) Bottom-up and top-down attention for image captioning and visual question answering. 2018 IEEE\/CVF Conf Comp Vision and Pattern Recog 6077\u20136086","DOI":"10.1109\/CVPR.2018.00636"},{"key":"20235_CR28","doi-asserted-by":"crossref","unstructured":"Ke L, Pei W, Li R, Shen X, Tai Y-W (2019) Reflective decoding network for image captioning. 2019 IEEE\/CVF Int Conf Comp Vis (ICCV), 8887\u20138896","DOI":"10.1109\/ICCV.2019.00898"},{"key":"20235_CR29","doi-asserted-by":"publisher","first-page":"664","DOI":"10.1109\/TPAMI.2016.2598339","volume":"39","author":"A Karpathy","year":"2014","unstructured":"Karpathy A, Fei-Fei L (2014) Deep visual-semantic alignments for generating image descriptions. IEEE Trans Pattern Anal Mach Intell 39:664\u2013676","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"20235_CR30","doi-asserted-by":"crossref","unstructured":"Wang Q, Mao Y, Wang J, Yu H, Nie S, Wang S, Feng F, Huang L, Quan X, Xu Z, Liu D (2023) APrompt: Attention prompt tuning for efficient adaptation of pre-trained language models. In: The 2023 Conference on Empirical Methods in Natural Language Processing . https:\/\/openreview.net\/forum?id=RSuN6p3wXR","DOI":"10.18653\/v1\/2023.emnlp-main.567"},{"key":"20235_CR31","unstructured":"Han C, Wang Q, Cui Y, Wang W, Huang L, Qi S, Liu D (2024) Facing the elephant in the room: Visual prompt tuning or full finetuning? In: The Twelfth International Conference on Learning Representations . https:\/\/openreview.net\/forum?id=bJx4iOIOxn"},{"key":"20235_CR32","unstructured":"Liang JC, Cui Y, Wang Q, Geng T, Wang W, Liu D (2023) Clusterformer: Clustering as a universal visual learner. In: Neural Information Processing Systems (NeurIPS)"},{"key":"20235_CR33","unstructured":"Han C, Liang J, Wang Q, Rabbani M, Dianat SA, Rao RM, Wu YN, Liu D (2024) Image translation as diffusion visual programmers. arXiv:2401.09742"},{"key":"20235_CR34","doi-asserted-by":"crossref","unstructured":"Wang J, Sun G, Wang P, Liu D, Dianat S, Rabbani M, Rao R, Tao Z (2024) Text is mass: Modeling as stochastic embedding for text-video retrieval. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","DOI":"10.1109\/CVPR52733.2024.01566"},{"key":"20235_CR35","doi-asserted-by":"crossref","unstructured":"Li X, Feng X, Hu S, Wu M, Zhang D, Zhang J, Huang K (2024) Dtllm-vlt: Diverse text generation for visual language tracking based on llm. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, pp 7283\u20137292","DOI":"10.1109\/CVPRW63382.2024.00724"},{"key":"20235_CR36","unstructured":"Qin Z, Han C, Wang Q, Nie X, Yin Y, Lu X (2023) Unified 3d segmenter as prototypical classifiers. In: Thirty-seventh Conference on Neural Information Processing Systems . https:\/\/openreview.net\/forum?id=Q6zd1hr7sD"},{"key":"20235_CR37","unstructured":"Wang W, Han C, Zhou T, Liu D (2023) Visual recognition with deep nearest centroids. In: International Conference on Learning Representations (ICLR)"},{"key":"20235_CR38","doi-asserted-by":"crossref","unstructured":"Raganato A, Calixto I, Ushio A, Camacho-Collados J, Pilehvar MT (2023) SemEval-2023 Task 1: Visual Word Sense Disambiguation. In: Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023). Associate Comput Linguis, Toronto, Canada","DOI":"10.18653\/v1\/2023.semeval-1.308"},{"key":"20235_CR39","unstructured":"Radford A, Kim JW, Hallacy C, Ramesh A, Goh G, Agarwal S, Sastry G, Askell A, Mishkin P, Clark J, Krueger G, Sutskever I (2021) Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning"},{"key":"20235_CR40","doi-asserted-by":"crossref","unstructured":"Reimers N, Gurevych I (2019) Sentence-bert: Sentence embeddings using siamese bert-networks. In: Conference on Empirical Methods in Natural Language Processing","DOI":"10.18653\/v1\/D19-1410"},{"key":"20235_CR41","doi-asserted-by":"crossref","unstructured":"Wolf T, Debut L, Sanh V, Chaumond J, Delangue C, Moi A, Cistac P, Rault T, Louf R, Funtowicz M, Brew J (2019) Transformers: State-of-the-art natural language processing. In: Conference on Empirical Methods in Natural Language Processing","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"20235_CR42","doi-asserted-by":"crossref","unstructured":"Sennrich R, Haddow B, Birch A (2015) Improving neural machine translation models with monolingual data. arXiv:1511.06709","DOI":"10.18653\/v1\/P16-1009"},{"key":"20235_CR43","doi-asserted-by":"crossref","unstructured":"Rombach R, Blattmann A, Lorenz D, Esser P, Ommer B (2021) High-resolution image synthesis with latent diffusion models. 2022 IEEE\/CVF Conf Comp Vis Pattern Recog (CVPR), 10674\u201310685","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"20235_CR44","doi-asserted-by":"crossref","unstructured":"Yang Q, Li Y, Wang X, Li S, Hao T (2023) Tam of scnu at semeval-2023 task 1: Fcll: A fine-grained contrastive language-image learning model for cross-language visual word sense disambiguation. In: International Workshop on Semantic Evaluation","DOI":"10.18653\/v1\/2023.semeval-1.70"},{"key":"20235_CR45","doi-asserted-by":"crossref","unstructured":"Zhang X, Zhen T, Zhang J, Wang Y, Liu S (2023) Srcb at semeval-2023 task 1: Prompt based and cross-modal retrieval enhanced visual word sense disambiguation. In: International Workshop on Semantic Evaluation","DOI":"10.18653\/v1\/2023.semeval-1.60"},{"key":"20235_CR46","unstructured":"Schuhmann C, Vencu R, Beaumont R, Kaczmarczyk R, Mullis C, Katta A, Coombes T, Jitsev J, Komatsuzaki A (2021) Laion-400m: Open dataset of clip-filtered 400 million image-text pairs. arXiv:2111.02114"},{"key":"20235_CR47","doi-asserted-by":"crossref","unstructured":"Cherti M, Beaumont R, Wightman R, Wortsman M, Ilharco G, Gordon C, Schuhmann C, Schmidt L, Jitsev J (2022) Reproducible scaling laws for contrastive language-image learning. arXiv:2212.07143","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"20235_CR48","doi-asserted-by":"crossref","unstructured":"Dadas S (2023) Opi at semeval-2023 task 1: Image-text embeddings and multimodal information retrieval for visual word sense disambiguation. arXiv:2304.07127","DOI":"10.18653\/v1\/2023.semeval-1.22"},{"key":"20235_CR49","doi-asserted-by":"crossref","unstructured":"Patil R, Patel P, Patel C, Verma M (2023) Rahul patil at semeval-2023 task 1: V-wsd: Visual word sense disambiguation. In: International Workshop on Semantic Evaluation","DOI":"10.18653\/v1\/2023.semeval-1.176"},{"key":"20235_CR50","doi-asserted-by":"crossref","unstructured":"Rombach R, Blattmann A, Lorenz D, Esser P, Ommer B (2022) High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 10684\u201310695","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"20235_CR51","doi-asserted-by":"publisher","unstructured":"Sun Z, Yao Y, Xiao J, Zhang L, Zhang J, Tang Z (2020) Exploiting textual queries for dynamically visual disambiguation. Pattern Recognition. 110, https:\/\/doi.org\/10.1016\/j.patcog.2020.107620","DOI":"10.1016\/j.patcog.2020.107620"},{"key":"20235_CR52","first-page":"63","volume":"2","author":"I Sumartono","year":"2016","unstructured":"Sumartono I, Siahaan APU, Arpan A (2016) Base64 character encoding and decoding modeling. Int J Recent Trends in Eng Res 2:63\u201368","journal-title":"Int J Recent Trends in Eng Res"},{"key":"20235_CR53","doi-asserted-by":"crossref","unstructured":"Xu F, Uszkoreit H, Du Y, Fan W, Zhao D, Zhu J (2019) Explainable ai: A brief survey on history, research areas, approaches and challenges. In: Natural Language Processing and Chinese Computing . https:\/\/api.semanticscholar.org\/CorpusID:203620028","DOI":"10.1007\/978-3-030-32236-6_51"},{"key":"20235_CR54","unstructured":"Wu X, Zhao H, Zhu Y, Shi Y, Yang F, Liu T, Zhai X, Yao W, Li J, Du M, Liu N (2024) Usable xai: 10 strategies towards exploiting explainability in the llm era. arXiv:2403.08946"},{"key":"20235_CR55","doi-asserted-by":"crossref","unstructured":"Audemard G, Bellart S, Bounia L, Koriche F, Lagniez J-M, Marquis P (2021) On the computational intelligibility of boolean classifiers. 18th Int Conf Principles of Knowl Represent Reason","DOI":"10.24963\/kr.2021\/8"},{"key":"20235_CR56","doi-asserted-by":"crossref","unstructured":"Darwiche A, Hirth A (2020) On the reasons behind decisions. In: Proc. of ECAI\u201920, pp 712\u2013720","DOI":"10.3233\/FAIA200158"},{"key":"20235_CR57","doi-asserted-by":"publisher","DOI":"10.1016\/j.datak.2022.102088","volume":"142","author":"G Audemard","year":"2022","unstructured":"Audemard G, Bellart S, Bounia L, Koriche F, Lagniez J-M, Marquis P (2022) On the explanatory power of boolean decision trees. Data Knowl Eng 142:102088","journal-title":"Data Knowl Eng"},{"key":"20235_CR58","doi-asserted-by":"crossref","unstructured":"Audemard G, Bellart S, Bounia L, Koriche F, Lagniez J-M, Marquis P (2022) Trading complexity for sparsity in random forest explanations. AAAI Conf Artif Intell","DOI":"10.1609\/aaai.v36i5.20484"},{"key":"20235_CR59","unstructured":"Audemard G, Bellart S, Bounia L, Lagniez J-M, Marquis P, Szczepanski N (2023) Pyxai : calculer en python des explications pour des mod\u00e8les d\u2019apprentissage supervis\u00e9. In: Extraction et la Gestion des Connaissances (EGC) . https:\/\/api.semanticscholar.org\/CorpusID:256665991"},{"key":"20235_CR60","first-page":"12","volume":"24","author":"S Sperandei","year":"2014","unstructured":"Sperandei S (2014) Understanding logistic regression analysis. Biochemia medica. 24:12\u20138","journal-title":"Understanding logistic regression analysis. Biochemia medica."},{"key":"20235_CR61","unstructured":"Bounia L, Koriche F (2023) Approximating probabilistic explanations via supermodular minimization. In: Conference on Uncertainty in Artificial Intelligence"},{"key":"20235_CR62","doi-asserted-by":"crossref","unstructured":"Ribeiro MT, Singh S, Guestrin C (2016) \u201cwhy should i trust you?\u201d: Explaining the predictions of any classifier. Proceedings of the 22nd ACM SIGKDD Int Conf Knowl Discovery and Data Mining","DOI":"10.1145\/2939672.2939778"},{"key":"20235_CR63","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1038\/s42256-019-0138-9","volume":"2","author":"SM Lundberg","year":"2020","unstructured":"Lundberg SM, Erion GG, Chen H, DeGrave AJ, Prutkin JM, Nair BG, Katz R, Himmelfarb J, Bansal N, Lee S-I (2020) From local explanations to global understanding with explainable ai for trees. Nat Machine Intell 2:56\u201367","journal-title":"Nat Machine Intell"},{"key":"20235_CR64","doi-asserted-by":"crossref","unstructured":"Katyal N, Rajpoot PK, Tamilarasu S, Mustafi J (2023) teampn at semeval-2023 task 1: Visual word sense disambiguation using zero-shot multimodal approach. In: International Workshop on Semantic Evaluation","DOI":"10.18653\/v1\/2023.semeval-1.63"},{"key":"20235_CR65","doi-asserted-by":"crossref","unstructured":"Berend G (2023) Szegedai at semeval-2023 task 1: Applying quasi-symbolic representations in visual word sense disambiguation. In: International Workshop on Semantic Evaluation","DOI":"10.18653\/v1\/2023.semeval-1.270"},{"key":"20235_CR66","doi-asserted-by":"crossref","unstructured":"Zhang S, Nath SK, Mazzaccara D (2023) Gpl at semeval-2023 task 1: Wordnet and clip to disambiguate images. In: International Workshop on Semantic Evaluation","DOI":"10.18653\/v1\/2023.semeval-1.219"},{"key":"20235_CR67","doi-asserted-by":"crossref","unstructured":"Ghahroodi O, Dalili SA, Mesforoush S, Asgari E (2023) Sut at semeval-2023 task 1: Prompt generation for visual word sense disambiguation. In: International Workshop on Semantic Evaluation","DOI":"10.18653\/v1\/2023.semeval-1.298"},{"key":"20235_CR68","doi-asserted-by":"crossref","unstructured":"Grbowiec M (2023) Opi pib at semeval-2023 task 1: A clip-based solution paired with an additional word context extension. In: International Workshop on Semantic Evaluation","DOI":"10.18653\/v1\/2023.semeval-1.67"},{"key":"20235_CR69","doi-asserted-by":"crossref","unstructured":"Poth CA, Hentschel M, Werner T, Sterz H, Bongard L (2023) Ml mob at semeval-2023 task 1: Probing clip on visual word-sense disambiguation. In: International Workshop on Semantic Evaluation","DOI":"10.18653\/v1\/2023.semeval-1.201"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-024-20235-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-024-20235-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-024-20235-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T11:27:40Z","timestamp":1757503660000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-024-20235-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,28]]},"references-count":69,"journal-issue":{"issue":"29","published-online":{"date-parts":[[2025,9]]}},"alternative-id":["20235"],"URL":"https:\/\/doi.org\/10.1007\/s11042-024-20235-6","relation":{},"ISSN":["1573-7721"],"issn-type":[{"type":"electronic","value":"1573-7721"}],"subject":[],"published":{"date-parts":[[2025,1,28]]},"assertion":[{"value":"3 May 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 July 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 September 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 January 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that there are no conflicts of interest or competing interests associated with this research.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of interests or Competing interests"}}]}}