{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T16:48:56Z","timestamp":1761929336710,"version":"build-2065373602"},"publisher-location":"Singapore","reference-count":50,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819537280","type":"print"},{"value":"9789819537297","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"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":[[2026]]},"DOI":"10.1007\/978-981-95-3729-7_2","type":"book-chapter","created":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T16:43:40Z","timestamp":1761929020000},"page":"15-26","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["CDHQA: A Quality Assessment Database for\u00a0Conversational Digital Human"],"prefix":"10.1007","author":[{"given":"Yingjie","family":"Zhou","sequence":"first","affiliation":[]},{"given":"Jing","family":"Wan","sequence":"additional","affiliation":[]},{"given":"Sitong","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Yinghan","family":"Xia","sequence":"additional","affiliation":[]},{"given":"Zhixiang","family":"Lu","sequence":"additional","affiliation":[]},{"given":"Farong","family":"Wen","sequence":"additional","affiliation":[]},{"given":"Zicheng","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Yu","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Yu","family":"Zhou","sequence":"additional","affiliation":[]},{"given":"Xiaohong","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Xiongkuo","family":"Min","sequence":"additional","affiliation":[]},{"given":"Jiezhang","family":"Cao","sequence":"additional","affiliation":[]},{"given":"Guangtao","family":"Zhai","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,11,1]]},"reference":[{"key":"2_CR1","unstructured":"BT, R.I.R.: Methodology for the subjective assessment of the quality of television pictures. Int. Telecommun. Union (2002)"},{"key":"2_CR2","doi-asserted-by":"publisher","DOI":"10.1016\/j.displa.2023.102540","volume":"80","author":"S Chen","year":"2023","unstructured":"Chen, S., Zhang, Z., Zhou, Y., Sun, W., Min, X.: A no-reference quality assessment metric for dynamic 3D digital human. Displays 80, 102540 (2023)","journal-title":"Displays"},{"key":"2_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1007\/978-3-319-54427-4_19","volume-title":"Computer Vision \u2013 ACCV 2016 Workshops","author":"JS Chung","year":"2017","unstructured":"Chung, J.S., Zisserman, A.: Out of time: automated lip sync in the wild. In: Chen, C.-S., Lu, J., Ma, K.-K. (eds.) ACCV 2016. LNCS, vol. 10117, pp. 251\u2013263. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-54427-4_19"},{"key":"2_CR4","first-page":"1","volume":"29","author":"J Guan","year":"2015","unstructured":"Guan, J., Zhang, W., Gu, J., Ren, H.: No-reference blur assessment based on edge modeling. JVCIR 29, 1\u20137 (2015)","journal-title":"JVCIR"},{"key":"2_CR5","unstructured":"Guo, D., et\u00a0al.: DeepSeek-R1: incentivizing reasoning capability in LLMs via reinforcement learning. arXiv preprint arXiv:2501.12948 (2025)"},{"key":"2_CR6","doi-asserted-by":"crossref","unstructured":"Guo, S., Guo, J., Wang, H., Wang, H., Huang, X., Zhang, L.: An efficient ophthalmic disease QA system integrated with knowledge graphs and digital humans. In: 2024 ICICSP, pp. 1094\u20131098. IEEE (2024)","DOI":"10.1109\/ICICSP62589.2024.10809040"},{"key":"2_CR7","doi-asserted-by":"crossref","unstructured":"Hao, H., et al.: Boosting large language model for speech synthesis: an empirical study. In: ICASSP, pp.\u00a01\u20135. IEEE (2025)","DOI":"10.1109\/ICASSP49660.2025.10890588"},{"key":"2_CR8","doi-asserted-by":"crossref","unstructured":"Hu, L.: Animate anyone: consistent and controllable image-to-video synthesis for character animation. In: CVPR, pp. 8153\u20138163 (2024)","DOI":"10.1109\/CVPR52733.2024.00779"},{"issue":"4","key":"2_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3592433","volume":"42","author":"B Kerbl","year":"2023","unstructured":"Kerbl, B., Kopanas, G., Leimk\u00fchler, T., Drettakis, G.: 3D Gaussian splatting for real-time radiance field rendering. ACM Trans. Graph. 42(4), 1\u2013139 (2023)","journal-title":"ACM Trans. Graph."},{"issue":"12","key":"2_CR10","doi-asserted-by":"publisher","first-page":"5923","DOI":"10.1109\/TIP.2019.2923051","volume":"28","author":"J Korhonen","year":"2019","unstructured":"Korhonen, J.: Two-level approach for no-reference consumer video quality assessment. IEEE Trans. Image Process. 28(12), 5923\u20135938 (2019)","journal-title":"IEEE Trans. Image Process."},{"issue":"9","key":"2_CR11","first-page":"5944","volume":"32","author":"B Li","year":"2022","unstructured":"Li, B., Zhang, W., Tian, M., Zhai, G., Wang, X.: Blindly assess quality of in-the-wild videos via quality-aware pre-training and motion perception. IEEE TCSVT 32(9), 5944\u20135958 (2022)","journal-title":"IEEE TCSVT"},{"key":"2_CR12","doi-asserted-by":"crossref","unstructured":"Li, D., Jiang, T., Jiang, M.: Quality assessment of in-the-wild videos. In: ACM MM, pp. 2351\u20132359 (2019)","DOI":"10.1145\/3343031.3351028"},{"key":"2_CR13","doi-asserted-by":"crossref","unstructured":"Li, Y.A., Han, C., Mesgarani, N.: StyleTTS: a style-based generative model for natural and diverse text-to-speech synthesis. IEEE JSTSP (2025)","DOI":"10.1109\/JSTSP.2025.3530171"},{"key":"2_CR14","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: CVPR, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"2_CR15","unstructured":"Midjourney (2023). https:\/\/www.midjourney.com\/home"},{"issue":"1","key":"2_CR16","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1145\/3503250","volume":"65","author":"B Mildenhall","year":"2021","unstructured":"Mildenhall, B., Srinivasan, P.P., Tancik, M., Barron, J.T., Ramamoorthi, R., Ng, R.: NeRF: representing scenes as neural radiance fields for view synthesis. Commun. ACM 65(1), 99\u2013106 (2021)","journal-title":"Commun. ACM"},{"issue":"12","key":"2_CR17","first-page":"4695","volume":"21","author":"A Mittal","year":"2012","unstructured":"Mittal, A., Moorthy, A.K., Bovik, A.C.: No-reference image quality assessment in the spatial domain. IEEE TIP 21(12), 4695\u20134708 (2012)","journal-title":"IEEE TIP"},{"issue":"1","key":"2_CR18","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1109\/TIP.2015.2502725","volume":"25","author":"A Mittal","year":"2015","unstructured":"Mittal, A., Saad, M.A., Bovik, A.C.: A completely blind video integrity oracle. IEEE Trans. Image Process. 25(1), 289\u2013300 (2015)","journal-title":"IEEE Trans. Image Process."},{"key":"2_CR19","doi-asserted-by":"crossref","unstructured":"Mittal, A., Soundararajan, R., Bovik, A.C.: Making a \u201ccompletely blind\u201d image quality analyzer. IEEE SPL 20(3), 209\u2013212 (2012)","DOI":"10.1109\/LSP.2012.2227726"},{"key":"2_CR20","unstructured":"OpenAI (2024). https:\/\/openai.com\/index\/hello-gpt-4o\/"},{"key":"2_CR21","unstructured":"OpenDalleV1.1 (2023). https:\/\/huggingface.co\/dataautogpt3\/OpenDalleV1.1"},{"key":"2_CR22","unstructured":"Podell, D., et al.: SDXL: improving latent diffusion models for high-resolution image synthesis. arXiv preprint arXiv:2307.01952 (2023)"},{"key":"2_CR23","doi-asserted-by":"crossref","unstructured":"Prajwal, K., Mukhopadhyay, R., Namboodiri, V.P., Jawahar, C.: A lip sync expert is all you need for speech to lip generation in the wild. In: ACM MM, pp. 484\u2013492 (2020)","DOI":"10.1145\/3394171.3413532"},{"key":"2_CR24","doi-asserted-by":"crossref","unstructured":"Saad, M.A., Bovik, A.C., Charrier, C.: Blind prediction of natural video quality. IEEE TIP (2014)","DOI":"10.1109\/TIP.2014.2299154"},{"key":"2_CR25","doi-asserted-by":"crossref","unstructured":"Shan, Y., Wang, S., Zhang, Z., Huang, K.: An XT slice based method for action recognition. In: 2011 ICCV Workshops, pp. 1897\u20131903. IEEE (2011)","DOI":"10.1109\/ICCVW.2011.6130480"},{"key":"2_CR26","doi-asserted-by":"crossref","unstructured":"Sun, W., Min, X., Lu, W., Zhai, G.: A deep learning based no-reference quality assessment model for UGC videos. In: ACM MM, pp. 856\u2013865 (2022)","DOI":"10.1145\/3503161.3548329"},{"key":"2_CR27","unstructured":"Tong, Z., Li, C., Chen, Z., Wu, B., Zhou, W.: MusePose: a pose-driven image-to-video framework for virtual human generation. arxiv (2024)"},{"key":"2_CR28","first-page":"4449","volume":"30","author":"Z Tu","year":"2021","unstructured":"Tu, Z., Wang, Y., Birkbeck, N., Adsumilli, B., Bovik, A.C.: UGC-VQA: benchmarking blind video quality assessment for user generated content. IEEE TIP 30, 4449\u20134464 (2021)","journal-title":"IEEE TIP"},{"key":"2_CR29","first-page":"425","volume":"2","author":"Z Tu","year":"2021","unstructured":"Tu, Z., Yu, X., Wang, Y., Birkbeck, N., Adsumilli, B., Bovik, A.C.: RAPIQUE: rapid and accurate video quality prediction of user generated content. IEEE OJSP 2, 425\u2013440 (2021)","journal-title":"IEEE OJSP"},{"key":"2_CR30","doi-asserted-by":"crossref","unstructured":"Wang, S., Li, L., Ding, Y., Fan, C., Yu, X.: Audio2head: audio-driven one-shot talking-head generation with natural head motion. arXiv preprint arXiv:2107.09293 (2021)","DOI":"10.24963\/ijcai.2021\/152"},{"key":"2_CR31","doi-asserted-by":"crossref","unstructured":"Wu, H., et al.: Fast-VQA: efficient end-to-end video quality assessment with fragment sampling. In: European Conference on Computer Vision, pp. 538\u2013554 (2022)","DOI":"10.1007\/978-3-031-20068-7_31"},{"key":"2_CR32","doi-asserted-by":"crossref","unstructured":"Yang, J., Abdel-Malek, K., Farrell, K., Nebel, K.: The IOWA interactive digital-human virtual environment. In: ASME International Mechanical Engineering Congress and Exposition, vol. 47136, pp. 1059\u20131067 (2004)","DOI":"10.1115\/IMECE2004-61791"},{"issue":"8","key":"2_CR33","first-page":"2579","volume":"24","author":"L Zhang","year":"2015","unstructured":"Zhang, L., Zhang, L., Bovik, A.C.: A feature-enriched completely blind image quality evaluator. IEEE TIP 24(8), 2579\u20132591 (2015)","journal-title":"IEEE TIP"},{"key":"2_CR34","doi-asserted-by":"crossref","unstructured":"Zhang, W., et al.: SadTalker: learning realistic 3d motion coefficients for stylized audio-driven single image talking face animation. In: CVPR, pp. 8652\u20138661 (2023)","DOI":"10.1109\/CVPR52729.2023.00836"},{"key":"2_CR35","unstructured":"Zhang, Y., et al.: MimicMotion: high-quality human motion video generation with confidence-aware pose guidance. arXiv preprint arXiv:2406.19680 (2024)"},{"issue":"6","key":"2_CR36","first-page":"1","volume":"20","author":"Z Zhang","year":"2024","unstructured":"Zhang, Z., et al.: GMS-3DQA: projection-based grid mini-patch sampling for 3D model quality assessment. ACM TOMM 20(6), 1\u201319 (2024)","journal-title":"ACM TOMM"},{"key":"2_CR37","unstructured":"Zhang, Z., et al.: Advancing zero-shot digital human quality assessment through text-prompted evaluation. arXiv preprint arXiv:2307.02808 (2023)"},{"key":"2_CR38","doi-asserted-by":"crossref","unstructured":"Zhang, Z., et al.: A reduced-reference quality assessment metric for textured mesh digital humans. In: ICASSP, pp. 2965\u20132969. IEEE (2024)","DOI":"10.1109\/ICASSP48485.2024.10447636"},{"key":"2_CR39","doi-asserted-by":"crossref","unstructured":"Zhang, Z., et al.: DDH-QA: a dynamic digital humans quality assessment database. In: ICME, pp. 2519\u20132524. IEEE (2023)","DOI":"10.1109\/ICME55011.2023.00429"},{"key":"2_CR40","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Zhou, Y., Sun, W., Min, X., Wu, Y., Zhai, G.: Perceptual quality assessment for digital human heads. In: ICASSP, pp.\u00a01\u20135. IEEE (2023)","DOI":"10.1109\/ICASSP49357.2023.10095347"},{"key":"2_CR41","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Zhou, Y., Sun, W., Min, X., Zhai, G.: Geometry-aware video quality assessment for dynamic digital human. In: ICIP, pp. 1365\u20131369. IEEE (2023)","DOI":"10.1109\/ICIP49359.2023.10222061"},{"key":"2_CR42","doi-asserted-by":"crossref","unstructured":"Zhang, Z., et al.: Quality-of-experience evaluation for digital twins in 6g network environments. IEEE Trans. Broadcast. (2024)","DOI":"10.1109\/TBC.2023.3345656"},{"key":"2_CR43","unstructured":"Zhou, Y., Chen, Y., Bi, K., Xiong, L., Liu, H.: An implementation of multimodal fusion system for intelligent digital human generation. arXiv preprint arXiv:2310.20251 (2023)"},{"key":"2_CR44","unstructured":"Zhou, Y., et al.: Memo-bench: a multiple benchmark for text-to-image and multimodal large language models on human emotion analysis. arXiv preprint arXiv:2411.11235 (2024)"},{"key":"2_CR45","doi-asserted-by":"crossref","unstructured":"Zhou, Y., et al.: Who is a better imitator: subjective and objective quality assessment of animated humans. TCSVT (2025)","DOI":"10.1109\/TCSVT.2025.3572000"},{"key":"2_CR46","doi-asserted-by":"crossref","unstructured":"Zhou, Y., et al.: THQA: a perceptual quality assessment database for talking heads. arXiv preprint arXiv:2404.09003 (2024)","DOI":"10.1109\/ICIP51287.2024.10647507"},{"key":"2_CR47","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Zhang, Z., Sun, W., Liu, X., Min, X., Zhai, G.: Subjective and objective quality-of-experience assessment for 3D talking heads. In: ACM MM 2024 (2024)","DOI":"10.1145\/3664647.3680964"},{"key":"2_CR48","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Zhang, Z., Sun, W., Min, X., Ma, X., Zhai, G.: A no-reference quality assessment method for digital human head. In: ICIP, pp. 36\u201340. IEEE (2023)","DOI":"10.1109\/ICIP49359.2023.10221964"},{"key":"2_CR49","doi-asserted-by":"crossref","unstructured":"Zhou, Y., et al.: 3DGCQA: a quality assessment database for 3D AI-generated contents. arXiv preprint arXiv:2409.07236 (2024)","DOI":"10.1109\/ICASSP49660.2025.10889921"},{"key":"2_CR50","doi-asserted-by":"crossref","unstructured":"Zhou, Y., et al.: ReLI-QA: a multidimensional quality assessment dataset for relighted human heads. In: VCIP (2024)","DOI":"10.1109\/VCIP63160.2024.10849906"}],"container-title":["Lecture Notes in Computer Science","Image and Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-3729-7_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T16:43:49Z","timestamp":1761929029000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-3729-7_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,1]]},"ISBN":["9789819537280","9789819537297"],"references-count":50,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-3729-7_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,1]]},"assertion":[{"value":"1 November 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIG","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Image and Graphics","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Xuzhou","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":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icig2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icig.csig.org.cn\/2025\/index.html","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}