{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T03:23:20Z","timestamp":1784258600968,"version":"3.55.0"},"publisher-location":"Cham","reference-count":58,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031732539","type":"print"},{"value":"9783031732546","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T00:00:00Z","timestamp":1732752000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T00:00:00Z","timestamp":1732752000000},"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\/978-3-031-73254-6_26","type":"book-chapter","created":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T07:23:50Z","timestamp":1732692230000},"page":"452-469","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["Exploring Pre-trained Text-to-Video Diffusion Models for\u00a0Referring Video Object Segmentation"],"prefix":"10.1007","author":[{"given":"Zixin","family":"Zhu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuelu","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongdong","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junsong","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chunming","family":"Qiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gang","family":"Hua","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,11,28]]},"reference":[{"key":"26_CR1","unstructured":"Blattmann, A., et\u00a0al.: Stable video diffusion: scaling latent video diffusion models to large datasets. arXiv preprint arXiv:2311.15127 (2023)"},{"key":"26_CR2","doi-asserted-by":"crossref","unstructured":"Blattmann, A., et al.: Align your latents: high-resolution video synthesis with latent diffusion models. In: CVPR, pp. 22563\u201322575 (2023)","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"26_CR3","doi-asserted-by":"crossref","unstructured":"Botach, A., Zheltonozhskii, E., Baskin, C.: End-to-end referring video object segmentation with multimodal transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4985\u20134995 (2022)","DOI":"10.1109\/CVPR52688.2022.00493"},{"key":"26_CR4","doi-asserted-by":"crossref","unstructured":"Chen, S., Sun, P., Song, Y., Luo, P.: Diffusiondet: diffusion model for object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 19830\u201319843 (2023)","DOI":"10.1109\/ICCV51070.2023.01816"},{"key":"26_CR5","doi-asserted-by":"crossref","unstructured":"Chen, W., et al.: Multi-attention network for compressed video referring object segmentation. In: ACM MM, pp. 4416\u20134425 (2022)","DOI":"10.1145\/3503161.3547761"},{"key":"26_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Z., Gao, R., Xiang, T.Z., Lin, F.: Diffusion model for camouflaged object detection. arXiv preprint arXiv:2308.00303 (2023)","DOI":"10.3233\/FAIA230302"},{"key":"26_CR7","doi-asserted-by":"crossref","unstructured":"Ding, H., Liu, C., Wang, S., Jiang, X.: VLT: vision-language transformer and query generation for referring segmentation. IEEE TPAMI (2022)","DOI":"10.1109\/ICCV48922.2021.01601"},{"key":"26_CR8","doi-asserted-by":"crossref","unstructured":"Ding, Z., Hui, T., Huang, J., Wei, X., Han, J., Liu, S.: Language-bridged spatial-temporal interaction for referring video object segmentation. In: CVPR, pp. 4964\u20134973 (2022)","DOI":"10.1109\/CVPR52688.2022.00491"},{"key":"26_CR9","unstructured":"Ding, Z., et al.: Progressive multimodal interaction network for referring video object segmentation. The 3rd Large-scale Video Object Segmentation Challenge 8 (2021)"},{"key":"26_CR10","doi-asserted-by":"crossref","unstructured":"Esser, P., Rombach, R., Ommer, B.: Taming transformers for high-resolution image synthesis. In: CVPR, pp. 12873\u201312883 (2021)","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"26_CR11","doi-asserted-by":"crossref","unstructured":"Fan, W.C., Chen, Y.C., Chen, D., Cheng, Y., Yuan, L., Wang, Y.C.F.: Frido: feature pyramid diffusion for complex scene image synthesis. In: Thirty-Seventh AAAI Conference on Artificial Intelligence (AAAI) (2023)","DOI":"10.1609\/aaai.v37i1.25133"},{"key":"26_CR12","doi-asserted-by":"crossref","unstructured":"Gavrilyuk, K., Ghodrati, A., Li, Z., Snoek, C.G.: Actor and action video segmentation from a sentence. In: CVPR, pp. 5958\u20135966 (2018)","DOI":"10.1109\/CVPR.2018.00624"},{"key":"26_CR13","doi-asserted-by":"crossref","unstructured":"Gu, S., et al.: Vector quantized diffusion model for text-to-image synthesis. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2022) (2022)","DOI":"10.1109\/CVPR52688.2022.01043"},{"key":"26_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1007\/978-3-319-46448-0_7","volume-title":"Computer Vision \u2013 ECCV 2016","author":"R Hu","year":"2016","unstructured":"Hu, R., Rohrbach, M., Darrell, T.: Segmentation from natural language expressions. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 108\u2013124. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_7"},{"key":"26_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1007\/978-3-030-20870-7_8","volume-title":"Computer Vision \u2013 ACCV 2018","author":"A Khoreva","year":"2019","unstructured":"Khoreva, A., Rohrbach, A., Schiele, B.: Video object segmentation with language referring expressions. In: Jawahar, C.V., Li, H., Mori, G., Schindler, K. (eds.) ACCV 2018. LNCS, vol. 11364, pp. 123\u2013141. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-20870-7_8"},{"key":"26_CR16","doi-asserted-by":"crossref","unstructured":"Kuhn, H.W.: The Hungarian method for the assignment problem. Naval Res. Logistics 52 (1955)","DOI":"10.1002\/nav.20053"},{"key":"26_CR17","doi-asserted-by":"crossref","unstructured":"Li, D., et al.: You only infer once: Cross-modal meta-transfer for referring video object segmentation. In: AAAI, pp. 1297\u20131305 (2022)","DOI":"10.1609\/aaai.v36i2.20017"},{"key":"26_CR18","first-page":"19652","volume":"34","author":"M Li","year":"2021","unstructured":"Li, M., Sigal, L.: Referring transformer: a one-step approach to multi-task visual grounding. NeurIPS 34, 19652\u201319664 (2021)","journal-title":"NeurIPS"},{"key":"26_CR19","doi-asserted-by":"crossref","unstructured":"Li, X., Sun, X., Meng, Y., Liang, J., Wu, F., Li, J.: Dice loss for data-imbalanced NLP tasks. arXiv preprint arXiv:1911.02855 (2019)","DOI":"10.18653\/v1\/2020.acl-main.45"},{"key":"26_CR20","doi-asserted-by":"crossref","unstructured":"Li, Z., Zhou, Q., Zhang, X., Zhang, Y., Wang, Y., Xie, W.: Open-vocabulary object segmentation with diffusion models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7667\u20137676 (2023)","DOI":"10.1109\/ICCV51070.2023.00705"},{"key":"26_CR21","unstructured":"Li, Z., Wang, M., Mei, J., Liu, Y.: MaIL: a unified mask-image-language trimodal network for referring image segmentation. arXiv preprint arXiv:2111.10747 (2021)"},{"key":"26_CR22","unstructured":"Liang, C., Wu, Y., Luo, Y., Yang, Y.: Clawcranenet: leveraging object-level relation for text-based video segmentation. arXiv preprint arXiv:2103.10702 (2021)"},{"key":"26_CR23","unstructured":"Liang, C., et al.: Rethinking cross-modal interaction from a top-down perspective for referring video object segmentation. arXiv preprint arXiv:2106.01061 (2021)"},{"key":"26_CR24","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: ICCV, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"issue":"9","key":"26_CR25","first-page":"4761","volume":"44","author":"S Liu","year":"2021","unstructured":"Liu, S., Hui, T., Huang, S., Wei, Y., Li, B., Li, G.: Cross-modal progressive comprehension for referring segmentation. IEEE TPAMI 44(9), 4761\u20134775 (2021)","journal-title":"IEEE TPAMI"},{"key":"26_CR26","unstructured":"Liu, Y., et al.: Roberta: a robustly optimized Bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)"},{"key":"26_CR27","unstructured":"Liu, Z., et al.: Video swin transformer. In: CVPR, pp. 3202\u20133211 (2022)"},{"key":"26_CR28","doi-asserted-by":"crossref","unstructured":"Mei, J., Piergiovanni, A., Hwang, J.N., Li, W.: SLVP: self-supervised language-video pre-training for referring video object segmentation. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 507\u2013517 (2024)","DOI":"10.1109\/WACVW60836.2024.00061"},{"key":"26_CR29","doi-asserted-by":"crossref","unstructured":"Miao, B., Bennamoun, M., Gao, Y., Mian, A.: Spectrum-guided multi-granularity referring video object segmentation. In: ICCV, pp. 920\u2013930 (2023)","DOI":"10.1109\/ICCV51070.2023.00091"},{"key":"26_CR30","unstructured":"Molad, E., et al.: Dreamix: video diffusion models are general video editors. arXiv preprint arXiv:2302.01329 (2023)"},{"key":"26_CR31","doi-asserted-by":"crossref","unstructured":"Park, H., Yoo, J., Jeong, S., Venkatesh, G., Kwak, N.: Learning dynamic network using a reuse gate function in semi-supervised video object segmentation. In: CVPR, pp. 8405\u20138414 (2021)","DOI":"10.1109\/CVPR46437.2021.00830"},{"key":"26_CR32","doi-asserted-by":"crossref","unstructured":"Pnvr, K., Singh, B., Ghosh, P., Siddiquie, B., Jacobs, D.: LD-ZNet: a latent diffusion approach for text-based image segmentation. In: ICCV, pp. 4157\u20134168 (2023)","DOI":"10.1109\/ICCV51070.2023.00384"},{"key":"26_CR33","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML, pp. 8748\u20138763. PMLR (2021)"},{"key":"26_CR34","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.061251(2), 3 (2022)"},{"key":"26_CR35","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. In: CVPR, pp. 658\u2013666 (2019)","DOI":"10.1109\/CVPR.2019.00075"},{"key":"26_CR36","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: CVPR, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"26_CR37","doi-asserted-by":"crossref","unstructured":"Saharia, C., et al.: Palette: image-to-image diffusion models. In: ACM SIGGRAPH, pp. 1\u201310 (2022)","DOI":"10.1145\/3528233.3530757"},{"key":"26_CR38","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"208","DOI":"10.1007\/978-3-030-58555-6_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"S Seo","year":"2020","unstructured":"Seo, S., Lee, J.-Y., Han, B.: URVOS: unified referring video object segmentation network with a large-scale benchmark. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12360, pp. 208\u2013223. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58555-6_13"},{"key":"26_CR39","doi-asserted-by":"crossref","unstructured":"Tur, A.O., Dall\u2019Asen, N., Beyan, C., Ricci, E.: Exploring diffusion models for unsupervised video anomaly detection. In: ICIP, pp. 2540\u20132544. IEEE (2023)","DOI":"10.1109\/ICIP49359.2023.10222594"},{"key":"26_CR40","unstructured":"Vaswani, A., et al.: Attention is all you need. NeurIPS 30 (2017)"},{"key":"26_CR41","doi-asserted-by":"crossref","unstructured":"Wang, H., Deng, C., Yan, J., Tao, D.: Asymmetric cross-guided attention network for actor and action video segmentation from natural language query. In: ICCV, pp. 3939\u20133948 (2019)","DOI":"10.1109\/ICCV.2019.00404"},{"key":"26_CR42","unstructured":"Wang, J., Yuan, H., Chen, D., Zhang, Y., Wang, X., Zhang, S.: Modelscope text-to-video technical report. arXiv preprint arXiv:2308.06571 (2023)"},{"key":"26_CR43","unstructured":"Wang, W., et al.: Semantic image synthesis via diffusion models. arXiv preprint arXiv:2207.00050 (2022)"},{"key":"26_CR44","doi-asserted-by":"crossref","unstructured":"Wang, Z., et al.: CRIS: clip-driven referring image segmentation. In: CVPR, pp. 11686\u201311695 (2022)","DOI":"10.1109\/CVPR52688.2022.01139"},{"key":"26_CR45","doi-asserted-by":"crossref","unstructured":"Wu, D., Dong, X., Shao, L., Shen, J.: Multi-level representation learning with semantic alignment for referring video object segmentation. In: CVPR, pp. 4996\u20135005 (2022)","DOI":"10.1109\/CVPR52688.2022.00494"},{"key":"26_CR46","doi-asserted-by":"crossref","unstructured":"Wu, D., Wang, T., Zhang, Y., Zhang, X., Shen, J.: Onlinerefer: a simple online baseline for referring video object segmentation. In: ICCV, pp. 2761\u20132770 (2023)","DOI":"10.1109\/ICCV51070.2023.00259"},{"key":"26_CR47","doi-asserted-by":"crossref","unstructured":"Wu, J., Jiang, Y., Sun, P., Yuan, Z., Luo, P.: Language as queries for referring video object segmentation. In: CVPR, pp. 4974\u20134984 (2022)","DOI":"10.1109\/CVPR52688.2022.00492"},{"key":"26_CR48","doi-asserted-by":"crossref","unstructured":"Wu, W., Zhao, Y., Shou, M.Z., Zhou, H., Shen, C.: Diffumask: synthesizing images with pixel-level annotations for semantic segmentation using diffusion models. arXiv preprint arXiv:2303.11681 (2023)","DOI":"10.1109\/ICCV51070.2023.00117"},{"key":"26_CR49","doi-asserted-by":"crossref","unstructured":"Xu, J., Liu, S., Vahdat, A., Byeon, W., Wang, X., De\u00a0Mello, S.: Open-vocabulary panoptic segmentation with text-to-image diffusion models. In: CVPR, pp. 2955\u20132966 (2023)","DOI":"10.1109\/CVPR52729.2023.00289"},{"key":"26_CR50","doi-asserted-by":"crossref","unstructured":"Yang, Z., Wang, J., Tang, Y., Chen, K., Zhao, H., Torr, P.H.: LAVT: language-aware vision transformer for referring image segmentation. In: CVPR, pp. 18155\u201318165 (2022)","DOI":"10.1109\/CVPR52688.2022.01762"},{"key":"26_CR51","doi-asserted-by":"crossref","unstructured":"Ye, L., Rochan, M., Liu, Z., Wang, Y.: Cross-modal self-attention network for referring image segmentation. In: CVPR, pp. 10502\u201310511 (2019)","DOI":"10.1109\/CVPR.2019.01075"},{"key":"26_CR52","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1007\/978-3-319-46475-6_5","volume-title":"Computer Vision \u2013 ECCV 2016","author":"L Yu","year":"2016","unstructured":"Yu, L., Poirson, P., Yang, S., Berg, A.C., Berg, T.L.: Modeling context in referring expressions. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 69\u201385. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46475-6_5"},{"key":"26_CR53","unstructured":"Zhang, J., et al.: A tale of two features: stable diffusion complements dino for zero-shot semantic correspondence. NeurIPS 36 (2024)"},{"key":"26_CR54","unstructured":"Zhao, H., Lin, K.Q., Yan, R., Li, Z.: Diffusionvmr: diffusion model for video moment retrieval. arXiv preprint arXiv:2308.15109 (2023)"},{"key":"26_CR55","unstructured":"Zhao, S., et al.: Uni-controlnet: all-in-one control to text-to-image diffusion models. In: Thirty-Seventh Conference on Neural Information Processing Systems (NeurIPS 2023) (2023)"},{"key":"26_CR56","unstructured":"Zhou, D., Wang, W., Yan, H., Lv, W., Zhu, Y., Feng, J.: Magicvideo: efficient video generation with latent diffusion models. arXiv preprint arXiv:2211.11018 (2022)"},{"issue":"1","key":"26_CR57","first-page":"330","volume":"32","author":"W Zhu","year":"2021","unstructured":"Zhu, W., Li, J., Lu, J., Zhou, J.: Separable structure modeling for semi-supervised video object segmentation. IEEE TCSVT 32(1), 330\u2013344 (2021)","journal-title":"IEEE TCSVT"},{"key":"26_CR58","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable DETR: deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159 (2020)"}],"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\/978-3-031-73254-6_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T08:12:12Z","timestamp":1732695132000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73254-6_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,28]]},"ISBN":["9783031732539","9783031732546"],"references-count":58,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73254-6_26","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,28]]},"assertion":[{"value":"28 November 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"}}]}}