{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T05:52:36Z","timestamp":1742968356854,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":38,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819787944"},{"type":"electronic","value":"9789819787951"}],"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\/978-981-97-8795-1_38","type":"book-chapter","created":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T23:02:52Z","timestamp":1730588572000},"page":"563-577","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Depth-Aware Dual-Stream Interactive Transformer Network for Facial Expression Recognition"],"prefix":"10.1007","author":[{"given":"Yiben","family":"Jiang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiao","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Keren","family":"Fu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongyu","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,3]]},"reference":[{"key":"38_CR1","unstructured":"Bhat, S.F., Alhashim, I., Wonka, P.: Adabins: Depth estimation using adaptive bins. In: IEEE Conf. Comput. Vis. Pattern Recog (CVPR), pp. 4009\u20134018 (2021)"},{"key":"38_CR2","doi-asserted-by":"crossref","unstructured":"Cui, J., Zhang, H., Han, H., Shan, S., Chen, X.: Improving 2d face recognition via discriminative face depth estimation. In: 2018 International Conference on Biometrics (ICB), pp. 140\u2013147. IEEE (2018)","DOI":"10.1109\/ICB2018.2018.00031"},{"key":"38_CR3","doi-asserted-by":"crossref","unstructured":"Deng, J., Guo, J., Xue, N., Zafeiriou, S.: Arcface: Additive angular margin loss for deep face recognition. In: IEEE Conf. Comput. Vis. Pattern Recog (CVPR), pp. 4690\u20134699 (2019)","DOI":"10.1109\/CVPR.2019.00482"},{"key":"38_CR4","doi-asserted-by":"crossref","unstructured":"Ding, H., Zhou, P., Chellappa, R.: Occlusion-adaptive deep network for robust facial expression recognition. In: 2020 IEEE International Joint Conference on Biometrics (IJCB), pp.\u00a01\u20139. IEEE (2020)","DOI":"10.1109\/IJCB48548.2020.9304923"},{"key":"38_CR5","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., et\u00a0al.: An image is worth 16x16 words: Transformers for image recognition at scale. arXiv:2010.11929 (2020)"},{"key":"38_CR6","doi-asserted-by":"crossref","unstructured":"Goswami, G., Bharadwaj, S., Vatsa, M., Singh, R.: On rgb-d face recognition using kinect. In: 2013 IEEE Sixth International Conference on Biometrics: Theory, Applications and Systems (BTAS), pp.\u00a01\u20136. IEEE (2013)","DOI":"10.1109\/BTAS.2013.6712717"},{"key":"38_CR7","doi-asserted-by":"crossref","unstructured":"Guo, Y., Zhang, L., Hu, Y., He, X., Gao, J.: Ms-celeb-1m: A dataset and benchmark for large-scale face recognition. In: Eur. Conf. Comput. Vis (ECCV), pp. 87\u2013102. Springer (2016)","DOI":"10.1007\/978-3-319-46487-9_6"},{"issue":"21","key":"38_CR8","doi-asserted-by":"publisher","first-page":"8293","DOI":"10.3390\/s22218293","volume":"22","author":"Y He","year":"2022","unstructured":"He, Y., Fu, K., Cheng, P., Zhang, J.: Facial expression recognition with geometric scattering on 3d point clouds. Sensors 22(21), 8293 (2022)","journal-title":"Sensors"},{"key":"38_CR9","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)"},{"key":"38_CR10","unstructured":"Hu, W.: Improving 2d face recognition via fine-level facial depth generation and rgb-d complementary feature learning. arXiv preprint arXiv:2305.04426 (2023)"},{"issue":"19","key":"38_CR11","doi-asserted-by":"publisher","first-page":"4124","DOI":"10.3390\/s19194124","volume":"19","author":"Z Hu","year":"2019","unstructured":"Hu, Z., Gui, P., Feng, Z., Zhao, Q., Fu, K., et al.: Boosting depth-based face recognition from a quality perspective. Sensors 19(19), 4124 (2019)","journal-title":"Sensors"},{"key":"38_CR12","doi-asserted-by":"crossref","unstructured":"Lai, P., Yin, M., Yin, Y., Xie, M.: Swinfusion: Channel query-response based feature fusion for monocular depth estimation. In: Chinese Conference on Pattern Recognition and Computer Vision (PRCV), pp. 246\u2013258. Springer (2023)","DOI":"10.1007\/978-981-99-8432-9_20"},{"key":"38_CR13","doi-asserted-by":"crossref","unstructured":"Li, H., Niu, H., Zhu, Z., Zhao, F.: Cliper: A unified vision-language framework for in-the-wild facial expression recognition. arXiv preprint arXiv:2303.00193 (2023)","DOI":"10.1109\/ICME57554.2024.10687508"},{"issue":"3","key":"38_CR14","doi-asserted-by":"publisher","first-page":"1195","DOI":"10.1109\/TAFFC.2020.2981446","volume":"13","author":"S Li","year":"2020","unstructured":"Li, S., Deng, W.: Deep facial expression recognition: A survey. IEEE Trans. Affect. Comput. (TAC) 13(3), 1195\u20131215 (2020)","journal-title":"IEEE Trans. Affect. Comput. (TAC)"},{"key":"38_CR15","doi-asserted-by":"crossref","unstructured":"Li, S., Deng, W., Du, J.: Reliable crowdsourcing and deep locality-preserving learning for expression recognition in the wild. In: IEEE Conf. Comput. Vis. Pattern Recog (CVPR), pp. 2852\u20132861 (2017)","DOI":"10.1109\/CVPR.2017.277"},{"key":"38_CR16","unstructured":"Li, Y., Wang, M., Gong, M., et\u00a0al.: Fer-former: Multi-modal transformer for facial expression recognition. arXiv preprint arXiv:2303.12997 (2023)"},{"issue":"5","key":"38_CR17","doi-asserted-by":"publisher","first-page":"2439","DOI":"10.1109\/TIP.2018.2886767","volume":"28","author":"Y Li","year":"2018","unstructured":"Li, Y., Zeng, J., et al.: Occlusion aware facial expression recognition using cnn with attention mechanism. IEEE T. Image Process (TIP) 28(5), 2439\u20132450 (2018)","journal-title":"IEEE T. Image Process (TIP)"},{"key":"38_CR18","doi-asserted-by":"publisher","first-page":"4275","DOI":"10.1109\/TMM.2022.3197365","volume":"24","author":"L Lo","year":"2022","unstructured":"Lo, L., Xie, H., Shuai, H.H., et al.: Facial chirality: From visual self-reflection to robust facial feature learning. IEEE T. Multimedia (TMM) 24, 4275\u20134284 (2022)","journal-title":"IEEE T. Multimedia (TMM)"},{"key":"38_CR19","doi-asserted-by":"crossref","unstructured":"Lu, C., Jiang, Y., Fu, K., Zhao, Q., Yang, H.: Lstpnet: Long short-term perception network for dynamic facial expression recognition in the wild. Image Vis. Comput. (IVC). 142, 104915 (2024)","DOI":"10.1016\/j.imavis.2024.104915"},{"issue":"2","key":"38_CR20","doi-asserted-by":"publisher","first-page":"1236","DOI":"10.1109\/TAFFC.2021.3122146","volume":"14","author":"F Ma","year":"2021","unstructured":"Ma, F., Sun, B., Li, S.: Facial expression recognition with visual transformers and attentional selective fusion. IEEE Trans. Affect. Comput. (TAC) 14(2), 1236\u20131248 (2021)","journal-title":"IEEE Trans. Affect. Comput. (TAC)"},{"issue":"1","key":"38_CR21","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1109\/TAFFC.2017.2740923","volume":"10","author":"A Mollahosseini","year":"2017","unstructured":"Mollahosseini, A., Hasani, B., Mahoor, M.H.: Affectnet: A database for facial expression, valence, and arousal computing in the wild. IEEE Trans. Affect. Comput. (TAC) 10(1), 18\u201331 (2017)","journal-title":"IEEE Trans. Affect. Comput. (TAC)"},{"key":"38_CR22","unstructured":"Navneet, D.: Histograms of oriented gradients for human detection. In: IEEE Conf. Comput. Vis. Pattern Recog (CVPR), vol.\u00a02, pp. 886\u2013893 (2005)"},{"key":"38_CR23","doi-asserted-by":"crossref","unstructured":"Peng, S., Zhu, X., Yi, DI, Qian, C., Lei, Z.: Formulating facial mesh tracking as a differentiable optimization problem: a backpropagation-based solution. Vis. Intell. 2(22) (2024)","DOI":"10.1007\/s44267-024-00054-x"},{"key":"38_CR24","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., et\u00a0al.: Grad-cam: Visual explanations from deep networks via gradient-based localization. In: Int. Conf. Comput. Vis (ICCV), pp. 618\u2013626 (2017)","DOI":"10.1109\/ICCV.2017.74"},{"issue":"6","key":"38_CR25","doi-asserted-by":"publisher","first-page":"803","DOI":"10.1016\/j.imavis.2008.08.005","volume":"27","author":"C Shan","year":"2009","unstructured":"Shan, C., Gong, S., et al.: Facial expression recognition based on local binary patterns: A comprehensive study. Image Vision Comput (IVC). 27(6), 803\u2013816 (2009)","journal-title":"Image Vision Comput (IVC)."},{"key":"38_CR26","doi-asserted-by":"crossref","unstructured":"She, J., Hu, Y., Shi, H., et\u00a0al.: Dive into ambiguity: Latent distribution mining and pairwise uncertainty estimation for facial expression recognition. In: IEEE Conf. Comput. Vis. Pattern Recog (CVPR), pp. 6248\u20136257 (2021)","DOI":"10.1109\/CVPR46437.2021.00618"},{"key":"38_CR27","doi-asserted-by":"publisher","first-page":"4057","DOI":"10.1109\/TIP.2019.2956143","volume":"29","author":"K Wang","year":"2020","unstructured":"Wang, K., Peng, X., Yang, J., Meng, D., Qiao, Y.: Region attention networks for pose and occlusion robust facial expression recognition. IEEE T. Image Process (TIP) 29, 4057\u20134069 (2020)","journal-title":"IEEE T. Image Process (TIP)"},{"key":"38_CR28","unstructured":"Wang, Q., Zhang, P., Xiong, H., Zhao, J.: Face. evolve: A high-performance face recognition library. arXiv preprint arXiv:2107.08621 (2021)"},{"key":"38_CR29","doi-asserted-by":"crossref","unstructured":"Wu, S.Y., Chiu, C.T., Hsu, Y.C.: Pose aware rgbd-based face recognition system with hierarchical bilinear pooling. In: 2023 21st IEEE Interregional NEWCAS Conference (NEWCAS), pp.\u00a01\u20135. IEEE (2023)","DOI":"10.1109\/NEWCAS57931.2023.10198097"},{"key":"38_CR30","doi-asserted-by":"crossref","unstructured":"Wu, Y., Jia, K., Sun, Z.: Facial expression recognition based on multi-scale feature fusion convolutional neural network and attention mechanism. In: Pattern Recognition and Computer Vision: 4th Chinese Conference, PRCV 2021, Beijing, China, October 29\u2013November 1, 2021, Proceedings, Part II 4, pp. 324\u2013335. Springer (2021)","DOI":"10.1007\/978-3-030-88007-1_27"},{"key":"38_CR31","doi-asserted-by":"crossref","unstructured":"Xue, F., Wang, Q., Guo, G.: Transfer: Learning relation-aware facial expression representations with transformers. In: Int. Conf. Comput. Vis (ICCV), pp. 3601\u20133610 (2021)","DOI":"10.1109\/ICCV48922.2021.00358"},{"key":"38_CR32","doi-asserted-by":"crossref","unstructured":"Xue, F., Wang, Q., Tan, Z., et\u00a0al.: Vision transformer with attentive pooling for robust facial expression recognition. IEEE Trans. Affect. Comput. (TAC) (2022)","DOI":"10.1109\/TAFFC.2022.3226473"},{"key":"38_CR33","doi-asserted-by":"crossref","unstructured":"Yan, P., Liu, X., Zhang, P., Lu, H.: Learning convolutional multi-level transformers for image-based person re-identification. Vis. Intell. 1(24) (2023)","DOI":"10.1007\/s44267-023-00025-8"},{"key":"38_CR34","doi-asserted-by":"crossref","unstructured":"Zeng, D., Lin, Z., et\u00a0al.: Face2exp: Combating data biases for facial expression recognition. In: IEEE Conf. Comput. Vis. Pattern Recog, pp. 20291\u201320300 (2022)","DOI":"10.1109\/CVPR52688.2022.01965"},{"key":"38_CR35","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1016\/j.neucom.2020.04.025","volume":"406","author":"J Zhang","year":"2020","unstructured":"Zhang, J., Gao, K., Fu, K., Cheng, P.: Deep 3d facial landmark localization on position maps. Neurocomputing 406, 89\u201398 (2020)","journal-title":"Neurocomputing"},{"key":"38_CR36","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Wang, C., Ling, X., et\u00a0al.: Learn from all: Erasing attention consistency for noisy label facial expression recognition. In: Eur. Conf. Comput. Vis (ECCV), pp. 418\u2013434. Springer (2022)","DOI":"10.1007\/978-3-031-19809-0_24"},{"key":"38_CR37","doi-asserted-by":"crossref","unstructured":"Zheng, C., Mendieta, M., Chen, C.: Poster: A pyramid cross-fusion transformer network for facial expression recognition. In: Int. Conf. Comput. Vis. Worksh (ICCVW), pp. 3146\u20133155 (2023)","DOI":"10.1109\/ICCVW60793.2023.00339"},{"key":"38_CR38","unstructured":"Zhou, G., Xie, Y., Tian, W.: Multi loss-based feature fusion and top two voting ensemble decision strategy for facial expression recognition in the wild. arXiv preprint arXiv:2311.03478 (2023)"}],"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\/978-981-97-8795-1_38","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T23:07:07Z","timestamp":1730588827000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-8795-1_38"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,3]]},"ISBN":["9789819787944","9789819787951"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-8795-1_38","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"}}]}}