{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T02:55:50Z","timestamp":1773888950598,"version":"3.50.1"},"publisher-location":"Cham","reference-count":57,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726484","type":"print"},{"value":"9783031726491","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T00:00:00Z","timestamp":1727654400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T00:00:00Z","timestamp":1727654400000},"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\/978-3-031-72649-1_20","type":"book-chapter","created":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T07:01:50Z","timestamp":1727593310000},"page":"350-366","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["PoseSOR: Human Pose Can Guide Our Attention"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0825-8658","authenticated-orcid":false,"given":"Huankang","family":"Guan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8957-8129","authenticated-orcid":false,"given":"Rynson W. H.","family":"Lau","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,9,30]]},"reference":[{"key":"20_CR1","doi-asserted-by":"crossref","unstructured":"Aberman, K., et al.: Deep saliency prior for reducing visual distraction. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01923"},{"key":"20_CR2","doi-asserted-by":"crossref","unstructured":"Achanta, R., Hemami, S.S., Estrada, F.J., S\u00fcsstrunk, S.: Frequency-tuned salient region detection. In: CVPR (2009)","DOI":"10.1109\/CVPR.2009.5206596"},{"key":"20_CR3","doi-asserted-by":"publisher","first-page":"112","DOI":"10.1016\/j.cognition.2015.04.014","volume":"141","author":"L Bardi","year":"2015","unstructured":"Bardi, L., Di Giorgio, E., Lunghi, M., Troje, N.F., Simion, F.: Walking direction triggers visuo-spatial orienting in 6-month-old infants and adults: an eye tracking study. Cognition 141, 112\u2013120 (2015)","journal-title":"Cognition"},{"key":"20_CR4","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"20_CR5","doi-asserted-by":"crossref","unstructured":"Cheng, B., Misra, I., Schwing, A.G., Kirillov, A., Girdhar, R.: Masked-attention mask transformer for universal image segmentation. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"20_CR6","doi-asserted-by":"crossref","unstructured":"Cheng, M., Warrell, J., Lin, W., Zheng, S., Vineet, V., Crook, N.T.: Efficient salient region detection with soft image abstraction. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.193"},{"issue":"1","key":"20_CR7","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1146\/annurev.ne.18.030195.001205","volume":"18","author":"R Desimone","year":"1995","unstructured":"Desimone, R., Duncan, J.: Neural mechanisms of selective visual attention. Annu. Rev. Neurosci. 18(1), 193\u2013222 (1995)","journal-title":"Annu. Rev. Neurosci."},{"issue":"5","key":"20_CR8","doi-asserted-by":"publisher","first-page":"509","DOI":"10.1080\/135062899394920","volume":"6","author":"J Driver IV","year":"1999","unstructured":"Driver, J., IV., Davis, G., Ricciardelli, P., Kidd, P., Maxwell, E., Baron-Cohen, S.: Gaze perception triggers reflexive visuospatial orienting. Vis. Cogn. 6(5), 509\u2013540 (1999)","journal-title":"Vis. Cogn."},{"issue":"5","key":"20_CR9","doi-asserted-by":"publisher","first-page":"3366","DOI":"10.1109\/TGRS.2019.2953936","volume":"58","author":"L Du","year":"2019","unstructured":"Du, L., Li, L., Wei, D., Mao, J.: Saliency-guided single shot multibox detector for target detection in SAR images. IEEE Trans. Geosci. Remote Sens. 58(5), 3366\u20133376 (2019)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"20_CR10","doi-asserted-by":"crossref","unstructured":"Fan, L., Wang, W., Huang, S., Tang, X., Zhu, S.C.: Understanding human gaze communication by spatio-temporal graph reasoning. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00582"},{"key":"20_CR11","doi-asserted-by":"crossref","unstructured":"Fan, R., Cheng, M.M., Hou, Q., Mu, T.J., Wang, J., Hu, S.M.: S4Net: single stage salient-instance segmentation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00626"},{"key":"20_CR12","doi-asserted-by":"crossref","unstructured":"Fang, H., et al.: Salient object ranking with position-preserved attention. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01602"},{"key":"20_CR13","doi-asserted-by":"crossref","unstructured":"Fang, Y., et al.: Instances as queries. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00683"},{"key":"20_CR14","doi-asserted-by":"publisher","first-page":"1437","DOI":"10.3758\/APP.72.6.1437","volume":"72","author":"WM Gervais","year":"2010","unstructured":"Gervais, W.M., Reed, C.L., Beall, P.M., Roberts, R.J.: Implied body action directs spatial attention. Attention, Perception, Psychophysics 72, 1437\u20131443 (2010)","journal-title":"Attention, Perception, Psychophysics"},{"issue":"3","key":"20_CR15","first-page":"1941","volume":"38","author":"H Guan","year":"2024","unstructured":"Guan, H., Lau, R.W.: SeqRank: sequential ranking of salient objects. Proc. AAAI Conf. Artif. Intell. 38(3), 1941\u20131949 (2024)","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"20_CR16","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"20_CR17","doi-asserted-by":"crossref","unstructured":"He, S., Jiao, J., Zhang, X., Han, G., Lau, R.W.: Delving into salient object subitizing and detection. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.120"},{"key":"20_CR18","doi-asserted-by":"crossref","unstructured":"Islam, M.A., Kalash, M., Bruce, N.D.: Revisiting salient object detection: simultaneous detection, ranking, and subitizing of multiple salient objects. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00746"},{"issue":"10\u201312","key":"20_CR19","doi-asserted-by":"publisher","first-page":"1489","DOI":"10.1016\/S0042-6989(99)00163-7","volume":"40","author":"L Itti","year":"2000","unstructured":"Itti, L., Koch, C.: A saliency-based search mechanism for overt and covert shifts of visual attention. Vision Res. 40(10\u201312), 1489\u20131506 (2000)","journal-title":"Vision Res."},{"key":"20_CR20","doi-asserted-by":"crossref","unstructured":"Jiang, B., Zhang, L., Lu, H., Yang, C., Yang, M.: Saliency detection via absorbing Markov chain. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.209"},{"issue":"1","key":"20_CR21","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1146\/annurev.ps.37.020186.000355","volume":"37","author":"WA Johnston","year":"1986","unstructured":"Johnston, W.A., Dark, V.J.: Selective attention. Annu. Rev. Psychol. 37(1), 43\u201375 (1986)","journal-title":"Annu. Rev. Psychol."},{"issue":"4","key":"20_CR22","first-page":"219","volume":"4","author":"C Koch","year":"1985","unstructured":"Koch, C., Ullman, S.: Shifts in selective visual attention: towards the underlying neural circuitry. Hum. Neurobiol. 4(4), 219\u2013227 (1985)","journal-title":"Hum. Neurobiol."},{"key":"20_CR23","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, vol. 25 (2012)"},{"issue":"2","key":"20_CR24","doi-asserted-by":"publisher","first-page":"747","DOI":"10.1037\/0096-1523.26.2.747","volume":"26","author":"SR Langton","year":"2000","unstructured":"Langton, S.R., Bruce, V.: You must see the point: automatic processing of cues to the direction of social attention. J. Exp. Psychol. Hum. Percept. Perform. 26(2), 747 (2000)","journal-title":"J. Exp. Psychol. Hum. Percept. Perform."},{"key":"20_CR25","doi-asserted-by":"crossref","unstructured":"Li, G., Xie, Y., Lin, L., Yu, Y.: Instance-level salient object segmentation. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.34"},{"key":"20_CR26","doi-asserted-by":"crossref","unstructured":"Li, H., et al.: Boosting low-data instance segmentation by unsupervised pre-training with saliency prompt. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01486"},{"key":"20_CR27","doi-asserted-by":"crossref","unstructured":"Li, X., Lu, H., Zhang, L., Ruan, X., Yang, M.: Saliency detection via dense and sparse reconstruction. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.370"},{"key":"20_CR28","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"20_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"issue":"7","key":"20_CR30","doi-asserted-by":"publisher","first-page":"3264","DOI":"10.1109\/TIP.2018.2817047","volume":"27","author":"N Liu","year":"2018","unstructured":"Liu, N., Han, J.: A deep spatial contextual long-term recurrent convolutional network for saliency detection. IEEE Trans. Image Process. 27(7), 3264\u20133274 (2018)","journal-title":"IEEE Trans. Image Process."},{"issue":"11","key":"20_CR31","first-page":"8321","volume":"44","author":"N Liu","year":"2021","unstructured":"Liu, N., Li, L., Zhao, W., Han, J., Shao, L.: Instance-level relative saliency ranking with graph reasoning. IEEE Trans. Pattern Anal. Mach. Intell. 44(11), 8321\u20138337 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"20_CR32","doi-asserted-by":"crossref","unstructured":"Liu, N., Zhang, N., Wan, K., Shao, L., Han, J.: Visual saliency transformer. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00468"},{"key":"20_CR33","doi-asserted-by":"publisher","first-page":"5862","DOI":"10.1109\/TIP.2021.3088282","volume":"30","author":"N Liu","year":"2021","unstructured":"Liu, N., Zhao, W., Shao, L., Han, J.: SCG: saliency and contour guided salient instance segmentation. IEEE Trans. Image Process. 30, 5862\u20135874 (2021)","journal-title":"IEEE Trans. Image Process."},{"key":"20_CR34","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"20_CR35","doi-asserted-by":"crossref","unstructured":"Mao, W., Tian, Z., Wang, X., Shen, C.: FCPose: fully convolutional multi-person pose estimation with dynamic instance-aware convolutions. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00892"},{"key":"20_CR36","doi-asserted-by":"crossref","unstructured":"Miangoleh, S.M.H., Bylinskii, Z., Kee, E., Shechtman, E., Aksoy, Y.: Realistic saliency guided image enhancement. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00026"},{"key":"20_CR37","doi-asserted-by":"crossref","unstructured":"Milletari, F., Navab, N., Ahmadi, S.A.: V-Net: fully convolutional neural networks for volumetric medical image segmentation. In: 2016 Fourth International Conference on 3D Vision (3DV), pp. 565\u2013571. IEEE (2016)","DOI":"10.1109\/3DV.2016.79"},{"key":"20_CR38","doi-asserted-by":"crossref","unstructured":"Neisser, U.: Cognitive Psychology: Classic Edition. Psychology Press (2014)","DOI":"10.4324\/9781315736174"},{"key":"20_CR39","doi-asserted-by":"publisher","first-page":"1964","DOI":"10.1109\/TMM.2022.3141891","volume":"25","author":"J Pei","year":"2022","unstructured":"Pei, J., Cheng, T., Tang, H., Chen, C.: Transformer-based efficient salient instance segmentation networks with orientative query. IEEE Trans. Multimedia 25, 1964\u20131978 (2022)","journal-title":"IEEE Trans. Multimedia"},{"key":"20_CR40","doi-asserted-by":"crossref","unstructured":"Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., Savarese, S.: Generalized intersection over union: a metric and a loss for bounding box regression (2019)","DOI":"10.1109\/CVPR.2019.00075"},{"key":"20_CR41","doi-asserted-by":"crossref","unstructured":"Shi, D., Wei, X., Li, L., Ren, Y., Tan, W.: End-to-end multi-person pose estimation with transformers. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01079"},{"key":"20_CR42","doi-asserted-by":"crossref","unstructured":"Shi, D., Wei, X., Yu, X., Tan, W., Ren, Y., Pu, S.: InsPose: instance-aware networks for single-stage multi-person pose estimation. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 3079\u20133087 (2021)","DOI":"10.1145\/3474085.3475447"},{"issue":"3","key":"20_CR43","doi-asserted-by":"publisher","first-page":"348","DOI":"10.1016\/j.cognition.2010.09.001","volume":"117","author":"J Shi","year":"2010","unstructured":"Shi, J., Weng, X., He, S., Jiang, Y.: Biological motion cues trigger reflexive attentional orienting. Cognition 117(3), 348\u2013354 (2010)","journal-title":"Cognition"},{"key":"20_CR44","doi-asserted-by":"crossref","unstructured":"Siris, A., Jiao, J., Tam, G.K., Xie, X., Lau, R.W.: Inferring attention shift ranks of objects for image saliency. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01215"},{"key":"20_CR45","doi-asserted-by":"crossref","unstructured":"Siris, A., Jiao, J., Tam, G.K., Xie, X., Lau, R.W.: Scene context-aware salient object detection. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00412"},{"key":"20_CR46","doi-asserted-by":"crossref","unstructured":"Sun, C., Xu, Y., Pei, J., Fang, H., Tang, H.: Partitioned saliency ranking with dense pyramid transformers. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 1874\u20131883 (2023)","DOI":"10.1145\/3581783.3611812"},{"key":"20_CR47","doi-asserted-by":"crossref","unstructured":"Tian, X., Xu, K., Yang, X., Du, L., Yin, B., Lau, R.W.: Bi-directional object-context prioritization learning for saliency ranking. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00579"},{"key":"20_CR48","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"20_CR49","doi-asserted-by":"crossref","unstructured":"Wang, Y., Wang, R., Fan, X., Wang, T., He, X.: Pixels, regions, and objects: multiple enhancement for salient object detection. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00967"},{"key":"20_CR50","doi-asserted-by":"crossref","unstructured":"Wei, J., Wang, S., Wu, Z., Su, C., Huang, Q., Tian, Q.: Label decoupling framework for salient object detection. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01304"},{"key":"20_CR51","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1007\/978-3-642-33712-3_3","volume-title":"Computer Vision \u2013 ECCV 2012","author":"Y Wei","year":"2012","unstructured":"Wei, Y., Wen, F., Zhu, W., Sun, J.: Geodesic saliency using background priors. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7574, pp. 29\u201342. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33712-3_3"},{"key":"20_CR52","doi-asserted-by":"publisher","first-page":"3125","DOI":"10.1109\/TIP.2022.3164550","volume":"31","author":"YH Wu","year":"2022","unstructured":"Wu, Y.H., Liu, Y., Zhang, L., Cheng, M.M., Ren, B.: EDN: salient object detection via extremely-downsampled network. IEEE Trans. Image Process. 31, 3125\u20133136 (2022)","journal-title":"IEEE Trans. Image Process."},{"key":"20_CR53","doi-asserted-by":"publisher","first-page":"3897","DOI":"10.1109\/TIP.2021.3065822","volume":"30","author":"YH Wu","year":"2021","unstructured":"Wu, Y.H., Liu, Y., Zhang, L., Gao, W., Cheng, M.M.: Regularized densely-connected pyramid network for salient instance segmentation. IEEE Trans. Image Process. 30, 3897\u20133907 (2021)","journal-title":"IEEE Trans. Image Process."},{"key":"20_CR54","doi-asserted-by":"crossref","unstructured":"Yan, Q., Xu, L., Shi, J., Jia, J.: Hierarchical saliency detection. In: CVPR (2013)","DOI":"10.1109\/CVPR.2013.153"},{"key":"20_CR55","doi-asserted-by":"publisher","first-page":"3534","DOI":"10.1109\/TIP.2019.2962688","volume":"29","author":"L Zhang","year":"2020","unstructured":"Zhang, L., Wu, J., Wang, T., Borji, A., Wei, G., Lu, H.: A multistage refinement network for salient object detection. IEEE Trans. Image Process. 29, 3534\u20133545 (2020)","journal-title":"IEEE Trans. Image Process."},{"key":"20_CR56","doi-asserted-by":"crossref","unstructured":"Zhang, L., Zhang, J., Lin, Z., Lu, H., He, Y.: CapSal: leveraging captioning to boost semantics for salient object detection. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00618"},{"key":"20_CR57","doi-asserted-by":"crossref","unstructured":"Zhu, W., Liang, S., Wei, Y., Sun, J.: Saliency optimization from robust background detection. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.360"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72649-1_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T07:11:13Z","timestamp":1727593873000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72649-1_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,30]]},"ISBN":["9783031726484","9783031726491"],"references-count":57,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72649-1_20","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9,30]]},"assertion":[{"value":"30 September 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","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":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}