{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T15:47:39Z","timestamp":1784389659896,"version":"3.55.0"},"reference-count":85,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T00:00:00Z","timestamp":1709337600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T00:00:00Z","timestamp":1709337600000},"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":["Int J Comput Vis"],"published-print":{"date-parts":[[2024,8]]},"DOI":"10.1007\/s11263-024-02020-y","type":"journal-article","created":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T06:01:21Z","timestamp":1709359281000},"page":"3067-3085","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":125,"title":["Cross-Modal Fusion and Progressive Decoding Network for RGB-D Salient Object Detection"],"prefix":"10.1007","volume":"132","author":[{"given":"Xihang","family":"Hu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3932-2712","authenticated-orcid":false,"given":"Fuming","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fasheng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haojie","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,3,2]]},"reference":[{"key":"2020_CR1","doi-asserted-by":"crossref","unstructured":"Achanta, R., Hemami, S., Estrada, F., & Susstrunk, S. (2009). Frequency-tuned salient region detection. In 2009 IEEE conference on computer vision and pattern recognition (pp. 1597\u20131604). IEEE.","DOI":"10.1109\/CVPRW.2009.5206596"},{"issue":"2","key":"2020_CR2","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1007\/s41095-019-0149-9","volume":"5","author":"A Borji","year":"2019","unstructured":"Borji, A., Cheng, M.-M., Hou, Q., Jiang, H., & Li, J. (2019). Salient object detection: A survey. Computational Visual Media, 5(2), 117\u2013150.","journal-title":"Computational Visual Media"},{"issue":"12","key":"2020_CR3","doi-asserted-by":"publisher","first-page":"5706","DOI":"10.1109\/TIP.2015.2487833","volume":"24","author":"A Borji","year":"2015","unstructured":"Borji, A., Cheng, M.-M., Jiang, H., & Li, J. (2015). Salient object detection: A benchmark. IEEE Transactions on Image Processing, 24(12), 5706\u20135722.","journal-title":"IEEE Transactions on Image Processing"},{"key":"2020_CR4","doi-asserted-by":"crossref","unstructured":"Chen, H., & Li, Y. (2018). Progressively complementarity-aware fusion network for rgb-d salient object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 3051\u20133060).","DOI":"10.1109\/CVPR.2018.00322"},{"issue":"6","key":"2020_CR5","doi-asserted-by":"publisher","first-page":"2825","DOI":"10.1109\/TIP.2019.2891104","volume":"28","author":"H Chen","year":"2019","unstructured":"Chen, H., & Li, Y. (2019). Three-stream attention-aware network for rgb-d salient object detection. IEEE Transactions on Image Processing, 28(6), 2825\u20132835.","journal-title":"IEEE Transactions on Image Processing"},{"issue":"4","key":"2020_CR6","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"L-C Chen","year":"2017","unstructured":"Chen, L.-C., Papandreou, G., Kokkinos, I., Murphy, K., & Yuille, A. L. (2017). Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE Transactions on Pattern Analysis and Machine Intelligence, 40(4), 834\u2013848.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2020_CR7","doi-asserted-by":"crossref","unstructured":"Chen, Q., Liu, Z., Zhang, Y., Fu, K., Zhao, Q., & Du, H. (2021). Rgb-d salient object detection via 3d convolutional neural networks. In Proceedings of the AAAI conference on artificial intelligence (Vol. 35, pp. 1063\u20131071).","DOI":"10.1609\/aaai.v35i2.16191"},{"key":"2020_CR8","doi-asserted-by":"publisher","first-page":"7012","DOI":"10.1109\/TIP.2020.3028289","volume":"30","author":"Z Chen","year":"2020","unstructured":"Chen, Z., Cong, R., Xu, Q., & Huang, Q. (2020). Dpanet: Depth potentiality-aware gated attention network for rgb-d salient object detection. IEEE Transactions on Image Processing, 30, 7012\u20137024.","journal-title":"IEEE Transactions on Image Processing"},{"key":"2020_CR9","doi-asserted-by":"crossref","unstructured":"Cheng, Y., Fu, H., Wei, X., Xiao, J., & Cao, X. (2014). Depth enhanced saliency detection method. In Proceedings of international conference on internet multimedia computing and service (pp. 23\u201327).","DOI":"10.1145\/2632856.2632866"},{"issue":"3","key":"2020_CR10","doi-asserted-by":"publisher","first-page":"569","DOI":"10.1109\/TPAMI.2014.2345401","volume":"37","author":"M-M Cheng","year":"2014","unstructured":"Cheng, M.-M., Mitra, N. J., Huang, X., Torr, P. H., & Hu, S.-M. (2014). Global contrast based salient region detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 37(3), 569\u2013582.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"7","key":"2020_CR11","doi-asserted-by":"publisher","first-page":"1660","DOI":"10.1109\/TMM.2018.2884481","volume":"21","author":"R Cong","year":"2018","unstructured":"Cong, R., Lei, J., Fu, H., Huang, Q., Cao, X., & Ling, N. (2018). Hscs: Hierarchical sparsity based co-saliency detection for rgbd images. IEEE Transactions on Multimedia, 21(7), 1660\u20131671.","journal-title":"IEEE Transactions on Multimedia"},{"key":"2020_CR12","doi-asserted-by":"publisher","first-page":"6800","DOI":"10.1109\/TIP.2022.3216198","volume":"31","author":"R Cong","year":"2022","unstructured":"Cong, R., Lin, Q., Zhang, C., Li, C., Cao, X., Huang, Q., & Zhao, Y. (2022). Cir-net: Cross-modality interaction and refinement for rgb-d salient object detection. IEEE Transactions on Image Processing, 31, 6800\u20136815.","journal-title":"IEEE Transactions on Image Processing"},{"issue":"1","key":"2020_CR13","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1007\/s10479-005-5724-z","volume":"134","author":"P-T De Boer","year":"2005","unstructured":"De Boer, P.-T., Kroese, D. P., Mannor, S., & Rubinstein, R. Y. (2005). A tutorial on the cross-entropy method. Annals of Operations Research, 134(1), 19\u201367.","journal-title":"Annals of Operations Research"},{"key":"2020_CR14","doi-asserted-by":"crossref","unstructured":"Deng, Z., Hu, X., Zhu, L., Xu, X., Qin, J., Han, G., & Heng, P.-A. (2018). R3net: Recurrent residual refinement network for saliency detection. In Proceedings of the 27th international joint conference on artificial intelligence (pp. 684\u2013690). AAAI Press Menlo Park, CA, USA.","DOI":"10.24963\/ijcai.2018\/95"},{"key":"2020_CR15","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. (2021). An image is worth 16x16 words: Transformers for image recognition at scale. In International conference on learning representations."},{"key":"2020_CR16","doi-asserted-by":"crossref","unstructured":"Fan, D., Gong, C., Cao, Y., Ren, B., Cheng, M., & Borji, A. (2018). Enhanced-alignment measure for binary foreground map evaluation. In Proceedings of the twenty-seventh international joint conference on artificial intelligence, IJCAI 2018, July 13\u201319, 2018, Stockholm, Sweden (pp. 698\u2013704).","DOI":"10.24963\/ijcai.2018\/97"},{"key":"2020_CR17","doi-asserted-by":"crossref","unstructured":"Fan, D.-P., Cheng, M.-M., Liu, Y., Li, T., & Borji, A. (2017). Structure-measure: A new way to evaluate foreground maps. In Proceedings of the IEEE international conference on computer vision (pp. 4548\u20134557).","DOI":"10.1109\/ICCV.2017.487"},{"issue":"5","key":"2020_CR18","doi-asserted-by":"publisher","first-page":"2075","DOI":"10.1109\/TNNLS.2020.2996406","volume":"32","author":"D-P Fan","year":"2020","unstructured":"Fan, D.-P., Lin, Z., Zhang, Z., Zhu, M., & Cheng, M.-M. (2020). Rethinking rgb-d salient object detection: Models, data sets, and large-scale benchmarks. IEEE Transactions on Neural Networks and Learning Systems, 32(5), 2075\u20132089.","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"2020_CR19","doi-asserted-by":"crossref","unstructured":"Fan, D.-P., Zhai, Y., Borji, A., Yang, J., & Shao, L. (2020). Bbs-net: Rgb-d salient object detection with a bifurcated backbone strategy network. In European conference on computer vision (pp. 275\u2013292). Springer.","DOI":"10.1007\/978-3-030-58610-2_17"},{"key":"2020_CR20","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108666","volume":"128","author":"G Feng","year":"2022","unstructured":"Feng, G., Meng, J., Zhang, L., & Lu, H. (2022). Encoder deep interleaved network with multi-scale aggregation for RGB-D salient object detection. Pattern Recognition, 128, 108666.","journal-title":"Pattern Recognition"},{"issue":"9","key":"2020_CR21","first-page":"5541","volume":"44","author":"K Fu","year":"2021","unstructured":"Fu, K., Fan, D.-P., Ji, G.-P., Zhao, Q., Shen, J., & Zhu, C. (2021). Siamese network for rgb-d salient object detection and beyond. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(9), 5541\u20135559.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"2","key":"2020_CR22","doi-asserted-by":"publisher","first-page":"652","DOI":"10.1109\/TPAMI.2019.2938758","volume":"43","author":"S-H Gao","year":"2019","unstructured":"Gao, S.-H., Cheng, M.-M., Zhao, K., Zhang, X.-Y., Yang, M.-H., & Torr, P. (2019). Res2net: A new multi-scale backbone architecture. IEEE Transactions on Pattern Analysis and Machine Intelligence, 43(2), 652\u2013662.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2020_CR23","doi-asserted-by":"crossref","unstructured":"Ha, Q., Watanabe, K., Karasawa, T., Ushiku, Y., & Harada, T. (2017). Mfnet: Towards real-time semantic segmentation for autonomous vehicles with multi-spectral scenes. In 2017 IEEE\/RSJ international conference on intelligent robots and systems (IROS) (pp. 5108\u20135115). IEEE.","DOI":"10.1109\/IROS.2017.8206396"},{"issue":"8","key":"2020_CR24","first-page":"1309","volume":"25","author":"J Han","year":"2014","unstructured":"Han, J., Zhang, D., Hu, X., Guo, L., Ren, J., & Wu, F. (2014). Background prior-based salient object detection via deep reconstruction residual. IEEE Transactions on Circuits and Systems for Video Technology, 25(8), 1309\u20131321.","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"2020_CR25","doi-asserted-by":"crossref","unstructured":"Hou, Q., Zhou, D., & Feng, J. (2021). Coordinate attention for efficient mobile network design. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 13713\u201313722).","DOI":"10.1109\/CVPR46437.2021.01350"},{"key":"2020_CR26","doi-asserted-by":"publisher","first-page":"1651","DOI":"10.1109\/TMM.2021.3069297","volume":"24","author":"N Huang","year":"2021","unstructured":"Huang, N., Yang, Y., Zhang, D., Zhang, Q., & Han, J. (2021). Employing bilinear fusion and saliency prior information for rgb-d salient object detection. IEEE Transactions on Multimedia, 24, 1651\u20131664.","journal-title":"IEEE Transactions on Multimedia"},{"key":"2020_CR27","doi-asserted-by":"crossref","unstructured":"Ji, W., Li, J., Yu, S., Zhang, M., Piao, Y., Yao, S., Bi, Q., Ma, K., Zheng, Y., & Lu, H. (2021). Calibrated rgb-d salient object detection. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 9471\u20139481).","DOI":"10.1109\/CVPR46437.2021.00935"},{"key":"2020_CR28","doi-asserted-by":"crossref","unstructured":"Ji, W., Li, J., Zhang, M., Piao, Y., & Lu, H. (2020). Accurate rgb-d salient object detection via collaborative learning. In European conference on computer vision (pp. 52\u201369). Springer.","DOI":"10.1007\/978-3-030-58523-5_4"},{"key":"2020_CR29","doi-asserted-by":"publisher","first-page":"2321","DOI":"10.1109\/TIP.2022.3154931","volume":"31","author":"W Ji","year":"2022","unstructured":"Ji, W., Yan, G., Li, J., Piao, Y., Yao, S., Zhang, M., Cheng, L., & Lu, H. (2022). Dmra: Depth-induced multi-scale recurrent attention network for rgb-d saliency detection. IEEE Transactions on Image Processing, 31, 2321\u20132336.","journal-title":"IEEE Transactions on Image Processing"},{"key":"2020_CR30","doi-asserted-by":"crossref","unstructured":"Jiang, H., Wang, J., Yuan, Z., Wu, Y., Zheng, N., & Li, S. (2013). Salient object detection: A discriminative regional feature integration approach. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 2083\u20132090).","DOI":"10.1109\/CVPR.2013.271"},{"key":"2020_CR31","doi-asserted-by":"crossref","unstructured":"Jiang, Z., & Davis, L. S. (2013). Submodular salient region detection. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 2043\u20132050).","DOI":"10.1109\/CVPR.2013.266"},{"key":"2020_CR32","unstructured":"Kingma, D. P., & Ba, J. (2015). Adam: A method for stochastic optimization. In 3rd International conference on learning representations, ICLR 2015, San Diego, CA, USA, May 7\u20139, 2015, conference track proceedings."},{"key":"2020_CR33","doi-asserted-by":"crossref","unstructured":"Klein, D. A., & Frintrop, S. (2011). Center-surround divergence of feature statistics for salient object detection. In 2011 International conference on computer vision (pp. 2214\u20132219). IEEE.","DOI":"10.1109\/ICCV.2011.6126499"},{"issue":"5","key":"2020_CR34","doi-asserted-by":"publisher","first-page":"5817","DOI":"10.1007\/s10489-021-02687-7","volume":"52","author":"X Lan","year":"2022","unstructured":"Lan, X., Gu, X., & Gu, X. (2022). Mmnet: Multi-modal multi-stage network for rgb-t image semantic segmentation. Applied Intelligence, 52(5), 5817\u20135829.","journal-title":"Applied Intelligence"},{"key":"2020_CR35","unstructured":"Lee, C.-Y., Xie, S., Gallagher, P., Zhang, Z., & Tu, Z. (2015). Deeply-supervised nets. In Artificial intelligence and statistics (pp. 562\u2013570). PMLR."},{"key":"2020_CR36","doi-asserted-by":"crossref","unstructured":"Lee, M., Park, C., Cho, S., & Lee, S. (2022). Spsn: Superpixel prototype sampling network for rgb-d salient object detection. In European conference on computer vision (pp. 630\u2013647). Springer.","DOI":"10.1007\/978-3-031-19818-2_36"},{"key":"2020_CR37","doi-asserted-by":"publisher","first-page":"3528","DOI":"10.1109\/TIP.2021.3062689","volume":"30","author":"G Li","year":"2021","unstructured":"Li, G., Liu, Z., Chen, M., Bai, Z., Lin, W., & Ling, H. (2021). Hierarchical alternate interaction network for rgb-d salient object detection. IEEE Transactions on Image Processing, 30, 3528\u20133542.","journal-title":"IEEE Transactions on Image Processing"},{"key":"2020_CR38","doi-asserted-by":"crossref","unstructured":"Li, N., Ye, J., Ji, Y., Ling, H., & Yu, J. (2014). Saliency detection on light field. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 2806\u20132813).","DOI":"10.1109\/CVPR.2014.359"},{"key":"2020_CR39","doi-asserted-by":"publisher","first-page":"132","DOI":"10.1016\/j.neucom.2022.03.029","volume":"490","author":"Y Liang","year":"2022","unstructured":"Liang, Y., Qin, G., Sun, M., Qin, J., Yan, J., & Zhang, Z. (2022). Multi-modal interactive attention and dual progressive decoding network for RGB-D\/T salient object detection. Neurocomputing, 490, 132\u2013145.","journal-title":"Neurocomputing"},{"key":"2020_CR40","doi-asserted-by":"crossref","unstructured":"Liu, J. J., Hou, Q., Cheng, M. M., Feng, J., & Jiang, J. (2019). A simple pooling-based design for real-time salient object detection. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 3917\u20133926).","DOI":"10.1109\/CVPR.2019.00404"},{"key":"2020_CR41","doi-asserted-by":"crossref","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 Proceedings of the IEEE\/CVF International Conference on Computer Vision (pp. 10012\u201310022).","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"2020_CR42","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1016\/j.neucom.2019.07.012","volume":"363","author":"Z Liu","year":"2019","unstructured":"Liu, Z., Shi, S., Duan, Q., Zhang, W., & Zhao, P. (2019). Salient object detection for rgb-d image by single stream recurrent convolution neural network. Neurocomputing, 363, 46\u201357.","journal-title":"Neurocomputing"},{"issue":"7","key":"2020_CR43","doi-asserted-by":"publisher","first-page":"4486","DOI":"10.1109\/TCSVT.2021.3127149","volume":"32","author":"Z Liu","year":"2021","unstructured":"Liu, Z., Tan, Y., He, Q., & Xiao, Y. (2021). Swinnet: Swin transformer drives edge-aware rgb-d and rgb-t salient object detection. IEEE Transactions on Circuits and Systems for Video Technology, 32(7), 4486\u20134497.","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"2020_CR44","doi-asserted-by":"crossref","unstructured":"Liu, Z., Wang, Y., Tu, Z., Xiao, Y., & Tang, B. (2021). Tritransnet: Rgb-d salient object detection with a triplet transformer embedding network. In Proceedings of the 29th ACM international conference on multimedia (pp. 4481\u20134490).","DOI":"10.1145\/3474085.3475601"},{"key":"2020_CR45","doi-asserted-by":"crossref","unstructured":"Luo, Z., Mishra, A., Achkar, A., Eichel, J., Li, S., & Jodoin, P.-M. (2017). Non-local deep features for salient object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 6609\u20136617).","DOI":"10.1109\/CVPR.2017.698"},{"key":"2020_CR46","first-page":"1","volume":"70","author":"J Ma","year":"2021","unstructured":"Ma, J., Tang, L., Xu, M., Zhang, H., & Xiao, G. (2021). Stdfusionnet: An infrared and visible image fusion network based on salient target detection. IEEE Transactions on Instrumentation and Measurement, 70, 1\u201313.","journal-title":"IEEE Transactions on Instrumentation and Measurement"},{"key":"2020_CR47","doi-asserted-by":"crossref","unstructured":"M\u00e1ttyus, G., Luo, W., & Urtasun, R. (2017). Deeproadmapper: Extracting road topology from aerial images. In Proceedings of the IEEE international conference on computer vision (pp. 3438\u20133446).","DOI":"10.1109\/ICCV.2017.372"},{"key":"2020_CR48","doi-asserted-by":"crossref","unstructured":"Pang, Y., Zhang, L., Zhao, X., & Lu, H. (2020). Hierarchical dynamic filtering network for rgb-d salient object detection. In European conference on computer vision (pp. 235\u2013252). Springer.","DOI":"10.1007\/978-3-030-58595-2_15"},{"key":"2020_CR49","doi-asserted-by":"crossref","unstructured":"Pang, Y., Zhao, X., Zhang, L., & Lu, H. (2020). Multi-scale interactive network for salient object detection. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 9413\u20139422).","DOI":"10.1109\/CVPR42600.2020.00943"},{"key":"2020_CR50","doi-asserted-by":"publisher","first-page":"892","DOI":"10.1109\/TIP.2023.3234702","volume":"32","author":"Y Pang","year":"2023","unstructured":"Pang, Y., Zhao, X., Zhang, L., & Lu, H. (2023). CAVER: Cross-modal view-mixed transformer for bi-modal salient object detection. IEEE Transactions on Image Processing, 32, 892\u2013904.","journal-title":"IEEE Transactions on Image Processing"},{"key":"2020_CR51","doi-asserted-by":"crossref","unstructured":"Peng, H., Li, B., Xiong, W., Hu, W., & Ji, R. (2014). Rgbd salient object detection: A benchmark and algorithms. In European conference on computer vision (pp. 92\u2013109). Springer.","DOI":"10.1007\/978-3-319-10578-9_7"},{"key":"2020_CR52","doi-asserted-by":"crossref","unstructured":"Perazzi, F., Kr\u00e4henb\u00fchl, P., Pritch, Y., & Hornung, A. (2012). Saliency filters: Contrast based filtering for salient region detection. In 2012 IEEE conference on computer vision and pattern recognition (pp. 733\u2013740). IEEE.","DOI":"10.1109\/CVPR.2012.6247743"},{"key":"2020_CR53","doi-asserted-by":"crossref","unstructured":"Piao, Y., Ji, W., Li, J., Zhang, M., & Lu, H. (2019). Depth-induced multi-scale recurrent attention network for saliency detection. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 7254\u20137263).","DOI":"10.1109\/ICCV.2019.00735"},{"key":"2020_CR54","doi-asserted-by":"crossref","unstructured":"Qin, X., Zhang, Z., Huang, C., Gao, C., Dehghan, M., & Jagersand, M. (2019). Basnet: Boundary-aware salient object detection. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 7479\u20137489).","DOI":"10.1109\/CVPR.2019.00766"},{"key":"2020_CR55","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107404","volume":"106","author":"X Qin","year":"2020","unstructured":"Qin, X., Zhang, Z., Huang, C., Dehghan, M., Zaiane, O. R., & Jagersand, M. (2020). U2-net: Going deeper with nested u-structure for salient object detection. Pattern Recognition, 106, 107404.","journal-title":"Pattern Recognition"},{"key":"2020_CR56","doi-asserted-by":"publisher","first-page":"6124","DOI":"10.1109\/TIP.2022.3205747","volume":"31","author":"M Song","year":"2022","unstructured":"Song, M., Song, W., Yang, G., & Chen, C. (2022). Improving RGB-D salient object detection via modality-aware decoder. IEEE Transactions on Image Processing, 31, 6124\u20136138.","journal-title":"IEEE Transactions on Image Processing"},{"issue":"3","key":"2020_CR57","doi-asserted-by":"publisher","first-page":"1000","DOI":"10.1109\/TASE.2020.2993143","volume":"18","author":"Y Sun","year":"2021","unstructured":"Sun, Y., Zuo, W., Yun, P., Wang, H., & Liu, M. (2021). Fuseseg: Semantic segmentation of urban scenes based on RGB and thermal data fusion. IEEE Transactions on Automation Science and Engineering, 18(3), 1000\u20131011.","journal-title":"IEEE Transactions on Automation Science and Engineering"},{"key":"2020_CR58","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.101828","volume":"98","author":"D Wang","year":"2023","unstructured":"Wang, D., Liu, J., Liu, R., & Fan, X. (2023). An interactively reinforced paradigm for joint infrared-visible image fusion and saliency object detection. Information Fusion, 98, 101828.","journal-title":"Information Fusion"},{"key":"2020_CR59","doi-asserted-by":"publisher","first-page":"1285","DOI":"10.1109\/TIP.2022.3140606","volume":"31","author":"F Wang","year":"2022","unstructured":"Wang, F., Pan, J., Xu, S., & Tang, J. (2022). Learning discriminative cross-modality features for rgb-d saliency detection. IEEE Transactions on Image Processing, 31, 1285\u20131297.","journal-title":"IEEE Transactions on Image Processing"},{"key":"2020_CR60","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.119047","volume":"214","author":"F Wang","year":"2023","unstructured":"Wang, F., Wang, R., & Sun, F. (2023). Dcmnet: Discriminant and cross-modality network for RGB-D salient object detection. Expert Systems with Applications, 214, 119047.","journal-title":"Expert Systems with Applications"},{"key":"2020_CR61","doi-asserted-by":"crossref","unstructured":"Wang, L., Lu, H., Ruan, X., & Yang, M.-H. (2015). Deep networks for saliency detection via local estimation and global search. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 3183\u20133192).","DOI":"10.1109\/CVPR.2015.7298938"},{"key":"2020_CR62","doi-asserted-by":"crossref","unstructured":"Wang, W., Xie, E., Li, X., Fan, D.-P., Song, K., Liang, D., Lu, T., Luo, P., & Shao, L. (2021). Pyramid vision transformer: A versatile backbone for dense prediction without convolutions. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 568\u2013578).","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"2020_CR63","doi-asserted-by":"crossref","unstructured":"Wei, J., Wang, S., & Huang, Q. (2020). F$$^3$$net: Fusion, feedback and focus for salient object detection. In Proceedings of the AAAI conference on artificial intelligence (Vol. 34, pp. 12321\u201312328).","DOI":"10.1609\/aaai.v34i07.6916"},{"key":"2020_CR64","doi-asserted-by":"crossref","unstructured":"Wei, J., Wang, S., Wu, Z., Su, C., Huang, Q., & Tian, Q. (2020). Label decoupling framework for salient object detection. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 13025\u201313034).","DOI":"10.1109\/CVPR42600.2020.01304"},{"key":"2020_CR65","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.-Y., & Kweon, I.S. (2018). Cbam: Convolutional block attention module. In Proceedings of the European conference on computer vision (ECCV) (pp. 3\u201319).","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"2020_CR66","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.116614","volume":"195","author":"J Wu","year":"2022","unstructured":"Wu, J., Sun, F., Xu, R., Meng, J., & Wang, F. (2022). Aggregate interactive learning for rgb-d salient object detection. Expert Systems with Applications, 195, 116614.","journal-title":"Expert Systems with Applications"},{"key":"2020_CR67","doi-asserted-by":"crossref","unstructured":"Wu, R., Feng, M., Guan, W., Wang, D., Lu, H., & Ding, E. (2019). A mutual learning method for salient object detection with intertwined multi-supervision. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 8150\u20138159).","DOI":"10.1109\/CVPR.2019.00834"},{"key":"2020_CR68","doi-asserted-by":"crossref","unstructured":"Yan, Q., Xu, L., Shi, J., & Jia, J. (2013). Hierarchical saliency detection. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 1155\u20131162).","DOI":"10.1109\/CVPR.2013.153"},{"issue":"8","key":"2020_CR69","doi-asserted-by":"publisher","first-page":"5346","DOI":"10.1109\/TCSVT.2022.3144852","volume":"32","author":"Y Yang","year":"2022","unstructured":"Yang, Y., Qin, Q., Luo, Y., Liu, Y., Zhang, Q., & Han, J. (2022). Bi-directional progressive guidance network for RGB-D salient object detection. IEEE Transactions on Circuits and Systems for Video Technology, 32(8), 5346\u20135360.","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"issue":"5","key":"2020_CR70","doi-asserted-by":"publisher","first-page":"865","DOI":"10.1109\/TPAMI.2016.2567393","volume":"39","author":"D Zhang","year":"2016","unstructured":"Zhang, D., Meng, D., & Han, J. (2016). Co-saliency detection via a self-paced multiple-instance learning framework. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(5), 865\u2013878.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2020_CR71","doi-asserted-by":"crossref","unstructured":"Zhang, L., Dai, J., Lu, H., He, Y., & Wang, G. (2018). A bi-directional message passing model for salient object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 1741\u20131750).","DOI":"10.1109\/CVPR.2018.00187"},{"key":"2020_CR72","doi-asserted-by":"crossref","unstructured":"Zhang, M., Ren, W., Piao, Y., Rong, Z., & Lu, H. (2020). Select, supplement and focus for rgb-d saliency detection. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 3472\u20133481).","DOI":"10.1109\/CVPR42600.2020.00353"},{"key":"2020_CR73","doi-asserted-by":"publisher","first-page":"5142","DOI":"10.1109\/TMM.2022.3187856","volume":"25","author":"M Zhang","year":"2023","unstructured":"Zhang, M., Yao, S., Hu, B., Piao, Y., & Ji, W. (2023). C$$^2$$dfnet: Criss-cross dynamic filter network for rgb-d salient object detection. IEEE Transactions on Multimedia, 25, 5142\u20135154.","journal-title":"IEEE Transactions on Multimedia"},{"key":"2020_CR74","doi-asserted-by":"crossref","unstructured":"Zhang, P., Wang, D., Lu, H., Wang, H., & Ruan, X. (2017) Amulet: Aggregating multi-level convolutional features for salient object detection. In Proceedings of the IEEE international conference on computer vision (pp. 202\u2013211).","DOI":"10.1109\/ICCV.2017.31"},{"key":"2020_CR75","doi-asserted-by":"crossref","unstructured":"Zhang, Q., Zhao, S., Luo, Y., Zhang, D., Huang, N., & Han, J. (2021). Abmdrnet: Adaptive-weighted bi-directional modality difference reduction network for rgb-t semantic segmentation. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 2633\u20132642).","DOI":"10.1109\/CVPR46437.2021.00266"},{"key":"2020_CR76","doi-asserted-by":"crossref","unstructured":"Zhao, J.-X., Cao, Y., Fan, D.-P., Cheng, M.-M., Li, X.-Y., & Zhang, L. (2019). Contrast prior and fluid pyramid integration for rgbd salient object detection. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 3927\u20133936).","DOI":"10.1109\/CVPR.2019.00405"},{"key":"2020_CR77","doi-asserted-by":"crossref","unstructured":"Zhao, J.-X., Liu, J.-J., Fan, D.-P., Cao, Y., Yang, J., & Cheng, M.-M. (2019). Egnet: Edge guidance network for salient object detection. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 8779\u20138788).","DOI":"10.1109\/ICCV.2019.00887"},{"key":"2020_CR78","doi-asserted-by":"crossref","unstructured":"Zhao, X., Pang, Y., Zhang, L., Lu, H., & Ruan, X. (2022). Self-supervised pretraining for rgb-d salient object detection. In Proceedings of the AAAI conference on artificial intelligence (Vol. 36, pp. 3463\u20133471).","DOI":"10.1609\/aaai.v36i3.20257"},{"key":"2020_CR79","doi-asserted-by":"crossref","unstructured":"Zhao, X., Pang, Y., Zhang, L., Lu, H., & Zhang, L. (2020) Suppress and balance: A simple gated network for salient object detection. In European conference on computer vision (pp. 35\u201351). Springer.","DOI":"10.1007\/978-3-030-58536-5_3"},{"key":"2020_CR80","doi-asserted-by":"crossref","unstructured":"Zhao, X., Zhang, L., Pang, Y., Lu, H., & Zhang, L. (2020). A single stream network for robust and real-time rgb-d salient object detection. In European conference on computer vision (pp. 646\u2013662). Springer.","DOI":"10.1007\/978-3-030-58542-6_39"},{"key":"2020_CR81","doi-asserted-by":"publisher","first-page":"1035","DOI":"10.1109\/TMM.2020.2991592","volume":"23","author":"L Zhou","year":"2020","unstructured":"Zhou, L., Gong, C., Liu, Z., & Fu, K. (2020). Sal: Selection and attention losses for weakly supervised semantic segmentation. IEEE Transactions on Multimedia, 23, 1035\u20131048.","journal-title":"IEEE Transactions on Multimedia"},{"key":"2020_CR82","doi-asserted-by":"crossref","unstructured":"Zhou, W., Dong, S., Xu, C., & Qian, Y. (2022). Edge-aware guidance fusion network for rgb\u2013thermal scene parsing. In Proceedings of the AAAI conference on artificial intelligence (Vol. 36, pp. 3571\u20133579).","DOI":"10.1609\/aaai.v36i3.20269"},{"issue":"3","key":"2020_CR83","doi-asserted-by":"publisher","first-page":"1224","DOI":"10.1109\/TCSVT.2021.3077058","volume":"32","author":"W Zhou","year":"2021","unstructured":"Zhou, W., Guo, Q., Lei, J., Yu, L., & Hwang, J.-N. (2021). Ecffnet: Effective and consistent feature fusion network for rgb-t salient object detection. IEEE Transactions on Circuits and Systems for Video Technology, 32(3), 1224\u20131235.","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"2020_CR84","doi-asserted-by":"crossref","unstructured":"Zhu, C., Cai, X., Huang, K., Li, T. H., & Li, G. (2019). Pdnet: Prior-model guided depth-enhanced network for salient object detection. In 2019 IEEE international conference on multimedia and expo (ICME) (pp. 199\u2013204). IEEE.","DOI":"10.1109\/ICME.2019.00042"},{"issue":"3","key":"2020_CR85","first-page":"3738","volume":"45","author":"M Zhuge","year":"2022","unstructured":"Zhuge, M., Fan, D.-P., Liu, N., Zhang, D., Xu, D., & Shao, L. (2022). Salient object detection via integrity learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(3), 3738\u20133752.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02020-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-024-02020-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02020-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,11]],"date-time":"2024-07-11T14:22:28Z","timestamp":1720707748000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-024-02020-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,2]]},"references-count":85,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2024,8]]}},"alternative-id":["2020"],"URL":"https:\/\/doi.org\/10.1007\/s11263-024-02020-y","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3,2]]},"assertion":[{"value":"3 January 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 January 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 March 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}