{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T17:19:00Z","timestamp":1765041540677},"reference-count":69,"publisher":"Springer Science and Business Media LLC","issue":"17-18","license":[{"start":{"date-parts":[[2024,6,10]],"date-time":"2024-06-10T00:00:00Z","timestamp":1717977600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,6,10]],"date-time":"2024-06-10T00:00:00Z","timestamp":1717977600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2024,9]]},"DOI":"10.1007\/s10489-024-05501-2","type":"journal-article","created":{"date-parts":[[2024,6,10]],"date-time":"2024-06-10T06:02:20Z","timestamp":1717999340000},"page":"7581-7602","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Semantic-alignment transformer and adversary hashing for cross-modal retrieval"],"prefix":"10.1007","volume":"54","author":[{"given":"Yajun","family":"Sun","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ying","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,6,10]]},"reference":[{"key":"5501_CR1","doi-asserted-by":"publisher","first-page":"1339","DOI":"10.1007\/s11042-019-08238-0","volume":"79","author":"D Xia","year":"2020","unstructured":"Xia D, Miao L, Fan A (2020) A cross-modal multimedia retrieval method using depth correlation mining in big data environment. Multimed Tools Appl 79:1339\u20131354. https:\/\/doi.org\/10.1007\/s11042-019-08238-0","journal-title":"Multimed Tools Appl"},{"key":"5501_CR2","doi-asserted-by":"publisher","DOI":"10.1145\/3447582","author":"P Ren","year":"2021","unstructured":"Ren P, Xiao Y, Chang X, Huang P-Y, Li Z, Chen X, Wang X (2021) A comprehensive survey of neural architecture search: challenges and solutions. ACM Comput Surv. https:\/\/doi.org\/10.1145\/3447582","journal-title":"ACM Comput Surv"},{"issue":"6","key":"5501_CR3","doi-asserted-by":"publisher","first-page":"2574","DOI":"10.1109\/TKDE.2020.3015777","volume":"34","author":"M Wang","year":"2020","unstructured":"Wang M, Fu W, He X, Hao S, Wu X (2020) A survey on large-scale machine learning. IEEE Trans Knowl Data Eng 34(6):2574\u20132594. https:\/\/doi.org\/10.1109\/TKDE.2020.3015777","journal-title":"IEEE Trans Knowl Data Eng"},{"issue":"10","key":"5501_CR4","doi-asserted-by":"publisher","first-page":"4514","DOI":"10.1109\/tnnls.2020.3018790","volume":"32","author":"Z Zhang","year":"2020","unstructured":"Zhang Z, Liu L, Luo Y, Huang Z, Shen F, Shen HT, Lu G (2020) Inductive structure consistent hashing via flexible semantic calibration. IEEE Trans Neural Netw Learn Syst 32(10):4514\u20134528. https:\/\/doi.org\/10.1109\/tnnls.2020.3018790","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"issue":"4","key":"5501_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3356338","volume":"15","author":"Z Ye","year":"2019","unstructured":"Ye Z, Peng Y (2019) Sequential cross-modal hashing learning via multi-scale correlation mining. ACM Trans Multimed Comput Commun Appl (TOMM) 15(4):1\u201320. https:\/\/doi.org\/10.1145\/3356338","journal-title":"ACM Trans Multimed Comput Commun Appl (TOMM)"},{"issue":"11","key":"5501_CR6","doi-asserted-by":"publisher","first-page":"3507","DOI":"10.1109\/tkde.2020.2974825","volume":"33","author":"Y Wang","year":"2020","unstructured":"Wang Y, Luo X, Nie L, Song J, Zhang W, Xu X-S (2020) Batch: a scalable asymmetric discrete cross-modal hashing. IEEE Trans Knowl Data Eng 33(11):3507\u20133519. https:\/\/doi.org\/10.1109\/tkde.2020.2974825","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"5501_CR7","doi-asserted-by":"publisher","unstructured":"Su S, Zhong Z, Zhang C (2019) Deep joint-semantics reconstructing hashing for large-scale unsupervised cross-modal retrieval. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 3027\u20133035. https:\/\/doi.org\/10.1109\/iccv.2019.00312","DOI":"10.1109\/iccv.2019.00312"},{"issue":"10","key":"5501_CR8","doi-asserted-by":"publisher","first-page":"3351","DOI":"10.1109\/tkde.2020.2970050","volume":"33","author":"HT Shen","year":"2020","unstructured":"Shen HT, Liu L, Yang Y, Xu X, Huang Z, Shen F, Hong R (2020) Exploiting subspace relation in semantic labels for cross-modal hashing. IEEE Trans Knowl Data Eng 33(10):3351\u20133365. https:\/\/doi.org\/10.1109\/tkde.2020.2970050","journal-title":"IEEE Trans Knowl Data Eng"},{"issue":"3","key":"5501_CR9","doi-asserted-by":"publisher","first-page":"964","DOI":"10.1109\/tpami.2019.2940446","volume":"43","author":"X Liu","year":"2019","unstructured":"Liu X, Hu Z, Ling H, Cheung Y-m (2019) Mtfh: a matrix tri-factorization hashing framework for efficient cross-modal retrieval. IEEE Trans Pattern Anal Mach Intell 43(3):964\u2013981. https:\/\/doi.org\/10.1109\/tpami.2019.2940446","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"5501_CR10","doi-asserted-by":"publisher","first-page":"3392","DOI":"10.1109\/tmm.2021.3097506","volume":"24","author":"Z Zhang","year":"2021","unstructured":"Zhang Z, Wang X, Lu G, Shen F, Zhu L (2021) Targeted attack of deep hashing via prototype-supervised adversarial networks. IEEE Trans Multimed 24:3392\u20133404. https:\/\/doi.org\/10.1109\/tmm.2021.3097506","journal-title":"IEEE Trans Multimed"},{"key":"5501_CR11","doi-asserted-by":"publisher","unstructured":"Wang X, Zhang Z, Wu B, Shen F, Lu G (2021) Prototype-supervised adversarial network for targeted attack of deep hashing. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 16357\u201316366. https:\/\/doi.org\/10.1109\/cvpr46437.2021.01609","DOI":"10.1109\/cvpr46437.2021.01609"},{"key":"5501_CR12","doi-asserted-by":"publisher","unstructured":"Huang F, Zhang L, Yang Y, Zhou X (2020) Probability weighted compact feature for domain adaptive retrieval. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 9582\u20139591. https:\/\/doi.org\/10.1109\/cvpr42600.2020.00960","DOI":"10.1109\/cvpr42600.2020.00960"},{"key":"5501_CR13","doi-asserted-by":"publisher","unstructured":"Shen F, Shen C, Liu W, Tao\u00a0Shen H (2015) Supervised discrete hashing. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 37\u201345. https:\/\/doi.org\/10.1109\/cvpr.2015.7298598","DOI":"10.1109\/cvpr.2015.7298598"},{"issue":"9","key":"5501_CR14","doi-asserted-by":"publisher","first-page":"2827","DOI":"10.1109\/tip.2015.2421443","volume":"24","author":"J Tang","year":"2015","unstructured":"Tang J, Li Z, Wang M, Zhao R (2015) Neighborhood discriminant hashing for large-scale image retrieval. IEEE Trans Image Process 24(9):2827\u20132840. https:\/\/doi.org\/10.1109\/tip.2015.2421443","journal-title":"IEEE Trans Image Process"},{"key":"5501_CR15","doi-asserted-by":"publisher","first-page":"4643","DOI":"10.1109\/tip.2020.2974065","volume":"29","author":"L Zhu","year":"2020","unstructured":"Zhu L, Lu X, Cheng Z, Li J, Zhang H (2020) Deep collaborative multi-view hashing for large-scale image search. IEEE Trans Image Process 29:4643\u20134655. https:\/\/doi.org\/10.1109\/tip.2020.2974065","journal-title":"IEEE Trans Image Process"},{"key":"5501_CR16","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2023.3254199","author":"X Liu","year":"2023","unstructured":"Liu X, Zeng H, Shi Y, Zhu J, Hsia C-H, Ma K-K (2023) Deep cross-modal hashing based on semantic consistent ranking. IEEE Trans Multimed. https:\/\/doi.org\/10.1109\/tmm.2023.3254199","journal-title":"IEEE Trans Multimed"},{"key":"5501_CR17","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1016\/j.sigpro.2018.09.007","volume":"154","author":"X Lu","year":"2019","unstructured":"Lu X, Zhu L, Cheng Z, Song X, Zhang H (2019) Efficient discrete latent semantic hashing for scalable cross-modal retrieval. Signal Process 154:217\u2013231. https:\/\/doi.org\/10.1016\/j.sigpro.2018.09.007","journal-title":"Signal Process"},{"key":"5501_CR18","doi-asserted-by":"publisher","first-page":"108823","DOI":"10.1016\/j.patcog.2022.108823","volume":"130","author":"F Yang","year":"2022","unstructured":"Yang F, Liu Y, Ding X, Ma F, Cao J (2022) Asymmetric cross-modal hashing with high-level semantic similarity. Pattern Recognit 130:108823. https:\/\/doi.org\/10.1016\/j.patcog.2022.108823","journal-title":"Pattern Recognit"},{"issue":"10","key":"5501_CR19","doi-asserted-by":"publisher","first-page":"10064","DOI":"10.1109\/tcyb.2021.3059886","volume":"52","author":"Y Wang","year":"2021","unstructured":"Wang Y, Chen Z-D, Luo X, Li R, Xu X-S (2021) Fast cross-modal hashing with global and local similarity embedding. IEEE Trans Cybern 52(10):10064\u201310077. https:\/\/doi.org\/10.1109\/tcyb.2021.3059886","journal-title":"IEEE Trans Cybern"},{"key":"5501_CR20","doi-asserted-by":"publisher","unstructured":"Hare JS, Lewis PH, Enser PG, Sandom CJ (2006) Mind the gap: Another look at the problem of the semantic gap in image retrieval 6073:75\u201386. https:\/\/doi.org\/10.1117\/12.647755. SPIE","DOI":"10.1117\/12.647755"},{"issue":"10","key":"5501_CR21","doi-asserted-by":"publisher","first-page":"3351","DOI":"10.1109\/tkde.2020.2970050","volume":"33","author":"HT Shen","year":"2020","unstructured":"Shen HT, Liu L, Yang Y, Xu X, Huang Z, Shen F, Hong R (2020) Exploiting subspace relation in semantic labels for cross-modal hashing. IEEE Trans Knowl Data Eng 33(10):3351\u20133365. https:\/\/doi.org\/10.1109\/tkde.2020.2970050","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"5501_CR22","doi-asserted-by":"publisher","unstructured":"Su S, Zhong Z, Zhang C (2019) Deep joint-semantics reconstructing hashing for large-scale unsupervised cross-modal retrieval. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 3027\u20133035. https:\/\/doi.org\/10.1109\/iccv.2019.00312","DOI":"10.1109\/iccv.2019.00312"},{"key":"5501_CR23","doi-asserted-by":"publisher","unstructured":"Yang D, Wu D, Zhang W, Zhang H, Li B, Wang W (2020) Deep semantic-alignment hashing for unsupervised cross-modal retrieval. In: Proceedings of the 2020 international conference on multimedia retrieval, pp 44\u201352. https:\/\/doi.org\/10.1145\/3372278.3390673","DOI":"10.1145\/3372278.3390673"},{"key":"5501_CR24","doi-asserted-by":"publisher","first-page":"466","DOI":"10.1109\/tmm.2021.3053766","volume":"24","author":"P-F Zhang","year":"2021","unstructured":"Zhang P-F, Li Y, Huang Z, Xu X-S (2021) Aggregation-based graph convolutional hashing for unsupervised cross-modal retrieval. IEEE Trans Multimed 24:466\u2013479. https:\/\/doi.org\/10.1109\/tmm.2021.3053766","journal-title":"IEEE Trans Multimed"},{"key":"5501_CR25","doi-asserted-by":"publisher","first-page":"673","DOI":"10.1007\/s11760-019-01534-0","volume":"15","author":"Y Li","year":"2021","unstructured":"Li Y, Wang X, Qi S, Huang C, Jiang ZL, Liao Q, Guan J, Zhang J (2021) Self-supervised learning-based weight adaptive hashing for fast cross-modal retrieval. Signal, Image Vid Process 15:673\u2013680. https:\/\/doi.org\/10.1007\/s11760-019-01534-0","journal-title":"Signal, Image Vid Process"},{"key":"5501_CR26","doi-asserted-by":"publisher","unstructured":"Jiang Q-Y, Li W-J (2017) Deep cross-modal hashing. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3232\u20133240. https:\/\/doi.org\/10.1109\/cvpr.2017.348","DOI":"10.1109\/cvpr.2017.348"},{"key":"5501_CR27","doi-asserted-by":"publisher","unstructured":"Li C, Deng C, Li N, Liu W, Gao X, Tao D (2018) Self-supervised adversarial hashing networks for cross-modal retrieval. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4242\u20134251. https:\/\/doi.org\/10.1109\/cvpr.2018.00446","DOI":"10.1109\/cvpr.2018.00446"},{"key":"5501_CR28","doi-asserted-by":"publisher","unstructured":"Gu W, Gu X, Gu J, Li B, Xiong Z, Wang W (2019) Adversary guided asymmetric hashing for cross-modal retrieval. In: Proceedings of the 2019 on international conference on multimedia retrieval, pp 159\u2013167. https:\/\/doi.org\/10.1145\/3323873.3325045","DOI":"10.1145\/3323873.3325045"},{"issue":"12","key":"5501_CR29","doi-asserted-by":"publisher","first-page":"3101","DOI":"10.1109\/tmm.2020.2969792","volume":"22","author":"X Ma","year":"2020","unstructured":"Ma X, Zhang T, Xu C (2020) Multi-level correlation adversarial hashing for cross-modal retrieval. IEEE Trans Multimed 22(12):3101\u20133114. https:\/\/doi.org\/10.1109\/tmm.2020.2969792","journal-title":"IEEE Trans Multimed"},{"issue":"9","key":"5501_CR30","doi-asserted-by":"publisher","first-page":"2022","DOI":"10.1109\/tmm.2017.2699863","volume":"19","author":"F Shen","year":"2017","unstructured":"Shen F, Yang Y, Liu L, Liu W, Tao D, Shen HT (2017) Asymmetric binary coding for image search. IEEE Trans Multimed 19(9):2022\u20132032. https:\/\/doi.org\/10.1109\/tmm.2017.2699863","journal-title":"IEEE Trans Multimed"},{"key":"5501_CR31","doi-asserted-by":"publisher","unstructured":"Hu P, Peng X, Zhu H, Zhen L, Lin J (2021) Learning cross-modal retrieval with noisy labels. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 5403\u20135413. https:\/\/doi.org\/10.1109\/cvpr46437.2021.00536","DOI":"10.1109\/cvpr46437.2021.00536"},{"issue":"12","key":"5501_CR32","doi-asserted-by":"publisher","first-page":"1551","DOI":"10.1631\/FITEE.2100463","volume":"22","author":"Y Yang","year":"2021","unstructured":"Yang Y, Zhuang Y, Pan Y (2021) Multiple knowledge representation for big data artificial intelligence: framework, applications, and case studies. Front Inf Technol Electron Eng 22(12):1551\u20131558. https:\/\/doi.org\/10.1631\/FITEE.2100463","journal-title":"Front Inf Technol Electron Eng"},{"key":"5501_CR33","doi-asserted-by":"publisher","unstructured":"Huang P-Y, Kang G, Liu W, Chang X, Hauptmann AG (2019) Annotation efficient cross-modal retrieval with adversarial attentive alignment. In: Proceedings of the 27th ACM international conference on multimedia, pp 1758\u20131767. https:\/\/doi.org\/10.1145\/3343031.3350894","DOI":"10.1145\/3343031.3350894"},{"key":"5501_CR34","doi-asserted-by":"publisher","first-page":"100336","DOI":"10.1016\/j.cosrev.2020.100336","volume":"39","author":"P Kaur","year":"2021","unstructured":"Kaur P, Pannu HS, Malhi AK (2021) Comparative analysis on cross-modal information retrieval: a review. Comput Sci Rev 39:100336. https:\/\/doi.org\/10.1016\/j.cosrev.2020.100336","journal-title":"Comput Sci Rev"},{"key":"5501_CR35","unstructured":"Andrew G, Arora R, Bilmes J, Livescu K (2013) Deep canonical correlation analysis. In: International conference on machine learning, pp 1247\u20131255. PMLR"},{"key":"5501_CR36","doi-asserted-by":"publisher","unstructured":"Ranjan V, Rasiwasia N, Jawahar C (2015) Multi-label cross-modal retrieval. In: Proceedings of the IEEE international conference on computer vision, pp 4094\u20134102. https:\/\/doi.org\/10.1109\/iccv.2015.466","DOI":"10.1109\/iccv.2015.466"},{"key":"5501_CR37","doi-asserted-by":"publisher","unstructured":"Tran TQN, Le\u00a0Borgne H, Crucianu M (2016) Aggregating image and text quantized correlated components. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2046\u20132054. https:\/\/doi.org\/10.1109\/cvpr.2016.225","DOI":"10.1109\/cvpr.2016.225"},{"issue":"11","key":"5501_CR38","doi-asserted-by":"publisher","first-page":"5585","DOI":"10.1109\/tip.2018.2852503","volume":"27","author":"Y Peng","year":"2018","unstructured":"Peng Y, Qi J, Yuan Y (2018) Modality-specific cross-modal similarity measurement with recurrent attention network. IEEE Trans Image Process 27(11):5585\u20135599. https:\/\/doi.org\/10.1109\/tip.2018.2852503","journal-title":"IEEE Trans Image Process"},{"key":"5501_CR39","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1109\/jproc.2023.3238524","volume":"111","author":"Z Zou","year":"2023","unstructured":"Zou Z, Chen K, Shi Z, Guo Y, Ye J (2023) Object detection in 20 years: a survey. Proc IEEE 111:257\u2013276. https:\/\/doi.org\/10.1109\/jproc.2023.3238524","journal-title":"Proc IEEE"},{"key":"5501_CR40","doi-asserted-by":"publisher","unstructured":"Amit Y, Felzenszwalb P, Girshick R (2021) Object detection. In: Computer vision: a reference guide, pp 875\u2013883. https:\/\/doi.org\/10.1007\/978-3-030-63416-2_660","DOI":"10.1007\/978-3-030-63416-2_660"},{"key":"5501_CR41","doi-asserted-by":"publisher","unstructured":"Li Y, Wu C-Y, Fan H, Mangalam K, Xiong B, Malik J, Feichtenhofer C (2022) Mvitv2: Improved multiscale vision transformers for classification and detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 4804\u20134814. https:\/\/doi.org\/10.1109\/cvpr52688.2022.00476","DOI":"10.1109\/cvpr52688.2022.00476"},{"key":"5501_CR42","doi-asserted-by":"publisher","unstructured":"Long A, Yin W, Ajanthan T, Nguyen V, Purkait P, Garg R, Blair A, Shen C, Hengel A (2022) Retrieval augmented classification for long-tail visual recognition. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 6959\u20136969. https:\/\/doi.org\/10.1109\/cvpr52688.2022.00683","DOI":"10.1109\/cvpr52688.2022.00683"},{"key":"5501_CR43","doi-asserted-by":"publisher","unstructured":"Wu G, Lin Z, Han J, Liu L, Ding G, Zhang B, Shen J (2018) Unsupervised deep hashing via binary latent factor models for large-scale cross-modal retrieval. In: IJCAI, vol 1, p 5. https:\/\/doi.org\/10.24963\/ijcai.2018\/396","DOI":"10.24963\/ijcai.2018\/396"},{"key":"5501_CR44","doi-asserted-by":"publisher","unstructured":"Lin Z, Ding G, Hu M, Wang J (2015) Semantics-preserving hashing for cross-view retrieval. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3864\u20133872. https:\/\/doi.org\/10.1109\/cvpr.2015.7299011","DOI":"10.1109\/cvpr.2015.7299011"},{"key":"5501_CR45","doi-asserted-by":"publisher","unstructured":"Yang, E, Deng C, Liu W, Liu X, Tao D, Gao X (2017) Pairwise relationship guided deep hashing for cross-modal retrieval. In: Proceedings of the AAAI conference on artificial intelligence, vol 31. https:\/\/doi.org\/10.1609\/aaai.v31i1.10719","DOI":"10.1609\/aaai.v31i1.10719"},{"key":"5501_CR46","doi-asserted-by":"publisher","DOI":"10.5244\/c.31.128","author":"Y Cao","year":"2017","unstructured":"Cao Y, Long M, Wang J, Yu PS (2017) Correlation hashing network for efficient cross-modal retrieval. BMVC. https:\/\/doi.org\/10.5244\/c.31.128","journal-title":"BMVC"},{"key":"5501_CR47","doi-asserted-by":"publisher","unstructured":"Bai C, Zeng C, Ma Q, Zhang J, Chen S (2020) Deep adversarial discrete hashing for cross-modal retrieval. In: Proceedings of the 2020 international conference on multimedia retrieval, pp 525\u2013531. https:\/\/doi.org\/10.1145\/3372278.3390711","DOI":"10.1145\/3372278.3390711"},{"key":"5501_CR48","doi-asserted-by":"publisher","unstructured":"Wang B, Yang Y, Xu X, Hanjalic A, Shen HT (2017) Adversarial cross-modal retrieval. In: Proceedings of the 25th ACM international conference on multimedia, pp 154\u2013162. https:\/\/doi.org\/10.1145\/3123266.3123326","DOI":"10.1145\/3123266.3123326"},{"key":"5501_CR49","doi-asserted-by":"publisher","first-page":"657","DOI":"10.1007\/s11280-018-0541-x","volume":"22","author":"X Xu","year":"2019","unstructured":"Xu X, He L, Lu H, Gao L, Ji Y (2019) Deep adversarial metric learning for cross-modal retrieval. World Wide Web 22:657\u2013672. https:\/\/doi.org\/10.1007\/s11280-018-0541-x","journal-title":"World Wide Web"},{"key":"5501_CR50","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1016\/j.knosys.2019.05.017","volume":"180","author":"P Hu","year":"2019","unstructured":"Hu P, Peng D, Wang X, Xiang Y (2019) Multimodal adversarial network for cross-modal retrieval. Knowl-Based Syst 180:38\u201350. https:\/\/doi.org\/10.1016\/j.knosys.2019.05.017","journal-title":"Knowl-Based Syst"},{"key":"5501_CR51","unstructured":"Goodfellow I, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville A, Bengio Y (2014) Generative adversarial nets. In: Advances in neural information processing systems, vol 27"},{"issue":"11","key":"5501_CR52","doi-asserted-by":"publisher","first-page":"3943","DOI":"10.1109\/tcsvt.2019.2920407","volume":"30","author":"H Zhang","year":"2019","unstructured":"Zhang H, Sindagi V, Patel VM (2019) Image de-raining using a conditional generative adversarial network. IEEE Trans Circuits Syst Vid Technol 30(11):3943\u20133956. https:\/\/doi.org\/10.1109\/tcsvt.2019.2920407","journal-title":"IEEE Trans Circuits Syst Vid Technol"},{"issue":"1","key":"5501_CR53","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3284750","volume":"15","author":"Y Peng","year":"2019","unstructured":"Peng Y, Qi J (2019) Cm-gans: Cross-modal generative adversarial networks for common representation learning. ACM Trans Multimed Comput Commun Appl (TOMM) 15(1):1\u201324. https:\/\/doi.org\/10.1145\/3284750","journal-title":"ACM Trans Multimed Comput Commun Appl (TOMM)"},{"key":"5501_CR54","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser \u0141, Polosukhin I (2017) Attention is all you need. Adv Neural Inf Process Syst 30"},{"key":"5501_CR55","doi-asserted-by":"publisher","unstructured":"Carion N, Massa F, Synnaeve G, Usunier N, Kirillov A, Zagoruyko S (2020) End-to-end object detection with transformers. In: European conference on computer vision, pp 213\u2013229. https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13. Springer","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"5501_CR56","unstructured":"Xiao T, Singh M, Mintun E, Darrell T, Doll\u00e1r P, Girshick R (2021) Early convolutions help transformers see better. In: Advances in neural information processing systems, vol 34, pp 30392\u201330400"},{"key":"5501_CR57","unstructured":"Radford A, Kim JW, Hallacy C, Ramesh A, Goh G, Agarwal S, Sastry G, Askell A, Mishkin P, Clark J et al (2021) Learning transferable visual models from natural language supervision 8748\u20138763. PMLR"},{"key":"5501_CR58","doi-asserted-by":"publisher","unstructured":"Kenton JDM-WC, Toutanova LK (2019) Bert: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of naacL-HLT, vol 1, p 2. https:\/\/doi.org\/10.48550\/arXiv.1810.04805","DOI":"10.48550\/arXiv.1810.04805"},{"key":"5501_CR59","doi-asserted-by":"publisher","unstructured":"Sun C, Myers A, Vondrick C, Murphy K, Schmid C (2019) Videobert: a joint model for video and language representation learning. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 7464\u20137473. https:\/\/doi.org\/10.1109\/iccv.2019.00756","DOI":"10.1109\/iccv.2019.00756"},{"key":"5501_CR60","doi-asserted-by":"publisher","unstructured":"Wang C-Y, Liao H-YM, Wu Y-H, Chen P-Y, Hsieh J-W, Yeh I-H (2020) Cspnet: a new backbone that can enhance learning capability of cnn. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition workshops, pp 390\u2013391. https:\/\/doi.org\/10.1109\/cvprw50498.2020.00203","DOI":"10.1109\/cvprw50498.2020.00203"},{"key":"5501_CR61","doi-asserted-by":"publisher","unstructured":"Shen X, Chen Y, Pan S, Liu W, Zheng Y (2023) Graph convolutional incomplete multi-modal hashing. In: Proceedings of the 31st ACM international conference on multimedia, pp 7029\u20137037. https:\/\/doi.org\/10.1145\/3581783.3612282","DOI":"10.1145\/3581783.3612282"},{"key":"5501_CR62","doi-asserted-by":"publisher","unstructured":"Gao D, Jin L, Chen B, Qiu M, Li P, Wei Y, Hu Y, Wang H (2020) Fashionbert: Text and image matching with adaptive loss for cross-modal retrieval, 2251\u20132260 https:\/\/doi.org\/10.1145\/3397271.3401430","DOI":"10.1145\/3397271.3401430"},{"key":"5501_CR63","doi-asserted-by":"publisher","unstructured":"Li S, Li X, Lu J, Zhou J (2021) Self-supervised video hashing via bidirectional transformers. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 13549\u201313558. https:\/\/doi.org\/10.1109\/cvpr46437.2021.01334","DOI":"10.1109\/cvpr46437.2021.01334"},{"key":"5501_CR64","doi-asserted-by":"publisher","first-page":"267","DOI":"10.1016\/j.catena.2022.106289","volume":"80","author":"A Abbaszadeh Shahri","year":"2021","unstructured":"Abbaszadeh Shahri A, Maghsoudi Moud F (2021) Landslide susceptibility mapping using hybridized block modular intelligence model. Bull Eng Geol Environ 80:267\u2013284. https:\/\/doi.org\/10.1016\/j.catena.2022.106289","journal-title":"Bull Eng Geol Environ"},{"key":"5501_CR65","doi-asserted-by":"publisher","unstructured":"Chatfield K, Simonyan K, Vedaldi A, Zisserman A (2014) Return of the devil in the details: Delving deep into convolutional nets. In: Proceedings of the British machine vision conference 2014, pp 1\u201312. https:\/\/doi.org\/10.5244\/c.28.6. British Machine Vision Association","DOI":"10.5244\/c.28.6"},{"key":"5501_CR66","doi-asserted-by":"publisher","unstructured":"Huiskes MJ, Lew MS (2008) The mir flickr retrieval evaluation, pp 39\u201343. Association for Computing Machinery, New York, NY, USA. https:\/\/doi.org\/10.1145\/1460096.1460104","DOI":"10.1145\/1460096.1460104"},{"key":"5501_CR67","doi-asserted-by":"publisher","unstructured":"Chua T-S, Tang J, Hong R, Li H, Luo Z, Zheng Y (2009) Nus-wide: a real-world web image database from National University of Singapore. CIVR \u201909. Association for Computing Machinery, New York, USA. https:\/\/doi.org\/10.1145\/1646396.1646452","DOI":"10.1145\/1646396.1646452"},{"key":"5501_CR68","doi-asserted-by":"publisher","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: Computer Vision \u2013 ECCV 2014, pp 740\u2013755. https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48. Springer","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"5501_CR69","doi-asserted-by":"publisher","first-page":"106289","DOI":"10.1016\/j.catena.2022.106289","volume":"214","author":"A Ghaderi","year":"2022","unstructured":"Ghaderi A, Abbaszadeh Shahri A, Larsson S (2022) A visualized hybrid intelligent model to delineate swedish fine-grained soil layers using clay sensitivity. CATENA 214:106289. https:\/\/doi.org\/10.1016\/j.catena.2022.106289","journal-title":"CATENA"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-024-05501-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-024-05501-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-024-05501-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,7]],"date-time":"2024-08-07T12:14:22Z","timestamp":1723032862000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-024-05501-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,10]]},"references-count":69,"journal-issue":{"issue":"17-18","published-print":{"date-parts":[[2024,9]]}},"alternative-id":["5501"],"URL":"https:\/\/doi.org\/10.1007\/s10489-024-05501-2","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"type":"print","value":"0924-669X"},{"type":"electronic","value":"1573-7497"}],"subject":[],"published":{"date-parts":[[2024,6,10]]},"assertion":[{"value":"2 May 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 June 2024","order":2,"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 no conflicts of interest that could potentially influence the outcome or interpretation of the research reported in this manuscript.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of interest"}},{"value":"The authors declare no competing interests related to the publication of this manuscript.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing Interests"}},{"value":"Informed consent was obtained from all human participants involved in this study.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed consent"}},{"value":"This study did not involve human participants or animals.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Research involving Human Participants and\/or Animals"}}]}}