{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T23:38:48Z","timestamp":1743032328457,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":39,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819785070"},{"type":"electronic","value":"9789819785087"}],"license":[{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"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\/978-981-97-8508-7_15","type":"book-chapter","created":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T06:04:25Z","timestamp":1730527465000},"page":"211-225","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Disparity Refinement Based on Cross-Modal Feature Fusion and Global Hourglass Aggregation for Robust Stereo Matching"],"prefix":"10.1007","author":[{"given":"Gang","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinlong","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yinghui","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,3]]},"reference":[{"key":"15_CR1","doi-asserted-by":"crossref","unstructured":"Mayer, N., et al.: A large dataset to train convolutional networks for disparity, optical flow, and scene flow estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4040\u20134048 (2016)","DOI":"10.1109\/CVPR.2016.438"},{"key":"15_CR2","doi-asserted-by":"crossref","unstructured":"Chang, J.R., Chen, Y.S.: Pyramid stereo matching network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5410\u20135418 (2018)","DOI":"10.1109\/CVPR.2018.00567"},{"key":"15_CR3","doi-asserted-by":"crossref","unstructured":"Guo, X., Yang, K., Yang, W., Wang, X., Li, H.: Group-wise correlation stereo network. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3273\u20133282 (2019)","DOI":"10.1109\/CVPR.2019.00339"},{"key":"15_CR4","doi-asserted-by":"crossref","unstructured":"Zhang, F., Prisacariu, V., Yang, R., Torr, P.H.: Ga-net: guided aggregation net for end-to-end stereo matching. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 185\u2013194 (2019)","DOI":"10.1109\/CVPR.2019.00027"},{"key":"15_CR5","doi-asserted-by":"crossref","unstructured":"Liu, B., Yu, H., Long, Y.: Local similarity pattern and cost self-reassembling for deep stereo matching networks. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 1647\u20131655 (2022)","DOI":"10.1609\/aaai.v36i2.20056"},{"issue":"1","key":"15_CR6","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1007\/s11263-023-01872-0","volume":"132","author":"J Cheng","year":"2024","unstructured":"Cheng, J., Xu, G., Guo, P., Yang, X.: Coatrsnet: fully exploiting convolution and attention for stereo matching by region separation. Int. J. Comput. Vision 132(1), 56\u201373 (2024)","journal-title":"Int. J. Comput. Vision"},{"key":"15_CR7","doi-asserted-by":"crossref","unstructured":"Song, X., Yang, G., Zhu, X., Zhou, H., Wang, Z., Shi, J.: Adastereo: a simple and efficient approach for adaptive stereo matching. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10328\u201310337 (2021)","DOI":"10.1109\/CVPR46437.2021.01019"},{"key":"15_CR8","doi-asserted-by":"crossref","unstructured":"Teed, Z., Deng, J.: Raft: Recurrent all-pairs field transforms for optical flow. In: Proceedings of the European Conference on Computer Vision, pp. 402\u2013419 (2020)","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"15_CR9","doi-asserted-by":"crossref","unstructured":"Lipson, L., Teed, Z., Deng, J.: Raft-stereo: Multilevel recurrent field transforms for stereo matching. In: Proceedings of the International Conference on 3D Vision, pp. 218\u2013227 (2021)","DOI":"10.1109\/3DV53792.2021.00032"},{"key":"15_CR10","doi-asserted-by":"crossref","unstructured":"Li, J., et al.: Practical stereo matching via cascaded recurrent network with adaptive correlation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16263\u201316272 (2022)","DOI":"10.1109\/CVPR52688.2022.01578"},{"key":"15_CR11","doi-asserted-by":"crossref","unstructured":"Liu, Z., Li, Y., Okutomi, M.: Global occlusion-aware transformer for robust stereo matching. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 3535\u20133544 (2024)","DOI":"10.1109\/WACV57701.2024.00350"},{"key":"15_CR12","doi-asserted-by":"crossref","unstructured":"Zhao, H., Zhou, H., Zhang, Y., Zhao, Y., Yang, Y., Ouyang, T.: Eai-stereo: Error aware iterative network for stereo matching. In: Proceedings of the Asian Conference on Computer Vision, pp. 315\u2013332 (2022)","DOI":"10.1007\/978-3-031-26319-4_1"},{"key":"15_CR13","doi-asserted-by":"crossref","unstructured":"Cho, K., et al.: Learning phrase representations using rnn encoder-decoder for statistical machine translation (2014). arXiv:1406.1078","DOI":"10.3115\/v1\/D14-1179"},{"issue":"2","key":"15_CR14","doi-asserted-by":"publisher","first-page":"328","DOI":"10.1109\/TPAMI.2007.1166","volume":"30","author":"H Hirschmuller","year":"2007","unstructured":"Hirschmuller, H.: Stereo processing by semiglobal matching and mutual information. IEEE Trans. Pattern Anal. Mach. Intell. 30(2), 328\u2013341 (2007)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"15_CR15","doi-asserted-by":"crossref","unstructured":"Xu, G., Wang, X., Ding, X., Yang, X.: Iterative geometry encoding volume for stereo matching. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21919\u201321928 (2023)","DOI":"10.1109\/CVPR52729.2023.02099"},{"key":"15_CR16","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"15_CR17","doi-asserted-by":"crossref","unstructured":"Tu, D., Min, X., Duan, H., Guo, G., Zhai, G., Shen, W.: End-to-end human-gaze-target detection with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2192\u20132200 (2022)","DOI":"10.1109\/CVPR52688.2022.00224"},{"key":"15_CR18","doi-asserted-by":"crossref","unstructured":"Chen, X., Kang, B., Wang, D., Li, D., Lu, H.: Efficient visual tracking via hierarchical cross-attention transformer. In: Proceedings of the European Conference on Computer Vision, pp. 461\u2013477 (2022)","DOI":"10.1007\/978-3-031-25085-9_26"},{"key":"15_CR19","doi-asserted-by":"crossref","unstructured":"Gu, J., et al.: Multi-scale high-resolution vision transformer for semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12094\u201312103 (2022)","DOI":"10.1109\/CVPR52688.2022.01178"},{"key":"15_CR20","first-page":"14541","volume":"35","author":"Z Pan","year":"2022","unstructured":"Pan, Z., Cai, J., Zhuang, B.: Fast vision transformers with hilo attention. Adv. Neural. Inf. Process. Syst. 35, 14541\u201314554 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"15_CR21","unstructured":"Shen, Z., Zhang, M., Zhao, H., Yi, S., Li, H.: Efficient attention: attention with linear complexities. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 3531\u20133539 (2021)"},{"key":"15_CR22","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? The kitti vision benchmark suite. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3354\u20133361 (2012)","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"15_CR23","doi-asserted-by":"crossref","unstructured":"Menze, M., Geiger, A.: Object scene flow for autonomous vehicles. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3061\u20133070 (2015)","DOI":"10.1109\/CVPR.2015.7298925"},{"key":"15_CR24","doi-asserted-by":"crossref","unstructured":"Scharstein, D., et al.: High-resolution stereo datasets with subpixel-accurate ground truth. In: Proceedings of the German Conference on Pattern Recognition, pp. 31\u201342 (2014)","DOI":"10.1007\/978-3-319-11752-2_3"},{"key":"15_CR25","doi-asserted-by":"crossref","unstructured":"Schops, T., et al.: A multi-view stereo benchmark with high-resolution images and multi-camera videos. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3260\u20133269 (2017)","DOI":"10.1109\/CVPR.2017.272"},{"key":"15_CR26","doi-asserted-by":"crossref","unstructured":"Zhao, H., Zhou, H., Zhang, Y., Chen, J., Yang, Y., Zhao, Y.: High-frequency stereo matching network. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1327\u20131336 (2023)","DOI":"10.1109\/CVPR52729.2023.00134"},{"key":"15_CR27","doi-asserted-by":"crossref","unstructured":"Shen, Z., Dai, Y., Rao, Z.: Cfnet: cascade and fused cost volume for robust stereo matching. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13906\u201313915 (2021)","DOI":"10.1109\/CVPR46437.2021.01369"},{"key":"15_CR28","doi-asserted-by":"publisher","first-page":"910","DOI":"10.1007\/s11263-019-01287-w","volume":"128","author":"X Song","year":"2020","unstructured":"Song, X., Zhao, X., Fang, L., Hu, H., Yu, Y.: Edgestereo: an effective multi-task learning network for stereo matching and edge detection. Int. J. Comput. Vision 128, 910\u2013930 (2020)","journal-title":"Int. J. Comput. Vision"},{"key":"15_CR29","doi-asserted-by":"crossref","unstructured":"Xu, G., Cheng, J., Guo, P., Yang, X.: Attention concatenation volume for accurate and efficient stereo matching. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12981\u201312990 (2022)","DOI":"10.1109\/CVPR52688.2022.01264"},{"key":"15_CR30","doi-asserted-by":"crossref","unstructured":"Liang, Z., Li, C.: Any-stereo: arbitrary scale disparity estimation for iterative stereo matching. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 3333\u20133341 (2024)","DOI":"10.1609\/aaai.v38i4.28119"},{"key":"15_CR31","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Chen, Y., Bai, X., Yu, S., Yu, K., Li, Z., Yang, K.: Adaptive unimodal cost volume filtering for deep stereo matching. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 12926\u201312934 (2020)","DOI":"10.1609\/aaai.v34i07.6991"},{"key":"15_CR32","doi-asserted-by":"crossref","unstructured":"Xu, H., et al.: Unifying flow, stereo and depth estimation. IEEE Trans. Pattern Anal. Mach. Intell. 45(11), 13941\u201313958 (2023)","DOI":"10.1109\/TPAMI.2023.3298645"},{"key":"15_CR33","doi-asserted-by":"crossref","unstructured":"Zeng, J., Yao, C., Yu, L., Wu, Y., Jia, Y.: Parameterized cost volume for stereo matching. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 18347\u201318357 (2023)","DOI":"10.1109\/ICCV51070.2023.01682"},{"issue":"12","key":"15_CR34","doi-asserted-by":"publisher","first-page":"14301","DOI":"10.1109\/TPAMI.2023.3300976","volume":"45","author":"Z Shen","year":"2023","unstructured":"Shen, Z., Song, X., Dai, Y., Zhou, D., Rao, Z., Zhang, L.: Digging into uncertainty-based pseudo-label for robust stereo matching. IEEE Trans. Pattern Anal. Mach. Intell. 45(12), 14301\u201314320 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"15_CR35","doi-asserted-by":"crossref","unstructured":"Bleyer, M., Rhemann, C., Rother, C.: Patchmatch stereo-stereo matching with slanted support windows. In: Proceedings of the British Machine Vision Conference, pp. 1\u201311 (2011)","DOI":"10.5244\/C.25.14"},{"issue":"2","key":"15_CR36","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1109\/TPAMI.2012.156","volume":"35","author":"A Hosni","year":"2012","unstructured":"Hosni, A., Rhemann, C., Bleyer, M., Rother, C., Gelautz, M.: Fast cost-volume filtering for visual correspondence and beyond. IEEE Trans. Pattern Anal. Mach. Intell. 35(2), 504\u2013511 (2012)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"15_CR37","doi-asserted-by":"crossref","unstructured":"Li, Z., et al.: Revisiting stereo depth estimation from a sequence-to-sequence perspective with transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6197\u20136206 (2021)","DOI":"10.1109\/ICCV48922.2021.00614"},{"key":"15_CR38","doi-asserted-by":"crossref","unstructured":"Zhang, J., et al.: Revisiting domain generalized stereo matching networks from a feature consistency perspective. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13001\u201313011 (2022)","DOI":"10.1109\/CVPR52688.2022.01266"},{"key":"15_CR39","doi-asserted-by":"crossref","unstructured":"Rao, Z., et al.: Masked representation learning for domain generalized stereo matching. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5435\u20135444 (2023)","DOI":"10.1109\/CVPR52729.2023.00526"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-8508-7_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T06:14:51Z","timestamp":1730528091000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-8508-7_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,3]]},"ISBN":["9789819785070","9789819785087"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-8508-7_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,3]]},"assertion":[{"value":"3 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Urumqi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"18 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2024.prcv.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}