{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,22]],"date-time":"2026-10-22T04:42:55Z","timestamp":1792644175847,"version":"4.5.0"},"publisher-location":"Cham","reference-count":81,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726293","type":"print"},{"value":"9783031726309","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,12,5]],"date-time":"2024-12-05T00:00:00Z","timestamp":1733356800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,5]],"date-time":"2024-12-05T00:00:00Z","timestamp":1733356800000},"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\/978-3-031-72630-9_18","type":"book-chapter","created":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T05:18:41Z","timestamp":1733289521000},"page":"303-321","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Siamese Vision Transformers are Scalable Audio-Visual Learners"],"prefix":"10.1007","author":[{"given":"Yan-Bo","family":"Lin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gedas","family":"Bertasius","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,12,5]]},"reference":[{"key":"18_CR1","unstructured":"Akbari, H., et al.: VATT: transformers for multimodal self-supervised learning from raw video, audio and text. In: NeurIPS (2021)"},{"key":"18_CR2","unstructured":"Alayrac, J.-B., et al.: Self-supervised multimodal versatile networks. In: NeurIPS (2020)"},{"key":"18_CR3","unstructured":"Alwassel, H., Mahajan, D., Torresani, L., Ghanem, B., Tran, D.: Self-supervised learning by cross-modal audio-video clustering. In: NeurIPS (2020)"},{"key":"18_CR4","doi-asserted-by":"crossref","unstructured":"Arandjelovic, R., Zisserman, A.: Look, listen and learn. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.73"},{"key":"18_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"451","DOI":"10.1007\/978-3-030-01246-5_27","volume-title":"Computer Vision \u2013 ECCV 2018","author":"R Arandjelovi\u0107","year":"2018","unstructured":"Arandjelovi\u0107, R., Zisserman, A.: Objects that sound. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11205, pp. 451\u2013466. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01246-5_27"},{"key":"18_CR6","unstructured":"Asano, Y.M., Patrick, M., Rupprecht, C., Vedaldi, A.: Labelling unlabelled videos from scratch with multi-modal self-supervision. In: NeurIPS (2020)"},{"key":"18_CR7","doi-asserted-by":"crossref","unstructured":"Aytar, Y., Vondrick, C., Torralba, A.: SoundNet: learning sound representations from unlabeled video. In: NeurIPS (2016)","DOI":"10.1109\/CVPR.2016.18"},{"key":"18_CR8","doi-asserted-by":"crossref","unstructured":"Baade, A., Peng, P., Harwath, D.: MAE-AST: masked autoencoding audio spectrogram transformer. In INTEERSPEECH (2022)","DOI":"10.21437\/Interspeech.2022-10961"},{"key":"18_CR9","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"348","DOI":"10.1007\/978-3-031-19836-6_20","volume-title":"ECCV 2022","author":"R Bachmann","year":"2022","unstructured":"Bachmann, R., et al.: MultiMAE: multi-modal multi-task masked autoencoders. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13697, pp. 348\u2013367. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19836-6_20"},{"key":"18_CR10","unstructured":"Baevski, A., Hsu, W.-N., Xu, Q., Babu, A., Gu, J., Auli, M.: Data2vec: a general framework for self-supervised learning in speech, vision and language. In: ICML (2022)"},{"key":"18_CR11","doi-asserted-by":"crossref","unstructured":"Chen, H., Xie, W., Vedaldi, A., Zisserman, A.: VGG-sound: a large-scale audio-visual dataset. In: ICASSP (2020)","DOI":"10.1109\/ICASSP40776.2020.9053174"},{"key":"18_CR12","unstructured":"Chen, X., et\u00a0al.: PaLI: a jointly-scaled multilingual language-image model. In: ICLR (2023)"},{"key":"18_CR13","doi-asserted-by":"crossref","unstructured":"Chen, Y., Xian, Y., Koepke, A., Shan, Y., Akata, Z.: Distilling audio-visual knowledge by compositional contrastive learning. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00694"},{"key":"18_CR14","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"431","DOI":"10.1007\/978-3-031-19830-4_25","volume-title":"ECCV 2022","author":"H Cheng","year":"2022","unstructured":"Cheng, H., Liu, Z., Zhou, H., Qian, C., Wu, W., Wang, L.: Joint-modal label denoising for weakly-supervised audio-visual video parsing. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13694, pp. 431\u2013448. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19830-4_25"},{"key":"18_CR15","unstructured":"Dai, Y., et al.: One model, multiple modalities: a sparsely activated approach for text, sound, image, video and code. arXiv Preprint (2022)"},{"key":"18_CR16","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: ICLR (2021)"},{"key":"18_CR17","doi-asserted-by":"crossref","unstructured":"Fang, Y., et al.: EVA: exploring the limits of masked visual representation learning at scale. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01855"},{"key":"18_CR18","doi-asserted-by":"crossref","unstructured":"Fayek, H.M., Kumar, A.: Large scale audiovisual learning of sounds with weakly labeled data. In: IJCAI (2020)","DOI":"10.24963\/ijcai.2020\/78"},{"key":"18_CR19","doi-asserted-by":"crossref","unstructured":"Gemmeke, J.F., et al.: Audio set: an ontology and human-labeled dataset for audio events. In: ICASSP (2017)","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"18_CR20","doi-asserted-by":"crossref","unstructured":"Georgescu, M.-I., Fonseca, E., Ionescu, R.T., Lucic, M., Schmid, C., Arnab, A.: Audiovisual masked autoencoders. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01479"},{"key":"18_CR21","doi-asserted-by":"crossref","unstructured":"Girdhar, R., El-Nouby, A., Singh, M., Alwala, K.V., Joulin, A., Misra, I.: OmniMAE: single model masked pretraining on images and videos. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01003"},{"key":"18_CR22","doi-asserted-by":"crossref","unstructured":"Girdhar, R., Singh, M., Ravi, N., van der Maaten, L., Joulin, A., Misra, I.: OMNIVORE: a single model for many visual modalities. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01563"},{"key":"18_CR23","doi-asserted-by":"crossref","unstructured":"Gong, Y., Chung, Y.-A., Glass, J.: AST: audio spectrogram transformer. In: INTEERSPEECH (2021)","DOI":"10.21437\/Interspeech.2021-698"},{"key":"18_CR24","doi-asserted-by":"crossref","unstructured":"Gong, Y., Chung, Y.-A., Glass, J.: PSLA: improving audio tagging with pretraining, sampling, labeling, and aggregation. TASLP (2021)","DOI":"10.1109\/TASLP.2021.3120633"},{"key":"18_CR25","doi-asserted-by":"publisher","first-page":"2437","DOI":"10.1109\/LSP.2022.3224688","volume":"29","author":"Y Gong","year":"2022","unstructured":"Gong, Y., Liu, A.H., Rouditchenko, A., Glass, J.: UAVM: a unified model for audio-visual learning. IEEE Signal Process. Lett. 29, 2437\u20132441 (2022)","journal-title":"IEEE Signal Process. Lett."},{"key":"18_CR26","unstructured":"Gong, Y., Rouditchenko, A., Liu, D.H., Karlinsky, L., Kuehne, H., Glass, J.: Contrastive audio-visual masked autoencoder. In: ICLR (2023)"},{"key":"18_CR27","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"18_CR28","unstructured":"Huang, P.-Y., et al.: MAViL: masked audio-video learners. In: NeurIPS (2023)"},{"key":"18_CR29","unstructured":"Jaegle, A., et\u00a0al.: Perceiver IO: a general architecture for structured inputs & outputs. In: ICLR (2022)"},{"key":"18_CR30","unstructured":"Jaegle, A., Gimeno, F., Brock, A., Vinyals, O., Zisserman, A., Carreira, J.: Perceiver: general perception with iterative attention. In: ICML (2021)"},{"key":"18_CR31","doi-asserted-by":"crossref","unstructured":"Jenni, S., Black, A., Collomosse, J.: Audio-visual contrastive learning with temporal self-supervision. In: AAAI (2023)","DOI":"10.1609\/aaai.v37i7.25967"},{"key":"18_CR32","unstructured":"Lee, J.-T., Jain, M., Park, H., Yun, S.: Cross-attentional audio-visual fusion for weakly-supervised action localization. In: ICLR (2021)"},{"key":"18_CR33","doi-asserted-by":"crossref","unstructured":"Lee, S., et al.: ACAV100M: automatic curation of large-scale datasets for audio-visual video representation learning. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01011"},{"key":"18_CR34","doi-asserted-by":"crossref","unstructured":"Li, G., Wei, Y., Tian, Y., Xu, C., Wen, J.-R., Hu, D.: Learning to answer questions in dynamic audio-visual scenarios. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01852"},{"key":"18_CR35","doi-asserted-by":"crossref","unstructured":"Li, Y., Fan, H., Hu, R., Feichtenhofer, C., He, K.: Scaling language-image pre-training via masking. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.02240"},{"key":"18_CR36","unstructured":"Li, Z., et\u00a0al.: MST: masked self-supervised transformer for visual representation. In: NeurIPS (2021)"},{"key":"18_CR37","unstructured":"Likhosherstov, V., et al.: PolyViT: co-training vision transformers on images, videos and audio. arXiv Preprint (2021)"},{"key":"18_CR38","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"413","DOI":"10.1007\/978-3-031-19830-4_24","volume-title":"ECCV 2022","author":"YB Lin","year":"2022","unstructured":"Lin, Y.B., Lei, J., Bansal, M., Bertasius, G.: EclipSE: efficient long-range video retrieval using sight and sound. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13694, pp. 413\u2013430. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19830-4_24"},{"key":"18_CR39","doi-asserted-by":"crossref","unstructured":"Lin, Y.-B., Sung, Y.-L., Lei, J., Bansal, M., Bertasius, G.: Vision transformers are parameter-efficient audio-visual learners. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00228"},{"key":"18_CR40","unstructured":"Lin, Y.-B., Tseng, H.-Y., Lee, H.-Y., Lin, Y.-Y., Yang, M.-H.: Exploring cross-video and cross-modality signals for weakly-supervised audio-visual video parsing. In: NeurIPS (2021)"},{"key":"18_CR41","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"274","DOI":"10.1007\/978-3-030-69544-6_17","volume-title":"Computer Vision \u2013 ACCV 2020","author":"Y-B Lin","year":"2021","unstructured":"Lin, Y.-B., Wang, Y.-C.F.: Audiovisual transformer with instance attention for audio-visual event localization. In: Ishikawa, H., Liu, C.-L., Pajdla, T., Shi, J. (eds.) ACCV 2020. LNCS, vol. 12627, pp. 274\u2013290. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-69544-6_17"},{"key":"18_CR42","unstructured":"Liu, X., Zhou, J., Kong, T., Lin, X., Ji, R.: Exploring target representations for masked autoencoders. arXiv Preprint (2022)"},{"key":"18_CR43","unstructured":"Ma, S., Zeng, Z., McDuff, D., Song, Y.: Active contrastive learning of audio-visual video representations. In: ICLR (2021)"},{"key":"18_CR44","unstructured":"Ma, S., Zeng, Z., McDuff, D., Song, Y.: Contrastive learning of global and local audio-visual representations. In: NeurIPS (2021)"},{"key":"18_CR45","doi-asserted-by":"crossref","unstructured":"Mahmud, T., Marculescu, D.: AVE-CLIP: audioclip-based multi-window temporal transformer for audio visual event localization. In: WACV (2023)","DOI":"10.1109\/WACV56688.2023.00513"},{"key":"18_CR46","unstructured":"Mo, S., Morgado, P.: A unified audio-visual learning framework for localization, separation, and recognition. In: ICML (2023)"},{"key":"18_CR47","doi-asserted-by":"crossref","unstructured":"Mo, S., Pian, W., Tian, Y.: Class-incremental grouping network for continual audio-visual learning. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00716"},{"key":"18_CR48","unstructured":"Mo, S., Tian, Y.: Multi-modal grouping network for weakly-supervised audio-visual video parsing. In: NeurIPS (2022)"},{"key":"18_CR49","doi-asserted-by":"crossref","unstructured":"Morgado, P., Misra, I., Vasconcelos, N.: Robust audio-visual instance discrimination. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01274"},{"key":"18_CR50","doi-asserted-by":"crossref","unstructured":"Morgado, P., Vasconcelos, N., Misra, I.: Audio-visual instance discrimination with cross-modal agreement. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01274"},{"key":"18_CR51","unstructured":"Mustafa, B., Riquelme, C., Puigcerver, J., Jenatton, R., Houlsby, N.: Multimodal contrastive learning with limoe: the language-image mixture of experts. In: NeurIPS (2022)"},{"key":"18_CR52","unstructured":"Nagrani, A., Yang, S., Arnab, A., Jansen, A., Schmid, C., Sun, C.: Attention bottlenecks for multimodal fusion. In: NeurIPS (2021)"},{"key":"18_CR53","unstructured":"van\u00a0den Oord, A., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv Preprint (2018)"},{"key":"18_CR54","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"639","DOI":"10.1007\/978-3-030-01231-1_39","volume-title":"Computer Vision \u2013 ECCV 2018","author":"A Owens","year":"2018","unstructured":"Owens, A., Efros, A.A.: Audio-visual scene analysis with self-supervised multisensory features. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11210, pp. 639\u2013658. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01231-1_39"},{"key":"18_CR55","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"801","DOI":"10.1007\/978-3-319-46448-0_48","volume-title":"Computer Vision \u2013 ECCV 2016","author":"A Owens","year":"2016","unstructured":"Owens, A., Wu, J., McDermott, J.H., Freeman, W.T., Torralba, A.: Ambient sound provides supervision for visual learning. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 801\u2013816. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_48"},{"key":"18_CR56","doi-asserted-by":"crossref","unstructured":"Ramaswamy, J.: What makes the sound?: a dual-modality interacting network for audio-visual event localization. In: ICASSP (2020)","DOI":"10.1109\/ICASSP40776.2020.9053895"},{"key":"18_CR57","doi-asserted-by":"crossref","unstructured":"Ramaswamy, J., Das, S.: See the sound, hear the pixels. In: WACV (2020)","DOI":"10.1109\/WACV45572.2020.9093616"},{"key":"18_CR58","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"689","DOI":"10.1007\/978-3-031-19830-4_39","volume-title":"ECCV 2022","author":"V Rao","year":"2022","unstructured":"Rao, V., Khalil, M.I., Li, H., Dai, P., Lu, J.: Dual perspective network for audio-visual event localization. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13694, pp. 689\u2013704. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19830-4_39"},{"key":"18_CR59","unstructured":"Recasens, A., et\u00a0al.: Zorro: the masked multimodal transformer. arXiv Preprint (2023)"},{"key":"18_CR60","unstructured":"Shi, B., Hsu, W.-N., Lakhotia, K., Mohamed, A.: Learning audio-visual speech representation by masked multimodal cluster prediction. In: ICLR (2022)"},{"key":"18_CR61","doi-asserted-by":"crossref","unstructured":"Shvetsova, N., et al.: Everything at once\u2013multi-modal fusion transformer for video retrieval. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01939"},{"key":"18_CR62","unstructured":"Tang, Z., Cho, J., Nie, Y., Bansal, M.: TVLT: textless vision-language transformer. In NeurIPS (2022)"},{"key":"18_CR63","doi-asserted-by":"crossref","unstructured":"Teney, D., Abbasnejad, E., Lucey, S., Van\u00a0den Hengel, A.: Evading the simplicity bias: training a diverse set of models discovers solutions with superior OOD generalization. In: CVPR 2022","DOI":"10.1109\/CVPR52688.2022.01626"},{"key":"18_CR64","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1007\/978-3-030-58580-8_26","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Tian","year":"2020","unstructured":"Tian, Y., Li, D., Xu, C.: Unified multisensory perception: weakly-supervised audio-visual video\u00a0parsing. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12348, pp. 436\u2013454. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58580-8_26"},{"key":"18_CR65","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"252","DOI":"10.1007\/978-3-030-01216-8_16","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Y Tian","year":"2018","unstructured":"Tian, Y., Shi, J., Li, B., Duan, Z., Xu, C.: Audio-visual event localization in unconstrained videos. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11206, pp. 252\u2013268. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01216-8_16"},{"key":"18_CR66","doi-asserted-by":"crossref","unstructured":"Tschannen, M., Mustafa, B., Houlsby, N.: CLIPPO: image-and-language understanding from pixels only. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01059"},{"key":"18_CR67","first-page":"2579","volume":"9","author":"L Van der Maaten","year":"2008","unstructured":"Van der Maaten, L., Hinton, G.: Visualizing data using t-SNE. JMLR 9, 2579\u20132605 (2008)","journal-title":"Visualizing data using t-SNE. JMLR"},{"key":"18_CR68","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1007\/978-3-031-20083-0_15","volume-title":"ECCV 2022","author":"T Wad","year":"2022","unstructured":"Wad, T., Sun, Q., Pranata, S., Jayashree, K., Zhang, H.: Equivariance and invariance inductive bias for learning from insufficient data. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13671, pp. 241\u2013258. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20083-0_15"},{"key":"18_CR69","unstructured":"Wang, P., et al.: One-peace: exploring one general representation model toward unlimited modalities. arXiv Preprint (2023)"},{"key":"18_CR70","doi-asserted-by":"crossref","unstructured":"Wang, W., Tran, D., Feiszli, M.: What makes training multi-modal classification networks hard? In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01271"},{"key":"18_CR71","doi-asserted-by":"crossref","unstructured":"Wei, C., Fan, H., Xie, S., Wu, C.-Y., Yuille, A., Feichtenhofer, C.: Masked feature prediction for self-supervised visual pre-training. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01426"},{"key":"18_CR72","doi-asserted-by":"crossref","unstructured":"Wu, Y., Yang, Y.: Exploring heterogeneous clues for weakly-supervised audio-visual video parsing. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00138"},{"key":"18_CR73","unstructured":"Yu, W., Zhu, L., Yan, Y., Yang, Y.: Dual attention matching for audio-visual event localization. In: ICCV (2019)"},{"key":"18_CR74","doi-asserted-by":"crossref","unstructured":"Xia, Y., Zhao, Z.: Cross-modal background suppression for audio-visual event localization. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01936"},{"key":"18_CR75","unstructured":"Hu, X., et\u00a0al.: Masked autoencoders that listen. In: NeurIPS (2022)"},{"key":"18_CR76","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: CVPR (2016)","DOI":"10.1109\/CVPR.2016.571"},{"key":"18_CR77","doi-asserted-by":"crossref","unstructured":"Xuan, H., Zhang, Z., Chen, S., Yang, J., Yan, Y.: Cross-modal attention network for temporal inconsistent audio-visual event localization. In: AAAI (2020)","DOI":"10.1609\/aaai.v34i01.5361"},{"key":"18_CR78","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1007\/978-3-031-19812-0_5","volume-title":"ECCV 2022","author":"H You","year":"2022","unstructured":"You, H., et al.: Learning visual representation from modality-shared contrastive language-image pre-training. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13687, pp. 69\u201387. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19812-0_5"},{"key":"18_CR79","unstructured":"Jiahui, Yu., Wang, Z., Vasudevan, V., Yeung, L., Seyedhosseini, M., Wu, Y.: CoCa: contrastive captioners are image-text foundation models. TMLR (2022)"},{"key":"18_CR80","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Doughty, H., Shao, L., Snoek, C.G.M.: Audio-adaptive activity recognition across video domains. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01342"},{"key":"18_CR81","doi-asserted-by":"crossref","unstructured":"Zhong, Y., Tang, H., Chen, J.-K., Wang, Y.-X.: Contrastive learning relies more on spatial inductive bias than supervised learning: an empirical study. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01496"}],"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\/978-3-031-72630-9_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T06:38:42Z","timestamp":1768199922000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72630-9_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,5]]},"ISBN":["9783031726293","9783031726309"],"references-count":81,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72630-9_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,5]]},"assertion":[{"value":"5 December 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"}}]}}