{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T04:42:43Z","timestamp":1743050563328,"version":"3.40.3"},"publisher-location":"Cham","reference-count":46,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031784460"},{"type":"electronic","value":"9783031784477"}],"license":[{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"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":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-78447-7_2","type":"book-chapter","created":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:24:11Z","timestamp":1733185451000},"page":"16-29","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Multi-ground Truth Approach for\u00a0RGB-D Saliency Detection"],"prefix":"10.1007","author":[{"given":"Nguyen Truong Thinh","family":"Huynh","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Van Linh","family":"Pham","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuan Toan","family":"Mai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tuan Anh","family":"Tran","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,3]]},"reference":[{"key":"2_CR1","doi-asserted-by":"crossref","unstructured":"Achanta, R., Hemami, S., Estrada, F., Susstrunk, S.: Frequency-tuned salient region detection. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1597\u20131604. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206596"},{"key":"2_CR2","doi-asserted-by":"publisher","unstructured":"Bachmann, R., Mizrahi, D., Atanov, A., Zamir, A.: MultiMAE: multi-modal multi-task masked autoencoders. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13697, pp. 348\u2013367. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19836-6_20","DOI":"10.1007\/978-3-031-19836-6_20"},{"key":"2_CR3","doi-asserted-by":"crossref","unstructured":"Bi, H., Wu, R., Liu, Z., Zhu, H., Zhang, C., Xiang, T.Z.: Cross-modal hierarchical interaction network for RGB-D salient object detection. Pattern Recognit. 136, 109194 (2022). https:\/\/api.semanticscholar.org\/CorpusID:253822254","DOI":"10.1016\/j.patcog.2022.109194"},{"issue":"12","key":"2_CR4","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.: Salient object detection: a benchmark. IEEE Trans. Image Process. 24(12), 5706\u20135722 (2015)","journal-title":"IEEE Trans. Image Process."},{"key":"2_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1007\/978-3-030-01264-9_9","volume-title":"Computer Vision \u2013 ECCV 2018","author":"M Caron","year":"2018","unstructured":"Caron, M., Bojanowski, P., Joulin, A., Douze, M.: Deep clustering for unsupervised learning of visual features. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer Vision \u2013 ECCV 2018. LNCS, vol. 11218, pp. 139\u2013156. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01264-9_9"},{"key":"2_CR6","doi-asserted-by":"publisher","first-page":"152","DOI":"10.1016\/j.neucom.2022.12.004","volume":"522","author":"T Chen","year":"2023","unstructured":"Chen, T., Xiao, J., Hu, X., Zhang, G., Wang, S.: Adaptive fusion network for RGB-D salient object detection. Neurocomputing 522, 152\u2013164 (2023)","journal-title":"Neurocomputing"},{"key":"2_CR7","doi-asserted-by":"crossref","unstructured":"Cheng, Y., Fu, H., Wei, X., Xiao, J., Cao, X.: Depth enhanced saliency detection method. In: Proceedings of International Conference on Internet Multimedia Computing and Service, pp. 23\u201327 (2014)","DOI":"10.1145\/2632856.2632866"},{"key":"2_CR8","unstructured":"Couprie, C., Farabet, C., Najman, L., LeCun, Y.: Indoor semantic segmentation using depth information. CoRR abs\/1301.3572 (2013). https:\/\/api.semanticscholar.org\/CorpusID:6681692"},{"key":"2_CR9","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"2_CR10","doi-asserted-by":"crossref","unstructured":"Fan, D.P., Cheng, M.M., Liu, Y., Li, T., Borji, A.: Structure-measure: a new way to evaluate foreground maps. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4548\u20134557 (2017)","DOI":"10.1109\/ICCV.2017.487"},{"key":"2_CR11","doi-asserted-by":"crossref","unstructured":"Fan, D.P., Gong, C., Cao, Y., Ren, B., Cheng, M.M., Borji, A.: Enhanced-alignment measure for binary foreground map evaluation. In: International Joint Conference on Artificial Intelligence (2018). https:\/\/api.semanticscholar.org\/CorpusID:44072899","DOI":"10.24963\/ijcai.2018\/97"},{"issue":"5","key":"2_CR12","doi-asserted-by":"publisher","first-page":"2075","DOI":"10.1109\/TNNLS.2020.2996406","volume":"32","author":"DP Fan","year":"2020","unstructured":"Fan, D.P., Lin, Z., Zhang, Z., Zhu, M., Cheng, M.M.: Rethinking RGB-D salient object detection: models, data sets, and large-scale benchmarks. IEEE Trans. Neural Netw. Learn. Syst. 32(5), 2075\u20132089 (2020)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"2_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"275","DOI":"10.1007\/978-3-030-58610-2_17","volume-title":"Computer Vision \u2013 ECCV 2020","author":"D-P Fan","year":"2020","unstructured":"Fan, D.-P., Zhai, Y., Borji, A., Yang, J., Shao, L.: BBS-net: RGB-D salient object detection with a bifurcated backbone strategy network. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12357, pp. 275\u2013292. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58610-2_17"},{"key":"2_CR14","doi-asserted-by":"crossref","unstructured":"Fang, X., Zhu, J., Shao, X., Wang, H.: Grouptransnet: group transformer network for RGB-D salient object detection. arXiv preprint arXiv:2203.10785 (2022)","DOI":"10.2139\/ssrn.4585918"},{"key":"2_CR15","doi-asserted-by":"crossref","unstructured":"Fu, K., Fan, D.P., Ji, G.P., Zhao, Q.: JL-DCF: joint learning and densely-cooperative fusion framework for RGB-D salient object detection, pp. 3052\u20133062 (2020)","DOI":"10.1109\/CVPR42600.2020.00312"},{"key":"2_CR16","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16000\u201316009 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"2_CR17","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"2_CR18","doi-asserted-by":"crossref","unstructured":"Ju, R., Ge, L., Geng, W., Ren, T., Wu, G.: Depth saliency based on anisotropic center-surround difference. In: 2014 IEEE International Conference on Image Processing (ICIP), pp. 1115\u20131119. IEEE (2014)","DOI":"10.1109\/ICIP.2014.7025222"},{"key":"2_CR19","doi-asserted-by":"crossref","unstructured":"Larsson, G., Maire, M., Shakhnarovich, G.: Colorization as a proxy task for visual understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6874\u20136883 (2017)","DOI":"10.1109\/CVPR.2017.96"},{"key":"2_CR20","doi-asserted-by":"crossref","unstructured":"Li, N., Ye, J., Ji, Y., Ling, H., Yu, J.: Saliency detection on light field. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2806\u20132813 (2014)","DOI":"10.1109\/CVPR.2014.359"},{"key":"2_CR21","doi-asserted-by":"crossref","unstructured":"Li, T., Chang, H., Mishra, S., Zhang, H., Katabi, D., Krishnan, D.: MAGE: masked generative encoder to unify representation learning and image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2142\u20132152 (2023)","DOI":"10.1109\/CVPR52729.2023.00213"},{"key":"2_CR22","doi-asserted-by":"crossref","unstructured":"Liu, N., Zhang, N., Han, J.: Learning selective self-mutual attention for RGB-D saliency detection, pp. 13756\u201313765 (2020)","DOI":"10.1109\/CVPR42600.2020.01377"},{"issue":"7","key":"2_CR23","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.: SwinNet: swin transformer drives edge-aware RGB-D and RGB-T salient object detection. IEEE Trans. Circuits Syst. Video Technol. 32(7), 4486\u20134497 (2021)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"2_CR24","doi-asserted-by":"crossref","unstructured":"Liu, Z., Wang, Y., Tu, Z., Xiao, Y., Tang, B.: 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 (2021)","DOI":"10.1145\/3474085.3475601"},{"key":"2_CR25","doi-asserted-by":"crossref","unstructured":"Liu, Z., Mao, H., Wu, C.Y., Feichtenhofer, C., Darrell, T., Xie, S.: A convnet for the 2020s. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11976\u201311986 (2022)","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"2_CR26","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: International Conference on Learning Representations (2017). https:\/\/api.semanticscholar.org\/CorpusID:53592270"},{"key":"2_CR27","doi-asserted-by":"crossref","unstructured":"Niu, Y., Geng, Y., Li, X., Liu, F.: Leveraging stereopsis for saliency analysis. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 454\u2013461. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6247708"},{"key":"2_CR28","unstructured":"Pang, D.J.: PySODmetrics: a simple and efficient implementation of SOD metrics. https:\/\/github.com\/lartpang\/PySODMetrics. Accessed 23 Oct 2023"},{"key":"2_CR29","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.: CAVER: cross-modal view-mixed transformer for bi-modal salient object detection. IEEE Trans. Image Process. 32, 892\u2013904 (2023)","journal-title":"IEEE Trans. Image Process."},{"key":"2_CR30","doi-asserted-by":"crossref","unstructured":"Pathak, D., Krahenbuhl, P., Donahue, J., Darrell, T., Efros, A.A.: Context encoders: feature learning by inpainting. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2536\u20132544 (2016)","DOI":"10.1109\/CVPR.2016.278"},{"key":"2_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1007\/978-3-319-10578-9_7","volume-title":"Computer Vision \u2013 ECCV 2014","author":"H Peng","year":"2014","unstructured":"Peng, H., Li, B., Xiong, W., Hu, W., Ji, R.: RGBD salient object detection: a benchmark and algorithms. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8691, pp. 92\u2013109. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10578-9_7"},{"key":"2_CR32","doi-asserted-by":"crossref","unstructured":"Perazzi, F., Kr\u00e4henb\u00fchl, P., Pritch, Y., Hornung, A.: Saliency filters: contrast based filtering for salient region detection. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 733\u2013740. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6247743"},{"key":"2_CR33","doi-asserted-by":"crossref","unstructured":"Piao, Y., Ji, W., Li, J., Zhang, M., Lu, H.: Depth-induced multi-scale recurrent attention network for saliency detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7254\u20137263 (2019)","DOI":"10.1109\/ICCV.2019.00735"},{"key":"2_CR34","doi-asserted-by":"crossref","unstructured":"Piao, Y., Rong, Z., Zhang, M., Ren, W., Lu, H.: A2dele: adaptive and attentive depth distiller for efficient RGB-D salient object detection, pp. 9060\u20139069 (2020)","DOI":"10.1109\/CVPR42600.2020.00908"},{"key":"2_CR35","doi-asserted-by":"crossref","unstructured":"Ranftl, R., Bochkovskiy, A., Koltun, V.: Vision transformers for dense prediction. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 12179\u201312188 (2021)","DOI":"10.1109\/ICCV48922.2021.01196"},{"issue":"3","key":"2_CR36","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., et al.: Imagenet large scale visual recognition challenge. Int. J. Comput. Vision 115(3), 211\u2013252 (2015)","journal-title":"Int. J. Comput. Vision"},{"key":"2_CR37","first-page":"10078","volume":"35","author":"Z Tong","year":"2022","unstructured":"Tong, Z., Song, Y., Wang, J., Wang, L.: Videomae: masked autoencoders are data-efficient learners for self-supervised video pre-training. Adv. Neural. Inf. Process. Syst. 35, 10078\u201310093 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2_CR38","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30, 6000\u20136010 (2017)"},{"key":"2_CR39","doi-asserted-by":"crossref","unstructured":"Vincent, P., Larochelle, H., Bengio, Y., Manzagol, P.A.: Extracting and composing robust features with denoising autoencoders. In: Proceedings of the 25th International Conference on Machine Learning, pp. 1096\u20131103 (2008)","DOI":"10.1145\/1390156.1390294"},{"key":"2_CR40","doi-asserted-by":"publisher","unstructured":"Wang, Y., Zhang, Y.: Three-stage bidirectional interaction network for efficient RGB-D salient object detection. In: Wang, L., Gall, J., Chin, TJ., Sato, I., Chellappa, R. (eds.) ACCV 2022. LNCS, vol. 13845, pp. 215\u2013233. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-26348-4_13","DOI":"10.1007\/978-3-031-26348-4_13"},{"key":"2_CR41","doi-asserted-by":"publisher","first-page":"2160","DOI":"10.1109\/TIP.2023.3263111","volume":"32","author":"Z Wu","year":"2023","unstructured":"Wu, Z., Allibert, G., Meriaudeau, F., Ma, C., Demonceaux, C.: HiDAnet: RGB-D salient object detection via hierarchical depth awareness. IEEE Trans. Image Process. 32, 2160\u20132173 (2023)","journal-title":"IEEE Trans. Image Process."},{"key":"2_CR42","doi-asserted-by":"crossref","unstructured":"Wu, Z., Gobichettipalayam, S., Tamadazte, B., Allibert, G., Paudel, D.P., Demonceaux, C.: Robust RGB-D fusion for saliency detection. In: 2022 International Conference on 3D Vision (3DV), pp. 403\u2013413. IEEE (2022)","DOI":"10.1109\/3DV57658.2022.00052"},{"key":"2_CR43","doi-asserted-by":"crossref","unstructured":"Wu, Z., et al.: Source-free depth for object pop-out. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1032\u20131042 (2023)","DOI":"10.1109\/ICCV51070.2023.00101"},{"key":"2_CR44","doi-asserted-by":"crossref","unstructured":"Wu, Z., et al.: Object segmentation by mining cross-modal semantics. In: Proceedings of the 31st ACM International Conference on Multimedia (2023). https:\/\/api.semanticscholar.org\/CorpusID:258762372","DOI":"10.1145\/3581783.3611970"},{"key":"2_CR45","doi-asserted-by":"crossref","unstructured":"Zhang, J., et al.: UC-Net: uncertainty inspired RGB-D saliency detection via conditional variational autoencoders, pp. 8582\u20138591 (2020)","DOI":"10.1109\/CVPR42600.2020.00861"},{"key":"2_CR46","doi-asserted-by":"crossref","unstructured":"Zhang, J., et al.: RGB-D saliency detection via cascaded mutual information minimization (2021)","DOI":"10.1109\/ICCV48922.2021.00430"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-78447-7_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T01:03:13Z","timestamp":1733187793000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78447-7_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,3]]},"ISBN":["9783031784460","9783031784477"],"references-count":46,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78447-7_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,12,3]]},"assertion":[{"value":"3 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kolkata","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}