{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T17:15:13Z","timestamp":1765041313855,"version":"3.37.3"},"reference-count":56,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2022,11,14]],"date-time":"2022-11-14T00:00:00Z","timestamp":1668384000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,11,14]],"date-time":"2022-11-14T00:00:00Z","timestamp":1668384000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Science and Technology on Information System Engineering Laboratory","award":["WDZC20205250410"],"award-info":[{"award-number":["WDZC20205250410"]}]},{"name":"Key-Area Research and Development Program of Guangdong Province under Grant","award":["2019B111101001"],"award-info":[{"award-number":["2019B111101001"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2023,12]]},"DOI":"10.1007\/s00371-022-02716-7","type":"journal-article","created":{"date-parts":[[2022,11,14]],"date-time":"2022-11-14T23:56:41Z","timestamp":1668470201000},"page":"6115-6132","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Multi-channel weighted fusion for image captioning"],"prefix":"10.1007","volume":"39","author":[{"given":"Jingyue","family":"Zhong","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4758-6091","authenticated-orcid":false,"given":"Yang","family":"Cao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yina","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Gong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiaosen","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,11,14]]},"reference":[{"issue":"1","key":"2716_CR1","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1016\/0031-3203(95)00067-4","volume":"29","author":"T Ojala","year":"1996","unstructured":"Ojala, T., Pietik\u00e4inen, M., Harwood, D.: A comparative study of texture measures with classification based on featured distributions. Pattern Recognit. 29(1), 51\u201359 (1996). https:\/\/doi.org\/10.1016\/0031-3203(95)00067-4","journal-title":"Pattern Recognit."},{"issue":"2","key":"2716_CR2","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"DG Lowe","year":"2004","unstructured":"Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60(2), 91\u2013110 (2004). https:\/\/doi.org\/10.1023\/B:VISI.0000029664.99615.94","journal-title":"Int. J. Comput. Vis."},{"key":"2716_CR3","doi-asserted-by":"publisher","unstructured":"Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 886\u2013893 (2005). https:\/\/doi.org\/10.1109\/CVPR.2005.177","DOI":"10.1109\/CVPR.2005.177"},{"key":"2716_CR4","unstructured":"Mitchell, M., Dodge, J., Goyal, A., Yamaguchi, K., Stratos, K., Han, X., Mensch, A.C., Berg, A.C., Berg, T.L., III, H.D.: Midge: generating image descriptions from computer vision detections. In: Association for Computational Linguistics (ACL), pp. 747\u2013756 (2012)"},{"key":"2716_CR5","doi-asserted-by":"publisher","unstructured":"Mason, R., Charniak, E.: Nonparametric method for data-driven image captioning. In: Association for Computational Linguistics (ACL), pp. 592\u2013598 (2014). https:\/\/doi.org\/10.3115\/v1\/p14-2097","DOI":"10.3115\/v1\/p14-2097"},{"key":"2716_CR6","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representations (ICLR), pp. 1409\u201315566 (2015)"},{"key":"2716_CR7","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770\u2013778 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"issue":"8","key":"2716_CR8","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997). https:\/\/doi.org\/10.1162\/neco.1997.9.8.1735","journal-title":"Neural Comput."},{"key":"2716_CR9","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., Polosukhin, I.: Attention is all you need. In: Advances in Neural Information Processing Systems (NIPS), pp. 5998\u20136008 (2017)"},{"key":"2716_CR10","doi-asserted-by":"publisher","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: a neural image caption generator. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3156\u20133164 (2015). https:\/\/doi.org\/10.1109\/CVPR.2015.7298935","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"2716_CR11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.neucom.2012.08.028","volume":"108","author":"L Leng","year":"2013","unstructured":"Leng, L., Zhang, J.: Palmhash code vs. palmphasor code. Neurocomputing 108, 1\u201312 (2013). https:\/\/doi.org\/10.1016\/j.neucom.2012.08.028","journal-title":"Neurocomputing"},{"issue":"1","key":"2716_CR12","doi-asserted-by":"publisher","first-page":"333","DOI":"10.1007\/s11042-015-3058-7","volume":"76","author":"L Leng","year":"2017","unstructured":"Leng, L., Li, M., Kim, C., Bi, X.: Dual-source discrimination power analysis for multi-instance contactless palmprint recognition. Multimed. Tools. Appl. 76(1), 333\u2013354 (2017). https:\/\/doi.org\/10.1007\/s11042-015-3058-7","journal-title":"Multimed. Tools. Appl."},{"issue":"4","key":"2716_CR13","doi-asserted-by":"publisher","first-page":"831","DOI":"10.1007\/s00371-020-01833-5","volume":"37","author":"MY Abbass","year":"2021","unstructured":"Abbass, M.Y., Kwon, K., Kim, N., Abdelwahab, S.A.S., El-Samie, F.E.A., Khalaf, A.A.M.: Efficient object tracking using hierarchical convolutional features model and correlation filters. Vis. Comput. 37(4), 831\u2013842 (2021). https:\/\/doi.org\/10.1007\/s00371-020-01833-5","journal-title":"Vis. Comput."},{"issue":"6","key":"2716_CR14","doi-asserted-by":"publisher","first-page":"1415","DOI":"10.1007\/s00371-020-01878-6","volume":"37","author":"M Asad","year":"2021","unstructured":"Asad, M., Yang, J., Jiang, H., Shamsolmoali, P., He, X.: Multi-frame feature-fusion-based model for violence detection. Vis. Comput. 37(6), 1415\u20131431 (2021). https:\/\/doi.org\/10.1007\/s00371-020-01878-6","journal-title":"Vis. Comput."},{"issue":"2","key":"2716_CR15","doi-asserted-by":"publisher","first-page":"457","DOI":"10.1007\/s00371-020-02028-8","volume":"38","author":"M Hazgui","year":"2022","unstructured":"Hazgui, M., Ghazouani, H., Barhoumi, W.: Genetic programming-based fusion of HOG and LBP features for fully automated texture classification. Vis. Comput. 38(2), 457\u2013476 (2022). https:\/\/doi.org\/10.1007\/s00371-020-02028-8","journal-title":"Vis. Comput."},{"key":"2716_CR16","doi-asserted-by":"publisher","first-page":"520","DOI":"10.1016\/j.neucom.2019.04.095","volume":"398","author":"S Ding","year":"2020","unstructured":"Ding, S., Qu, S., Xi, Y., Wan, S.: Stimulus-driven and concept-driven analysis for image caption generation. Neurocomputing 398, 520\u2013530 (2020). https:\/\/doi.org\/10.1016\/j.neucom.2019.04.095","journal-title":"Neurocomputing"},{"key":"2716_CR17","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2020.103068","volume":"201","author":"H Wei","year":"2020","unstructured":"Wei, H., Li, Z., Zhang, C., Ma, H.: The synergy of double attention: Combine sentence-level and word-level attention for image captioning. Comput. Vis. Image Underst. 201, 103068 (2020). https:\/\/doi.org\/10.1016\/j.cviu.2020.103068","journal-title":"Comput. Vis. Image Underst."},{"key":"2716_CR18","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.115462","volume":"184","author":"J Zhang","year":"2021","unstructured":"Zhang, J., Li, K., Wang, Z., Zhao, X., Wang, Z.: Visual enhanced GLSTM for image captioning. Expert Syst. Appl. 184, 115462 (2021). https:\/\/doi.org\/10.1016\/j.eswa.2021.115462","journal-title":"Expert Syst. Appl."},{"issue":"1","key":"2716_CR19","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1007\/s11063-018-09973-5","volume":"50","author":"P Cao","year":"2019","unstructured":"Cao, P., Yang, Z., Sun, L., Liang, Y., Yang, M.Q., Guan, R.: Image captioning with bidirectional semantic attention-based guiding of long short-term memory. Neural Process. Lett. 50(1), 103\u2013119 (2019). https:\/\/doi.org\/10.1007\/s11063-018-09973-5","journal-title":"Neural Process. Lett."},{"key":"2716_CR20","doi-asserted-by":"publisher","unstructured":"Farhadi, A., Hejrati, S.M.M., Sadeghi, M.A., Young, P., Rashtchian, C., Hockenmaier, J., Forsyth, D.A.: Every picture tells a story: generating sentences from images. In: European Conference on Computer Vision (ECCV), vol.\u00a06314, pp. 15\u201329 (2010). https:\/\/doi.org\/10.1007\/978-3-642-15561-1_2","DOI":"10.1007\/978-3-642-15561-1_2"},{"issue":"8","key":"2716_CR21","doi-asserted-by":"publisher","first-page":"1485","DOI":"10.1109\/JPROC.2010.2050411","volume":"98","author":"BZ Yao","year":"2010","unstructured":"Yao, B.Z., Yang, X., Lin, L., Lee, M.W., Zhu, S.-C.: I2T: image parsing to text description. Proc. IEEE 98(8), 1485\u20131508 (2010). https:\/\/doi.org\/10.1109\/JPROC.2010.2050411","journal-title":"Proc. IEEE"},{"key":"2716_CR22","unstructured":"Mao, J., Xu, W., Yang, Y., Wang, J., Huang, Z., Yuille, A.L.: Deep captioning with multimodal recurrent neural networks (m-RNN). In: International Conference on Learning Representations (ICLR), pp. 1412\u201366325 (2015)"},{"key":"2716_CR23","unstructured":"Xu, K., Ba, J.L., Kiros, R., Cho, K., Courville, A.C., Salakhutdinov, R., Zemel, R.S., Bengio, Y.: Show, attend and tell: Neural image caption generation with visual attention. In: International Conference on Machine Learning (ICML), vol. 37, pp. 2048\u20132057 (2015)"},{"issue":"12","key":"2716_CR24","doi-asserted-by":"publisher","first-page":"2321","DOI":"10.1109\/TPAMI.2016.2642953","volume":"39","author":"K Fu","year":"2017","unstructured":"Fu, K., Jin, J., Cui, R., Sha, F., Zhang, C.: Aligning where to see and what to tell: Image captioning with region-based attention and scene-specific contexts. IEEE Trans. Pattern Anal. Mach. Intell. 39(12), 2321\u20132334 (2017). https:\/\/doi.org\/10.1109\/TPAMI.2016.2642953","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2716_CR25","doi-asserted-by":"publisher","unstructured":"Jia, X., Gavves, E., Fernando, B., Tuytelaars, T.: Guiding the long-short term memory model for image caption generation. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 2407\u20132415 (2015). https:\/\/doi.org\/10.1109\/ICCV.2015.277","DOI":"10.1109\/ICCV.2015.277"},{"issue":"11","key":"2716_CR26","doi-asserted-by":"publisher","first-page":"1655","DOI":"10.1007\/s00371-018-1565-z","volume":"35","author":"T Jiang","year":"2019","unstructured":"Jiang, T., Zhang, Z., Yang, Y.: Modeling coverage with semantic embedding for image caption generation. Vis. Comput. 35(11), 1655\u20131665 (2019). https:\/\/doi.org\/10.1007\/s00371-018-1565-z","journal-title":"Vis. Comput."},{"key":"2716_CR27","doi-asserted-by":"crossref","unstructured":"Feng, Y., Ma, L., Liu, W., Luo, J.: Unsupervised image captioning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4120\u20134129 (2019)","DOI":"10.1109\/CVPR.2019.00425"},{"issue":"6","key":"2716_CR28","doi-asserted-by":"publisher","first-page":"1309","DOI":"10.1007\/s00371-020-01867-9","volume":"37","author":"G Barlas","year":"2021","unstructured":"Barlas, G., Veinidis, C., Arampatzis, A.: What we see in a photograph: content selection for image captioning. Vis. Comput. 37(6), 1309\u20131326 (2021). https:\/\/doi.org\/10.1007\/s00371-020-01867-9","journal-title":"Vis. Comput."},{"issue":"2","key":"2716_CR29","doi-asserted-by":"publisher","first-page":"710","DOI":"10.1109\/TPAMI.2019.2909864","volume":"44","author":"Z Zha","year":"2022","unstructured":"Zha, Z., Liu, D., Zhang, H., Zhang, Y., Wu, F.: Context-aware visual policy network for fine-grained image captioning. IEEE Trans. Pattern Anal. Mach. Intell. 44(2), 710\u2013722 (2022). https:\/\/doi.org\/10.1109\/TPAMI.2019.2909864","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"2","key":"2716_CR30","doi-asserted-by":"publisher","first-page":"1035","DOI":"10.1109\/TPAMI.2020.3013834","volume":"44","author":"Q Wang","year":"2022","unstructured":"Wang, Q., Wan, J., Chan, A.B.: On diversity in image captioning: Metrics and methods. IEEE Trans. Pattern Anal. Mach. Intell. 44(2), 1035\u20131049 (2022). https:\/\/doi.org\/10.1109\/TPAMI.2020.3013834","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"6","key":"2716_CR31","doi-asserted-by":"publisher","first-page":"3685","DOI":"10.1109\/TCSVT.2021.3107035","volume":"32","author":"A Liu","year":"2022","unstructured":"Liu, A., Zhai, Y., Xu, N., Nie, W., Li, W., Zhang, Y.: Region-aware image captioning via interaction learning. IEEE Trans. Circuits Syst. Video Technol. 32(6), 3685\u20133696 (2022). https:\/\/doi.org\/10.1109\/TCSVT.2021.3107035","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"2716_CR32","doi-asserted-by":"publisher","first-page":"904","DOI":"10.1109\/TMM.2021.3060948","volume":"24","author":"H Ben","year":"2022","unstructured":"Ben, H., Pan, Y., Li, Y., Yao, T., Hong, R., Wang, M., Mei, T.: Unpaired image captioning with semantic-constrained self-learning. IEEE Trans. Multimedia 24, 904\u2013916 (2022). https:\/\/doi.org\/10.1109\/TMM.2021.3060948","journal-title":"IEEE Trans. Multimedia"},{"key":"2716_CR33","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., Houlsby, N.: An image is worth 16 x 16 words: transformer for image recognition at scale. In: International Conference on Learning Representations (ICLR), pp. 2010\u2013119292 (2021)"},{"issue":"3","key":"2716_CR34","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M.S., Berg, A.C., Fei-Fei, L.: Imagenet large scale visual recognition challenge. Int. J. Comput. Vis. 115(3), 211\u2013252 (2015). https:\/\/doi.org\/10.1007\/s11263-015-0816-y","journal-title":"Int. J. Comput. Vis."},{"issue":"6","key":"2716_CR35","doi-asserted-by":"publisher","first-page":"1452","DOI":"10.1109\/TPAMI.2017.2723009","volume":"40","author":"B Zhou","year":"2018","unstructured":"Zhou, B., Lapedriza, A., Khosla, A., Oliva, A., Torralba, A.: Places: a 10 million image database for scene recognition. IEEE Trans. Pattern Anal. Mach. Intell. 40(6), 1452\u20131464 (2018). https:\/\/doi.org\/10.1109\/TPAMI.2017.2723009","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2716_CR36","doi-asserted-by":"publisher","unstructured":"Girshick, R.B.: Fast R-CNN. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1440\u20131448 (2015). https:\/\/doi.org\/10.1109\/ICCV.2015.169","DOI":"10.1109\/ICCV.2015.169"},{"key":"2716_CR37","unstructured":"Wu, Y., Kirillov, A., Massa, F., Lo, W.-Y., Girshick, R.: Detectron2 (2019)"},{"key":"2716_CR38","unstructured":"Chung, J., G\u00fcl\u00e7ehre, \u00c7., Cho, K., Bengio, Y.: Empirical evaluation of gated recurrent neural networks on sequence modeling. In: Neural and Evolutionary Computing, pp. 1412\u201335551 (2014)"},{"key":"2716_CR39","doi-asserted-by":"publisher","first-page":"853","DOI":"10.1613\/jair.3994","volume":"47","author":"H Micah","year":"2013","unstructured":"Micah, H., Young, P., Hockenmaier, J.: Framing image description as a ranking task: data, models and evaluation metrics. J. Artif. Intell. Res. 47, 853\u2013899 (2013). https:\/\/doi.org\/10.1613\/jair.3994","journal-title":"J. Artif. Intell. Res."},{"key":"2716_CR40","doi-asserted-by":"crossref","unstructured":"Young, P., Lai, A., Hodosh, M., Hockenmaier, J.: From image descriptions to visual denotations: New similarity metrics for semantic inference over event descriptions. In: Association for Computational Linguistics, vol. 2, pp. 67\u201378 (2014)","DOI":"10.1162\/tacl_a_00166"},{"key":"2716_CR41","doi-asserted-by":"publisher","unstructured":"Lin, T., Maire, M., Belongie, S.J., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., Zitnick, C.L.: Microsoft coco: common objects in context. In: European Conference on Computer Vision (ECCV), vol. 8693, pp. 740\u2013755 (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"2716_CR42","doi-asserted-by":"publisher","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.-J.: BLEU: a method for automatic evaluation of machine translation. In: Association for Computational Linguistics, pp. 311\u2013318 (2002). https:\/\/doi.org\/10.3115\/1073083.1073135","DOI":"10.3115\/1073083.1073135"},{"key":"2716_CR43","doi-asserted-by":"crossref","unstructured":"Lavie, A., Agarwal, A.: METEOR: An automatic metric for MT evaluation with high levels of correlation with human judgments. In: Association for Computational Linguistics, pp. 228\u2013231 (2005)","DOI":"10.3115\/1626355.1626389"},{"key":"2716_CR44","doi-asserted-by":"publisher","unstructured":"Lin, C., Och, F.J.: Automatic evaluation of machine translation quality using longest common subsequence and skip-bigram statistics. In: Association for Computational Linguistics, pp. 605\u2013612 (2004). https:\/\/doi.org\/10.3115\/1218955.1219032","DOI":"10.3115\/1218955.1219032"},{"key":"2716_CR45","doi-asserted-by":"publisher","unstructured":"Vedantam, R., Zitnick, C.L., Parikh, D.: CIDEr: consensus-based image description evaluation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4566\u20134575 (2015). https:\/\/doi.org\/10.1109\/CVPR.2015.7299087","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"2716_CR46","unstructured":"Kingma, D.P., Bah, J.: Adam: a method for stochastic optimization. In: International Conference on Learning Representations (ICLR), pp. 1412\u201369809 (2015)"},{"key":"2716_CR47","doi-asserted-by":"publisher","unstructured":"Chen, L., Zhang, H., Xiao, J., Nie, L., Shao, J., Liu, W., Chua, T.: SCA-CNN: Spatial and channel-wise attention in convolutional networks for image captioning. In: Proceedings of the IEEE conference on computer vision and pattern Recognition (CVPR), pp. 6298\u20136306 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.667","DOI":"10.1109\/CVPR.2017.667"},{"key":"2716_CR48","doi-asserted-by":"publisher","first-page":"694","DOI":"10.1109\/TIP.2019.2928144","volume":"29","author":"L Zhou","year":"2020","unstructured":"Zhou, L., Zhang, Y., Jiang, Y., Zhang, T., Fan, W.: Re-caption: saliency-enhanced image captioning through two-phase learning. IEEE Trans. Image Process. 29, 694\u2013709 (2020). https:\/\/doi.org\/10.1109\/TIP.2019.2928144","journal-title":"IEEE Trans. Image Process."},{"issue":"8","key":"2716_CR49","doi-asserted-by":"publisher","first-page":"2149","DOI":"10.1109\/TMM.2019.2951226","volume":"22","author":"L Guo","year":"2020","unstructured":"Guo, L., Liu, J., Lu, S., Lu, H.: Show, tell, and polish: ruminant decoding for image captioning. IEEE Trans. Multimed. 22(8), 2149\u20132162 (2020). https:\/\/doi.org\/10.1109\/TMM.2019.2951226","journal-title":"IEEE Trans. Multimed."},{"key":"2716_CR50","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1109\/TMM.2020.2976552","volume":"23","author":"J Zhang","year":"2021","unstructured":"Zhang, J., Mei, K., Zheng, Y., Fan, J.: Integrating part of speech guidance for image captioning. IEEE Trans. Multimed. 23, 92\u2013104 (2021). https:\/\/doi.org\/10.1109\/TMM.2020.2976552","journal-title":"IEEE Trans. Multimed."},{"issue":"3","key":"2716_CR51","doi-asserted-by":"publisher","first-page":"808","DOI":"10.1109\/TMM.2019.2931815","volume":"22","author":"L Wu","year":"2020","unstructured":"Wu, L., Xu, M., Wang, J., Perry, S.W.: Recall what you see continually using gridlstm in image captioning. IEEE Trans. Multimed. 22(3), 808\u2013818 (2020). https:\/\/doi.org\/10.1109\/TMM.2019.2931815","journal-title":"IEEE Trans. Multimed."},{"key":"2716_CR52","doi-asserted-by":"publisher","unstructured":"do Carmo\u00a0Nogueira, T., Vinhal, C.D.N., da Cruz\u00a0Jr., G., Ullmann, M.R.D.: Reference-based model using multimodal gated recurrent units for image captioning. Multimed. Tools. Appl. 79(41-42), 30615\u201330635 (2020). https:\/\/doi.org\/10.1007\/s11042-020-09539-5","DOI":"10.1007\/s11042-020-09539-5"},{"key":"2716_CR53","doi-asserted-by":"publisher","first-page":"835","DOI":"10.1109\/TMM.2020.2990074","volume":"23","author":"L Yang","year":"2021","unstructured":"Yang, L., Wang, H., Tang, P., Li, Q.: Captionnet: a tailor-made recurrent neural network for generating image descriptions. IEEE Trans. Multimed 23, 835\u2013845 (2021). https:\/\/doi.org\/10.1109\/TMM.2020.2990074","journal-title":"IEEE Trans. Multimed"},{"issue":"5","key":"2716_CR54","doi-asserted-by":"publisher","first-page":"2313","DOI":"10.1109\/TPAMI.2020.3042192","volume":"44","author":"X Yang","year":"2022","unstructured":"Yang, X., Zhang, H., Cai, J.: Auto-encoding and distilling scene graphs for image captioning. IEEE Trans. Pattern Anal. Mach. Intell. 44(5), 2313\u20132327 (2022). https:\/\/doi.org\/10.1109\/TPAMI.2020.3042192","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2716_CR55","doi-asserted-by":"publisher","first-page":"1775","DOI":"10.1109\/TMM.2021.3072479","volume":"24","author":"L Yu","year":"2022","unstructured":"Yu, L., Zhang, J., Wu, Q.: Dual attention on pyramid feature maps for image captioning. IEEE Trans. Multimed. 24, 1775\u20131786 (2022). https:\/\/doi.org\/10.1109\/TMM.2021.3072479","journal-title":"IEEE Trans. Multimed."},{"issue":"3","key":"2716_CR56","doi-asserted-by":"publisher","first-page":"280","DOI":"10.1049\/cvi2.12087","volume":"16","author":"X Li","year":"2022","unstructured":"Li, X., Zhang, W., Sun, X., Gao, X.: Without detection: two-step clustering features with local-global attention for image captioning. IET Comput. Vis. 16(3), 280\u2013294 (2022). https:\/\/doi.org\/10.1049\/cvi2.12087","journal-title":"IET Comput. Vis."}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-022-02716-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-022-02716-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-022-02716-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,8]],"date-time":"2024-10-08T05:08:41Z","timestamp":1728364121000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-022-02716-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,14]]},"references-count":56,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2023,12]]}},"alternative-id":["2716"],"URL":"https:\/\/doi.org\/10.1007\/s00371-022-02716-7","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"type":"print","value":"0178-2789"},{"type":"electronic","value":"1432-2315"}],"subject":[],"published":{"date-parts":[[2022,11,14]]},"assertion":[{"value":"22 October 2022","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 November 2022","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 that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}