{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T04:49:11Z","timestamp":1780634951537,"version":"3.54.1"},"publisher-location":"Cham","reference-count":79,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031200731","type":"print"},{"value":"9783031200748","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-20074-8_25","type":"book-chapter","created":{"date-parts":[[2022,11,11]],"date-time":"2022-11-11T20:23:11Z","timestamp":1668198191000},"page":"431-449","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["MUGEN: A Playground for\u00a0Video-Audio-Text Multimodal Understanding and\u00a0GENeration"],"prefix":"10.1007","author":[{"given":"Thomas","family":"Hayes","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Songyang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xi","family":"Yin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guan","family":"Pang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sasha","family":"Sheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Harry","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Songwei","family":"Ge","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiyuan","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Devi","family":"Parikh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,11,12]]},"reference":[{"key":"25_CR1","doi-asserted-by":"crossref","unstructured":"Agrawal, H., et al.: NoCaps: novel object captioning at scale. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8948\u20138957 (2019)","DOI":"10.1109\/ICCV.2019.00904"},{"key":"25_CR2","doi-asserted-by":"crossref","unstructured":"Anderson, P., Fernando, B., Johnson, M., Gould, S.: Guided open vocabulary image captioning with constrained beam search. arXiv preprint arXiv:1612.00576 (2016)","DOI":"10.18653\/v1\/D17-1098"},{"key":"25_CR3","doi-asserted-by":"crossref","unstructured":"Anne Hendricks, L., Wang, O., Shechtman, E., Sivic, J., Darrell, T., Russell, B.: Localizing moments in video with natural language. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5803\u20135812 (2017)","DOI":"10.1109\/ICCV.2017.618"},{"key":"25_CR4","doi-asserted-by":"crossref","unstructured":"Antol, S., et al.: VQA: visual question answering. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2425\u20132433 (2015)","DOI":"10.1109\/ICCV.2015.279"},{"key":"25_CR5","doi-asserted-by":"crossref","unstructured":"Bain, M., Nagrani, A., Varol, G., Zisserman, A.: Frozen in time: a joint video and image encoder for end-to-end retrieval. In: IEEE International Conference on Computer Vision (2021)","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"25_CR6","doi-asserted-by":"crossref","unstructured":"Changpinyo, S., Sharma, P., Ding, N., Soricut, R.: Conceptual 12M: pushing web-scale image-text pre-training to recognize long-tail visual concepts. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3558\u20133568 (2021)","DOI":"10.1109\/CVPR46437.2021.00356"},{"key":"25_CR7","unstructured":"Chen, D., Dolan, W.B.: Collecting highly parallel data for paraphrase evaluation. In: Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, pp. 190\u2013200 (2011)"},{"key":"25_CR8","doi-asserted-by":"crossref","unstructured":"Chen, H., Xie, W., Vedaldi, A., Zisserman, A.: VGGSound: a large-scale audio-visual dataset. In: ICASSP 2020\u20132020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 721\u2013725. IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9053174"},{"key":"25_CR9","doi-asserted-by":"crossref","unstructured":"Chen, L., Srivastava, S., Duan, Z., Xu, C.: Deep cross-modal audio-visual generation. In: 2017 Proceedings of the on Thematic Workshops of ACM Multimedia, pp. 349\u2013357 (2017)","DOI":"10.1145\/3126686.3126723"},{"key":"25_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1007\/978-3-030-58577-8_7","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y-C Chen","year":"2020","unstructured":"Chen, Y.-C., et al.: UNITER: UNiversal image-TExt representation learning. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12375, pp. 104\u2013120. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58577-8_7"},{"key":"25_CR11","unstructured":"Cobbe, K., Klimov, O., Hesse, C., Kim, T., Schulman, J.: Quantifying generalization in reinforcement learning. In: International Conference on Machine Learning, pp. 1282\u20131289. PMLR (2019)"},{"key":"25_CR12","doi-asserted-by":"crossref","unstructured":"Cui, Y., Yang, G., Veit, A., Huang, X., Belongie, S.: Learning to evaluate image captioning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5804\u20135812 (2018)","DOI":"10.1109\/CVPR.2018.00608"},{"key":"25_CR13","unstructured":"Dhariwal, P., Jun, H., Payne, C., Kim, J.W., Radford, A., Sutskever, I.: Jukebox: a generative model for music. arXiv preprint arXiv:2005.00341 (2020)"},{"key":"25_CR14","unstructured":"Ding, M., et al.: CogView: mastering text-to-image generation via transformers. In: Advances in Neural Information Processing Systems, vol. 34 (2021)"},{"key":"25_CR15","unstructured":"Edwards, A., Sahni, H., Schroecker, Y., Isbell, C.: Imitating latent policies from observation. In: International Conference on Machine Learning, pp. 1755\u20131763. PMLR (2019)"},{"key":"25_CR16","unstructured":"Espeholt, L., et al.: IMPALA: scalable distributed deep-RL with importance weighted actor-learner architectures. In: International Conference on Machine Learning, pp. 1407\u20131416. PMLR (2018)"},{"key":"25_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"214","DOI":"10.1007\/978-3-030-58548-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"V Gabeur","year":"2020","unstructured":"Gabeur, V., Sun, C., Alahari, K., Schmid, C.: Multi-modal transformer for video retrieval. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12349, pp. 214\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58548-8_13"},{"issue":"2","key":"25_CR18","first-page":"23","volume":"12","author":"P Gage","year":"1994","unstructured":"Gage, P.: A new algorithm for data compression. C Users J. 12(2), 23\u201338 (1994)","journal-title":"C Users J."},{"key":"25_CR19","doi-asserted-by":"crossref","unstructured":"Gao, J., Sun, C., Yang, Z., Nevatia, R.: TALL: temporal activity localization via language query. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.563"},{"issue":"9","key":"25_CR20","doi-asserted-by":"publisher","first-page":"2045","DOI":"10.1109\/TMM.2017.2729019","volume":"19","author":"L Gao","year":"2017","unstructured":"Gao, L., Guo, Z., Zhang, H., Xu, X., Shen, H.T.: Video captioning with attention-based LSTM and semantic consistency. IEEE Trans. Multimed. 19(9), 2045\u20132055 (2017)","journal-title":"IEEE Trans. Multimed."},{"key":"25_CR21","doi-asserted-by":"crossref","unstructured":"Ge, S., et al.: Long video generation with time-agnostic VQGAN and time-sensitive transformer. arXiv preprint arXiv:2204.03638 (2022)","DOI":"10.1007\/978-3-031-19790-1_7"},{"key":"25_CR22","doi-asserted-by":"crossref","unstructured":"Gemmeke, J.F., et al.: AudioSet: an ontology and human-labeled dataset for audio events. In: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 776\u2013780. IEEE (2017)","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"25_CR23","doi-asserted-by":"crossref","unstructured":"Goyal, Y., Khot, T., Summers-Stay, D., Batra, D., Parikh, D.: Making the V in VQA matter: elevating the role of image understanding in visual question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6904\u20136913 (2017)","DOI":"10.1109\/CVPR.2017.670"},{"key":"25_CR24","unstructured":"Grauman, K., et al.: Ego4D: around the world in 3,000 hours of egocentric video. arXiv preprint arXiv:2110.07058 (2021)"},{"key":"25_CR25","doi-asserted-by":"crossref","unstructured":"Gupta, T., Schwenk, D., Farhadi, A., Hoiem, D., Kembhavi, A.: Imagine this! Scripts to compositions to videos. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 598\u2013613 (2018)","DOI":"10.1007\/978-3-030-01237-3_37"},{"key":"25_CR26","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"25_CR27","unstructured":"Huang, T.H., et al.: Visual storytelling. In: NAACL (2016)"},{"key":"25_CR28","unstructured":"Iashin, V., Rahtu, E.: Taming visually guided sound generation. arXiv preprint arXiv:2110.08791 (2021)"},{"key":"25_CR29","unstructured":"Igl, M., et al.: Generalization in reinforcement learning with selective noise injection and information bottleneck. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"25_CR30","doi-asserted-by":"crossref","unstructured":"Johnson, J., Hariharan, B., Van Der Maaten, L., Fei-Fei, L., Lawrence Zitnick, C., Girshick, R.: CLEVR: a diagnostic dataset for compositional language and elementary visual reasoning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2901\u20132910 (2017)","DOI":"10.1109\/CVPR.2017.215"},{"key":"25_CR31","doi-asserted-by":"crossref","unstructured":"Johnson, J., Karpathy, A., Fei-Fei, L.: DenseCap: fully convolutional localization networks for dense captioning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4565\u20134574 (2016)","DOI":"10.1109\/CVPR.2016.494"},{"key":"25_CR32","doi-asserted-by":"crossref","unstructured":"Johnson, J., et al.: Image retrieval using scene graphs. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3668\u20133678 (2015)","DOI":"10.1109\/CVPR.2015.7298990"},{"key":"25_CR33","doi-asserted-by":"crossref","unstructured":"Kahou, S.E., Michalski, V., Memisevic, R., Pal, C., Vincent, P.: RATM: recurrent attentive tracking model. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 1613\u20131622. IEEE (2017)","DOI":"10.1109\/CVPRW.2017.206"},{"key":"25_CR34","unstructured":"Kay, W., et al.: The kinetics human action video dataset. arXiv preprint arXiv:1705.06950 (2017)"},{"key":"25_CR35","unstructured":"Kim, C.D., Kim, B., Lee, H., Kim, G.: AudioCaps: generating captions for audios in the wild. In: NAACL-HLT (2019)"},{"key":"25_CR36","doi-asserted-by":"crossref","unstructured":"Koepke, A.S., Oncescu, A.M., Henriques, J., Akata, Z., Albanie, S.: Audio retrieval with natural language queries: a benchmark study. IEEE Trans. Multimed. (2022)","DOI":"10.21437\/Interspeech.2021-2227"},{"key":"25_CR37","doi-asserted-by":"crossref","unstructured":"Krishna, R., Hata, K., Ren, F., Fei-Fei, L., Niebles, J.C.: Dense-captioning events in videos. In: International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.83"},{"key":"25_CR38","doi-asserted-by":"crossref","unstructured":"Le, T.M., Le, V., Venkatesh, S., Tran, T.: Hierarchical conditional relation networks for video question answering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9972\u20139981 (2020)","DOI":"10.1109\/CVPR42600.2020.00999"},{"key":"25_CR39","doi-asserted-by":"crossref","unstructured":"Lei, J., et al.: Less is more: ClipBERT for video-and-language learning via sparse sampling. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7331\u20137341 (2021)","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"25_CR40","doi-asserted-by":"crossref","unstructured":"Lei, J., Yu, L., Bansal, M., Berg, T.L.: TVQA: localized, compositional video question answering. In: EMNLP (2018)","DOI":"10.18653\/v1\/D18-1167"},{"key":"25_CR41","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"447","DOI":"10.1007\/978-3-030-58589-1_27","volume-title":"Computer Vision \u2013 ECCV 2020","author":"J Lei","year":"2020","unstructured":"Lei, J., Yu, L., Berg, T.L., Bansal, M.: TVR: a large-scale dataset for video-subtitle moment retrieval. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12366, pp. 447\u2013463. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58589-1_27"},{"key":"25_CR42","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1007\/978-3-030-58577-8_8","volume-title":"Computer Vision \u2013 ECCV 2020","author":"X Li","year":"2020","unstructured":"Li, X., et al.: Oscar: object-semantics aligned pre-training for vision-language tasks. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12375, pp. 121\u2013137. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58577-8_8"},{"key":"25_CR43","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: StoryGAN: a sequential conditional GAN for story visualization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6329\u20136338 (2019)","DOI":"10.1109\/CVPR.2019.00649"},{"key":"25_CR44","doi-asserted-by":"crossref","unstructured":"Li, Y., Min, M., Shen, D., Carlson, D., Carin, L.: Video generation from text. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32 (2018)","DOI":"10.1609\/aaai.v32i1.12233"},{"key":"25_CR45","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"25_CR46","doi-asserted-by":"crossref","unstructured":"Liu, Y., Wang, X., Yuan, Y., Zhu, W.: Cross-modal dual learning for sentence-to-video generation. In: Proceedings of the 27th ACM International Conference on Multimedia, pp. 1239\u20131247 (2019)","DOI":"10.1145\/3343031.3350986"},{"key":"25_CR47","unstructured":"Mama, R., Tyndel, M.S., Kadhim, H., Clifford, C., Thurairatnam, R.: NWT: towards natural audio-to-video generation with representation learning. arXiv preprint arXiv:2106.04283 (2021)"},{"key":"25_CR48","doi-asserted-by":"crossref","unstructured":"Mazaheri, A., Shah, M.: Video generation from text employing latent path construction for temporal modeling. arXiv preprint arXiv:2107.13766 (2021)","DOI":"10.1109\/ICPR56361.2022.9956706"},{"key":"25_CR49","doi-asserted-by":"crossref","unstructured":"Miech, A., Alayrac, J.B., Smaira, L., Laptev, I., Sivic, J., Zisserman, A.: End-to-end learning of visual representations from uncurated instructional videos. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00990"},{"key":"25_CR50","doi-asserted-by":"crossref","unstructured":"Miech, A., Zhukov, D., Alayrac, J.B., Tapaswi, M., Laptev, I., Sivic, J.: HowTO100M: learning a text-video embedding by watching hundred million narrated video clips. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2630\u20132640 (2019)","DOI":"10.1109\/ICCV.2019.00272"},{"key":"25_CR51","doi-asserted-by":"crossref","unstructured":"Mittal, G., Marwah, T., Balasubramanian, V.N.: Sync-DRAW: automatic video generation using deep recurrent attentive architectures. In: Proceedings of the 25th ACM International Conference on Multimedia, pp. 1096\u20131104 (2017)","DOI":"10.1145\/3123266.3123309"},{"key":"25_CR52","doi-asserted-by":"crossref","unstructured":"Niu, Y., Tang, K., Zhang, H., Lu, Z., Hua, X.S., Wen, J.R.: Counterfactual VQA: a cause-effect look at language bias. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12700\u201312710 (2021)","DOI":"10.1109\/CVPR46437.2021.01251"},{"key":"25_CR53","unstructured":"Ordonez, V., Kulkarni, G., Berg, T.: Im2Text: describing images using 1 million captioned photographs. In: Advances in Neural Information Processing Systems, vol. 24 (2011)"},{"key":"25_CR54","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"25_CR55","unstructured":"Ramesh, A., et al.: Zero-shot text-to-image generation. In: International Conference on Machine Learning, pp. 8821\u20138831. PMLR (2021)"},{"key":"25_CR56","unstructured":"Reed, S., Akata, Z., Yan, X., Logeswaran, L., Schiele, B., Lee, H.: Generative adversarial text to image synthesis. In: International Conference on Machine Learning, pp. 1060\u20131069. PMLR (2016)"},{"key":"25_CR57","doi-asserted-by":"crossref","unstructured":"Rohrbach, A., Rohrbach, M., Tandon, N., Schiele, B.: A dataset for movie description. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 3202\u20133212 (2015)","DOI":"10.1109\/CVPR.2015.7298940"},{"key":"25_CR58","unstructured":"Sanh, V., Debut, L., Chaumond, J., Wolf, T.: DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108 (2019)"},{"key":"25_CR59","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"25_CR60","doi-asserted-by":"publisher","unstructured":"Sennrich, R., Haddow, B., Birch, A.: Neural machine translation of rare words with subword units. In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 1715\u20131725. Association for Computational Linguistics, Berlin, Germany (2016). https:\/\/doi.org\/10.18653\/v1\/P16-1162, https:\/\/aclanthology.org\/P16-1162","DOI":"10.18653\/v1\/P16-1162"},{"key":"25_CR61","doi-asserted-by":"crossref","unstructured":"Sharma, P., Ding, N., Goodman, S., Soricut, R.: Conceptual captions: a cleaned, hypernymed, image alt-text dataset for automatic image captioning. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 2556\u20132565 (2018)","DOI":"10.18653\/v1\/P18-1238"},{"key":"25_CR62","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"510","DOI":"10.1007\/978-3-319-46448-0_31","volume-title":"Computer Vision \u2013 ECCV 2016","author":"GA Sigurdsson","year":"2016","unstructured":"Sigurdsson, G.A., Varol, G., Wang, X., Farhadi, A., Laptev, I., Gupta, A.: Hollywood in homes: crowdsourcing data collection for activity understanding. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 510\u2013526. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_31"},{"key":"25_CR63","doi-asserted-by":"crossref","unstructured":"Singh, A., et al.: FLAVA: a foundational language and vision alignment model. arXiv preprint arXiv:2112.04482 (2021)","DOI":"10.1109\/CVPR52688.2022.01519"},{"key":"25_CR64","doi-asserted-by":"crossref","unstructured":"Srinivasan, K., Raman, K., Chen, J., Bendersky, M., Najork, M.: WIT: Wikipedia-based image text dataset for multimodal multilingual machine learning. In: SIGIR (2021)","DOI":"10.1145\/3404835.3463257"},{"key":"25_CR65","unstructured":"Van Den Oord, A., Vinyals, O., et al.: Neural discrete representation learning. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"25_CR66","doi-asserted-by":"crossref","unstructured":"Xie, S., Sun, C., Huang, J., Tu, Z., Murphy, K.: Rethinking spatiotemporal feature learning: speed-accuracy trade-offs in video classification. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 305\u2013321 (2018)","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"25_CR67","doi-asserted-by":"crossref","unstructured":"Xu, C., Hsieh, S.H., Xiong, C., Corso, J.J.: Can humans fly? Action understanding with multiple classes of actors. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2264\u20132273 (2015)","DOI":"10.1109\/CVPR.2015.7298839"},{"key":"25_CR68","doi-asserted-by":"crossref","unstructured":"Xu, J., Mei, T., Yao, T., Rui, Y.: MSR-VTT: a large video description dataset for bridging video and language. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5288\u20135296 (2016)","DOI":"10.1109\/CVPR.2016.571"},{"key":"25_CR69","doi-asserted-by":"crossref","unstructured":"Xue, H., et al.: Advancing high-resolution video-language representation with large-scale video transcriptions. In: International Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.00498"},{"key":"25_CR70","unstructured":"Yan, W., Zhang, Y., Abbeel, P., Srinivas, A.: VideoGPT: video generation using VQ-VAE and transformers (2021)"},{"key":"25_CR71","doi-asserted-by":"crossref","unstructured":"Yang, Z., Gong, B., Wang, L., Huang, W., Yu, D., Luo, J.: A fast and accurate one-stage approach to visual grounding. In: The IEEE International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00478"},{"key":"25_CR72","doi-asserted-by":"crossref","unstructured":"You, Q., Jin, H., Wang, Z., Fang, C., Luo, J.: Image captioning with semantic attention. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4651\u20134659 (2016)","DOI":"10.1109\/CVPR.2016.503"},{"key":"25_CR73","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1162\/tacl_a_00166","volume":"2","author":"P Young","year":"2014","unstructured":"Young, P., Lai, A., Hodosh, M., Hockenmaier, J.: From image descriptions to visual denotations: new similarity metrics for semantic inference over event descriptions. Trans. Assoc. Comput. Linguist. 2, 67\u201378 (2014)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"25_CR74","unstructured":"Yuan, L., et al.: Florence: a new foundation model for computer vision. arXiv preprint arXiv:2111.11432 (2021)"},{"key":"25_CR75","doi-asserted-by":"crossref","unstructured":"Zeng, R., Xu, H., Huang, W., Chen, P., Tan, M., Gan, C.: Dense regression network for video grounding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10287\u201310296 (2020)","DOI":"10.1109\/CVPR42600.2020.01030"},{"key":"25_CR76","doi-asserted-by":"crossref","unstructured":"Zhang, P., et al.: VinVL: revisiting visual representations in vision-language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5579\u20135588 (2021)","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"25_CR77","doi-asserted-by":"crossref","unstructured":"Zhang, S., Peng, H., Fu, J., Lu, Y., Luo, J.: Multi-scale 2D temporal adjacent networks for moment localization with natural language. TPAMI (2021)","DOI":"10.1609\/aaai.v34i07.6984"},{"key":"25_CR78","doi-asserted-by":"crossref","unstructured":"Zhou, L., Palangi, H., Zhang, L., Hu, H., Corso, J., Gao, J.: Unified vision-language pre-training for image captioning and VQA. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 13041\u201313049 (2020)","DOI":"10.1609\/aaai.v34i07.7005"},{"key":"25_CR79","doi-asserted-by":"crossref","unstructured":"Zhou, L., Xu, C., Corso, J.J.: Towards automatic learning of procedures from web instructional videos. In: Thirty-Second AAAI Conference on Artificial Intelligence (2018)","DOI":"10.1609\/aaai.v32i1.12342"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-20074-8_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,11]],"date-time":"2023-03-11T21:50:59Z","timestamp":1678571459000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20074-8_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031200731","9783031200748"],"references-count":79,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20074-8_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"12 November 2022","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":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","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":"1645","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":"28% - 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":"3.21","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":"3.91","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)"}}]}}