{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,28]],"date-time":"2025-10-28T15:17:10Z","timestamp":1761664630417,"version":"3.40.3"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031463136"},{"type":"electronic","value":"9783031463143"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-46314-3_29","type":"book-chapter","created":{"date-parts":[[2023,10,28]],"date-time":"2023-10-28T06:03:06Z","timestamp":1698472986000},"page":"360-372","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Learning to\u00a0Fuse Residual and\u00a0Conditional Information for\u00a0Video Compression and\u00a0Reconstruction"],"prefix":"10.1007","author":[{"given":"Ran","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhuang","family":"Qi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangxu","family":"Meng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Meng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,10,29]]},"reference":[{"key":"29_CR1","unstructured":"Ball\u00e9, J., Laparra, V., Simoncelli, E.P.: End-to-end optimized image compression. arXiv preprint arXiv:1611.01704 (2016)"},{"key":"29_CR2","unstructured":"Ball\u00e9, J., Minnen, D., Singh, S., Hwang, S.J., Johnston, N.: Variational image compression with a scale hyperprior. arXiv preprint arXiv:1802.01436 (2018)"},{"key":"29_CR3","doi-asserted-by":"publisher","first-page":"15835","DOI":"10.1109\/JIOT.2023.3265645","volume":"10","author":"QL Guan","year":"2023","unstructured":"Guan, Q.L., Zheng, Y., Meng, L., Dong, L.Q., Hao, Q.: Improving the generalization of visual classification models across IoT cameras via cross-modal inference and fusion. IEEE Internet Things J. 10, 15835\u201315846 (2023)","journal-title":"IEEE Internet Things J."},{"key":"29_CR4","doi-asserted-by":"publisher","unstructured":"He, D., Zheng, Y., Sun, B., Wang, Y., Qin, H.: Checkerboard context model for efficient learned image compression. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 14766\u201314775 (2021). https:\/\/doi.org\/10.1109\/CVPR46437.2021.01453","DOI":"10.1109\/CVPR46437.2021.01453"},{"key":"29_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1007\/978-3-030-58536-5_12","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Z Hu","year":"2020","unstructured":"Hu, Z., Chen, Z., Xu, D., Lu, G., Ouyang, W., Gu, S.: Improving deep video compression by resolution-adaptive flow coding. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12347, pp. 193\u2013209. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58536-5_12"},{"key":"29_CR6","doi-asserted-by":"crossref","unstructured":"Hu, Z., Lu, G., Xu, D.: FVC: a new framework towards deep video compression in feature space. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1502\u20131511 (2021)","DOI":"10.1109\/CVPR46437.2021.00155"},{"key":"29_CR7","doi-asserted-by":"crossref","unstructured":"Johnston, N., et al.: Improved lossy image compression with priming and spatially adaptive bit rates for recurrent networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 4385\u20134393 (2018)","DOI":"10.1109\/CVPR.2018.00461"},{"issue":"12","key":"29_CR8","doi-asserted-by":"publisher","first-page":"4434","DOI":"10.1109\/TCSVT.2020.2981652","volume":"30","author":"SJ Lee","year":"2020","unstructured":"Lee, S.J., Lee, S., Cho, S.I., Kang, S.J.: Object detection-based video retargeting with spatial-temporal consistency. IEEE Trans. Circuits Syst. Video Technol. 30(12), 4434\u20134439 (2020)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"29_CR9","doi-asserted-by":"crossref","unstructured":"Li, C., Liu, X., Zhang, X., Qin, B.: Design of UAV single object tracking algorithm based on feature fusion. In: 2021 40th Chinese Control Conference (CCC), pp. 3088\u20133092. IEEE (2021)","DOI":"10.23919\/CCC52363.2021.9549909"},{"key":"29_CR10","first-page":"18114","volume":"34","author":"J Li","year":"2021","unstructured":"Li, J., Li, B., Lu, Y.: Deep contextual video compression. Adv. Neural. Inf. Process. Syst. 34, 18114\u201318125 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"29_CR11","doi-asserted-by":"crossref","unstructured":"Li, X., Wu, L., Chen, X., Meng, L., Meng, X.: DSE-Net: artistic font image synthesis via disentangled style encoding. In: 2022 IEEE International Conference on Multimedia and Expo (ICME), pp. 1\u20136. IEEE (2022)","DOI":"10.1109\/ICME52920.2022.9859795"},{"key":"29_CR12","doi-asserted-by":"crossref","unstructured":"Li, X., Wu, L., Wang, C., Meng, L., Meng, X.: Compositional zero-shot artistic font synthesis. In: Proceedings of IJCAI (2023)","DOI":"10.24963\/ijcai.2023\/122"},{"key":"29_CR13","doi-asserted-by":"crossref","unstructured":"Li, X., Ma, H., Meng, L., Meng, X.: Comparative study of adversarial training methods for long-tailed classification. In: Proceedings of the 1st International Workshop on Adversarial Learning for Multimedia,","DOI":"10.1145\/3475724.3483601"},{"key":"29_CR14","doi-asserted-by":"crossref","unstructured":"Li, X., Zheng, Y., Ma, H., Qi, Z., Meng, X., Meng, L.: Cross-modal learning using privileged information for long-tailed image classification. In: Proceedings of CVM (2023)","DOI":"10.1007\/s41095-023-0382-0"},{"key":"29_CR15","doi-asserted-by":"crossref","unstructured":"Lin, J., Liu, D., Li, H., Wu, F.: M-LVC: multiple frames prediction for learned video compression. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3546\u20133554 (2020)","DOI":"10.1109\/CVPR42600.2020.00360"},{"key":"29_CR16","doi-asserted-by":"crossref","unstructured":"Liu, J., et al.: Prompt learning with cross-modal feature alignment for visual domain adaptation. In: Proceedings of CAAI (2022)","DOI":"10.1007\/978-3-031-20497-5_34"},{"key":"29_CR17","doi-asserted-by":"crossref","unstructured":"Liu, T., Qi, Z., Chen, Z., Meng, X., Meng, L.: Cross-training with prototypical distillation for improving the generalization of federated learning. In: Proceedings of ICME (2023)","DOI":"10.1109\/ICME55011.2023.00117"},{"key":"29_CR18","doi-asserted-by":"crossref","unstructured":"Lu, G., Ouyang, W., Xu, D., Zhang, X., Cai, C., Gao, Z.: DVC: an end-to-end deep video compression framework. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11006\u201311015 (2019)","DOI":"10.1109\/CVPR.2019.01126"},{"key":"29_CR19","doi-asserted-by":"crossref","unstructured":"Ma, H., Li, X., Meng, L., Meng, X.: Comparative study of adversarial training methods for cold-start recommendation. In: Proceedings of ADVM (2021)","DOI":"10.1145\/3475724.3483600"},{"key":"29_CR20","doi-asserted-by":"crossref","unstructured":"Ma, H., Qi, Z., Dong, X., Li, X., Zheng, Y., Meng, X.M.L.: Cross-modal content inference and feature enrichment for cold-start recommendation. In: Proceedings of IJCNN (2023)","DOI":"10.1109\/IJCNN54540.2023.10191979"},{"key":"29_CR21","doi-asserted-by":"crossref","unstructured":"Ma, H., et al.: Exploring false hard negative sample in cross-domain recommendation. In: Proceedings of RecSys (2023)","DOI":"10.1145\/3604915.3608791"},{"key":"29_CR22","unstructured":"Ma, H., et al.: Triple sequence learning for cross-domain recommendation. arXiv preprint arXiv:2304.05027 (2023)"},{"key":"29_CR23","unstructured":"McMahan, B., Moore, E., Ramage, D., Hampson, S., y Arcas, B.A.: Communication-efficient learning of deep networks from decentralized data. In: Artificial intelligence and statistics, pp. 1273\u20131282. PMLR (2017)"},{"key":"29_CR24","doi-asserted-by":"crossref","unstructured":"Meng, L., Feng, F., He, X., Gao, X., Chua, T.S.: Heterogeneous fusion of semantic and collaborative information for visually-aware food recommendation. In: Proceedings of MM (2020)","DOI":"10.1145\/3394171.3413598"},{"key":"29_CR25","doi-asserted-by":"crossref","unstructured":"Mercat, A., Viitanen, M., Vanne, J.: UVG dataset: 50\/120fps 4K sequences for video codec analysis and development. In: Proceedings of the 11th ACM Multimedia Systems Conference, pp. 297\u2013302 (2020)","DOI":"10.1145\/3339825.3394937"},{"key":"29_CR26","unstructured":"Minnen, D., Ball\u00e9, J., Toderici, G.D.: Joint autoregressive and hierarchical priors for learned image compression. In: Advances in Neural Information Processing Systems, vol. 31 (2018)"},{"key":"29_CR27","doi-asserted-by":"publisher","unstructured":"Qi, Z., Wang, Y., Chen, Z., Wang, R., Meng, X., Meng, L.: Clustering-based curriculum construction for sample-balanced federated learning. In: Fang, L., Povey, D., Zhai, G., Mei, T., Wang, R. (eds.) Artificial Intelligence. CICAI 2022. Lecture Notes in Computer Science, vol. 13606, pp. 155\u2013166. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20503-3_13","DOI":"10.1007\/978-3-031-20503-3_13"},{"issue":"12","key":"29_CR28","doi-asserted-by":"publisher","first-page":"1649","DOI":"10.1109\/TCSVT.2012.2221191","volume":"22","author":"GJ Sullivan","year":"2012","unstructured":"Sullivan, G.J., Ohm, J.R., Han, W.J., Wiegand, T.: Overview of the high efficiency video coding (HEVC) standard. IEEE Trans. Circuits Syst. Video Technol. 22(12), 1649\u20131668 (2012)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"29_CR29","doi-asserted-by":"publisher","unstructured":"Sun, W., Li, X., Li, M., Wang, Y., Zheng, Y., Meng, X., Meng, L.: Sequential fusion of multi-view video frames for 3D scene generation. In: Fang, L., Povey, D., Zhai, G., Mei, T., Wang, R. (eds.) Artificial Intelligence. CICAI 2022. Lecture Notes in Computer Science, vol. 13604, pp. 597\u2013608. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20497-5_49","DOI":"10.1007\/978-3-031-20497-5_49"},{"issue":"8","key":"29_CR30","doi-asserted-by":"publisher","first-page":"1336","DOI":"10.1109\/JPROC.2002.800725","volume":"90","author":"D Taubman","year":"2002","unstructured":"Taubman, D., Marcellin, M.: JPEG 2000: standard for interactive imaging. Proc. IEEE 90(8), 1336\u20131357 (2002). https:\/\/doi.org\/10.1109\/JPROC.2002.800725","journal-title":"Proc. IEEE"},{"key":"29_CR31","unstructured":"Toderici, G., et al.: Variable rate image compression with recurrent neural networks. arXiv preprint arXiv:1511.06085 (2015)"},{"key":"29_CR32","doi-asserted-by":"publisher","unstructured":"Wang, Y., Li, X., Ma, H., Qi, Z., Meng, X., Meng, L.: Causal inference with sample balancing for out-of-distribution detection in visual classification. In: Fang, L., Povey, D., Zhai, G., Mei, T., Wang, R. (eds.) Artificial Intelligence. CICAI 2022. Lecture Notes in Computer Science, vol. 13604, pp. 572\u2013583. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20497-5_47","DOI":"10.1007\/978-3-031-20497-5_47"},{"key":"29_CR33","doi-asserted-by":"publisher","unstructured":"Wang, Y., Li, X., Qi, Z., Li, J., Li, X., Meng, X., Meng, L.: Meta-causal feature learning for out-of-distribution generalization. In: Karlinsky, L., Michaeli, T., Nishino, K. (eds.) Computer Vision \u2013 ECCV 2022 Workshops. ECCV 2022. Lecture Notes in Computer Science, vol. 13806, pp. 530\u2013545. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-25075-0_36","DOI":"10.1007\/978-3-031-25075-0_36"},{"key":"29_CR34","doi-asserted-by":"crossref","unstructured":"Wang, Y., Qi, Z., Li, X., Liu, J., Meng, X., Meng, L.: Multi-channel attentive weighting of visual frames for multimodal video classification. In: Proceedings of IJCNN (2023)","DOI":"10.1109\/IJCNN54540.2023.10192036"},{"key":"29_CR35","unstructured":"Wang, Z., Simoncelli, E.P., Bovik, A.C.: Multiscale structural similarity for image quality assessment. In: The Thirty-Seventh Asilomar Conference on Signals, Systems and Computers, vol. 2, pp. 1398\u20131402. IEEE (2003)"},{"issue":"7","key":"29_CR36","doi-asserted-by":"publisher","first-page":"560","DOI":"10.1109\/TCSVT.2003.815165","volume":"13","author":"T Wiegand","year":"2003","unstructured":"Wiegand, T., Sullivan, G.J., Bjontegaard, G., Luthra, A.: Overview of the h. 264\/AVC video coding standard. IEEE Trans. Circ. Syst. Video Technol. 13(7), 560\u2013576 (2003)","journal-title":"IEEE Trans. Circ. Syst. Video Technol."},{"key":"29_CR37","doi-asserted-by":"publisher","first-page":"1106","DOI":"10.1007\/s11263-018-01144-2","volume":"127","author":"T Xue","year":"2019","unstructured":"Xue, T., Chen, B., Wu, J., Wei, D., Freeman, W.T.: Video enhancement with task-oriented flow. Int. J. Comput. Vision 127, 1106\u20131125 (2019)","journal-title":"Int. J. Comput. Vision"},{"key":"29_CR38","doi-asserted-by":"crossref","unstructured":"Yang, R., Mentzer, F., Gool, L.V., Timofte, R.: Learning for video compression with hierarchical quality and recurrent enhancement. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6628\u20136637 (2020)","DOI":"10.1109\/CVPR42600.2020.00666"},{"issue":"5","key":"29_CR39","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3444944","volume":"15","author":"L Yao","year":"2021","unstructured":"Yao, L., Chu, Z., Li, S., Li, Y., Gao, J., Zhang, A.: A survey on causal inference. ACM Trans. Knowl. Disc. Data (TKDD) 15(5), 1\u201346 (2021)","journal-title":"ACM Trans. Knowl. Disc. Data (TKDD)"},{"issue":"4","key":"29_CR40","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3391743","volume":"11","author":"R Yao","year":"2020","unstructured":"Yao, R., Lin, G., Xia, S., Zhao, J., Zhou, Y.: Video object segmentation and tracking: a survey. ACM Trans. Intell. Syst. Technol. (TIST) 11(4), 1\u201347 (2020)","journal-title":"ACM Trans. Intell. Syst. Technol. (TIST)"}],"container-title":["Lecture Notes in Computer Science","Image and Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-46314-3_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T23:56:42Z","timestamp":1730419002000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-46314-3_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031463136","9783031463143"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-46314-3_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"29 October 2023","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":"Nanjing","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":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icig2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/icig2023.csig.org.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Conference Management Toolkit","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"409","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"166","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"41% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}