{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T19:58:57Z","timestamp":1780775937999,"version":"3.54.1"},"publisher-location":"Singapore","reference-count":30,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819212996","type":"print"},{"value":"9789819213009","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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\/978-981-92-1300-9_14","type":"book-chapter","created":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T19:04:52Z","timestamp":1780772692000},"page":"175-186","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Dual-Modality Latent Gloss Alignment for\u00a0Gloss-Free Sign Language Translation"],"prefix":"10.1007","author":[{"given":"Yunlong","family":"Yu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ming","family":"Ji","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziqian","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,7]]},"reference":[{"key":"14_CR1","doi-asserted-by":"crossref","unstructured":"Camgoz, N.C., Hadfield, S., Koller, O., Ney, H., Bowden, R.: Neural sign language translation. In: CVPR, pp. 7784\u20137793 (2018)","DOI":"10.1109\/CVPR.2018.00812"},{"key":"14_CR2","doi-asserted-by":"crossref","unstructured":"Camgoz, N.C., Koller, O., Hadfield, S., Bowden, R.: Multi-channel transformers for multi-articulatory sign language translation. In: ECCV Workshops, pp. 301\u2013319 (2020)","DOI":"10.1007\/978-3-030-66823-5_18"},{"key":"14_CR3","unstructured":"Camgoz, N.C., Koller, O., Hadfield, S., Bowden, R.: Sign language transformers: Joint end-to-end sign language recognition and translation. In: CVPR, pp. 10023\u201310033 (2020)"},{"key":"14_CR4","doi-asserted-by":"crossref","unstructured":"Chen, Y., Wei, F., Sun, X., Wu, Z., Lin, S.: A simple multi-modality transfer learning baseline for sign language translation. In: CVPR, pp. 5120\u20135130 (2022)","DOI":"10.1109\/CVPR52688.2022.00506"},{"key":"14_CR5","doi-asserted-by":"crossref","unstructured":"Chen, Y., Zuo, R., Wei, F., Wu, Y., Liu, S., Mak, B.: Two-stream network for sign language recognition and translation. In: NeurIPS, pp. 17043\u201317056 (2022)","DOI":"10.52202\/068431-1240"},{"key":"14_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Z., et al.: C2rl: Content and context representation learning for gloss-free sign language translation and retrieval. In: IEEE Transactions on Circuits and Systems for Video Technology (2025)","DOI":"10.1109\/TCSVT.2025.3553052"},{"key":"14_CR7","doi-asserted-by":"crossref","unstructured":"Fu, B., et al.: A token-level contrastive framework for sign language translation. In: ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing, pp.\u00a01\u20135 (2023)","DOI":"10.1109\/ICASSP49357.2023.10095466"},{"key":"14_CR8","doi-asserted-by":"crossref","unstructured":"Gong, J., Foo, L.G., He, Y., Rahmani, H., Liu, J.: LLMs are good sign language translators. In: CVPR, pp. 18362\u201318372 (2024)","DOI":"10.1109\/CVPR52733.2024.01738"},{"key":"14_CR9","doi-asserted-by":"crossref","unstructured":"Guan, M., Wang, Y., Ma, G., Liu, J., Sun, M.: Multi-stream keypoint attention network for sign language recognition and translation, arXiv:2405.05672 (2024)","DOI":"10.1016\/j.patcog.2025.111602"},{"key":"14_CR10","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.111602","volume":"165","author":"M Guan","year":"2025","unstructured":"Guan, M., Wang, Y., Ma, G., Liu, J., Sun, M.: Mska: Multi-stream keypoint attention network for sign language recognition and translation. Pattern Recogn. 165, 111602 (2025)","journal-title":"Pattern Recogn."},{"key":"14_CR11","unstructured":"Guo, J., Li, P., Cohn, T.: Bridging sign and spoken languages: Pseudo gloss generation for sign language translation. arXiv preprint arXiv:2505.15438 (2025)"},{"issue":"9","key":"14_CR12","doi-asserted-by":"publisher","first-page":"11221","DOI":"10.1109\/TPAMI.2023.3269220","volume":"45","author":"H Hu","year":"2023","unstructured":"Hu, H., Zhao, W., Zhou, W., Li, H.: Signbert+: Hand-model-aware self-supervised pre-training for sign language understanding. IEEE Trans. Pattern Anal. Mach. Intell. 45(9), 11221\u201311239 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"14_CR13","doi-asserted-by":"crossref","unstructured":"Jang, Y., Raajesh, H., Momeni, L., Varol, G., Zisserman, A.: Lost in translation. In: Sign language translation with contextual cues, arXiv preprint arXiv:2501.09754 (2025)","DOI":"10.1109\/CVPR52734.2025.00817"},{"key":"14_CR14","doi-asserted-by":"crossref","unstructured":"Jiao, P., Min, Y., Chen, X.: Visual alignment pre-training for sign language translation, pp. 349\u2013367. ECCV (2024)","DOI":"10.1007\/978-3-031-72946-1_20"},{"key":"14_CR15","doi-asserted-by":"crossref","unstructured":"Liu, Y., Zhang, W., Ren, S., Huang, C., Yu, J., Xu, L.: Scope: Sign language contextual processing with embedding from LLMs, pp. 5739\u20135747. AAAI (2025)","DOI":"10.1609\/aaai.v39i6.32612"},{"key":"14_CR16","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML, pp. 8748\u20138763 (2021)"},{"key":"14_CR17","doi-asserted-by":"crossref","unstructured":"Shi, B., Brentari, D., Shakhnarovich, G., Livescu, K.: Open-domain sign language translation learned from online video. In: EMNLP, pp. 6365\u20136379 (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.427"},{"key":"14_CR18","unstructured":"Sincan, O.M., Camgoz, N.C., Bowden, R.: Using an llm to turn sign spottings into spoken language sentences. arXiv preprint arXiv:2403.10434 (2024)"},{"key":"14_CR19","unstructured":"Sohn, K.: Improved deep metric learning with multi-class n-pair loss objective. NeurIPS (2016)"},{"key":"14_CR20","doi-asserted-by":"crossref","unstructured":"Voskou, A., Panousis, K.P., Kosmopoulos, D., Metaxas, D.N., Chatzis, S.: Stochastic transformer networks with linear competing units: Application to end-to-end sl translation. In: ICCV, pp. 11946\u201311955 (2021)","DOI":"10.1109\/ICCV48922.2021.01173"},{"key":"14_CR21","unstructured":"Wong, R.C., Camg\u00f6z, N.C., Bowden, R.: Sign2gpt: leveraging large language models for gloss-free sign language translation. In: ICLR. (2024)"},{"key":"14_CR22","unstructured":"Ye, J., Wang, X., Jiao, W., Liang, J., Xiong, H.: Improving gloss-free sign language translation by reducing representation density. In: NeurIPS (2024)"},{"key":"14_CR23","doi-asserted-by":"crossref","unstructured":"Yin, A., Zhong, T., Tang, L., Jin, W., Jin, T., Zhao, Z.: Gloss attention for gloss-free sign language translation. In: CVPR, pp. 2551\u20132562 (2023)","DOI":"10.1109\/CVPR52729.2023.00251"},{"key":"14_CR24","unstructured":"Zhang, B., M\u00fcller, M., Sennrich, R.: Sltunet: A simple unified model for sign language translation. In: ICLR (2024)"},{"key":"14_CR25","doi-asserted-by":"crossref","unstructured":"Zhang, B., Tanzer, G., Firat, O.: Scaling sign language translation. In: NeurIPS (2025)","DOI":"10.18653\/v1\/2025.naacl-long.19"},{"key":"14_CR26","unstructured":"Zhang, R., Hu, C., Yu, P., Chen, Y.: Improving multilingual sign language translation with automatically clustered language family information. In: Proceedings of the 31st International Conference on Computational Linguistics, pp. 3579\u20133588 (2025)"},{"key":"14_CR27","doi-asserted-by":"crossref","unstructured":"Zhao, R., Zhang, L., Fu, B., Hu, C., Su, J., Chen, Y.: Conditional variational autoencoder for sign language translation with cross-modal alignment, pp. 19643\u201319651. AAAI (2024)","DOI":"10.1609\/aaai.v38i17.29937"},{"key":"14_CR28","doi-asserted-by":"crossref","unstructured":"Zhou, B., et al.: Gloss-free sign language translation: Improving from visual-language pretraining. In: ICCV, pp. 20871\u201320881 (2023)","DOI":"10.1109\/ICCV51070.2023.01908"},{"key":"14_CR29","doi-asserted-by":"crossref","unstructured":"Zhou, H., Zhou, W., Qi, W., Pu, J., Li, H.: Improving sign language translation with monolingual data by sign back-translation. In: CVPR, pp. 1316\u20131325 (2021)","DOI":"10.1109\/CVPR46437.2021.00137"},{"key":"14_CR30","doi-asserted-by":"publisher","first-page":"768","DOI":"10.1109\/TMM.2021.3059098","volume":"24","author":"H Zhou","year":"2021","unstructured":"Zhou, H., Zhou, W., Zhou, Y., Li, H.: Spatial-temporal multi-cue network for sign language recognition and translation. IEEE Trans. Multimedia 24, 768\u2013779 (2021)","journal-title":"IEEE Trans. Multimedia"}],"container-title":["Lecture Notes in Computer Science","Advances in Knowledge Discovery and Data Mining"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-92-1300-9_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T19:04:58Z","timestamp":1780772698000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-1300-9_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819212996","9789819213009"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-1300-9_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"7 June 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PAKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific-Asia Conference on Knowledge Discovery and Data Mining","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hong Kong","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":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 June 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 June 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pakdd2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.pakdd2026.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}