{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T06:00:17Z","timestamp":1742968817899,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":63,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819609079"},{"type":"electronic","value":"9789819609086"}],"license":[{"start":{"date-parts":[[2024,12,7]],"date-time":"2024-12-07T00:00:00Z","timestamp":1733529600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,7]],"date-time":"2024-12-07T00:00:00Z","timestamp":1733529600000},"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\/978-981-96-0908-6_13","type":"book-chapter","created":{"date-parts":[[2024,12,6]],"date-time":"2024-12-06T19:24:08Z","timestamp":1733513048000},"page":"220-238","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Capture Concept Through Comparison: Vision-and-Language Representation Learning with\u00a0Intrinsic Information Mining"],"prefix":"10.1007","author":[{"given":"Yun-Zhu","family":"Song","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi-Syuan","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tzu-Ling","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bei","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianlong","family":"Fu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hong-Han","family":"Shuai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,7]]},"reference":[{"key":"13_CR1","doi-asserted-by":"crossref","unstructured":"Archer, E.J.: Chapter 3 - the psychological nature of concepts. In: Analyses of Concept Learning. Academic Press (1966)","DOI":"10.1016\/B978-1-4832-3127-3.50008-0"},{"key":"13_CR2","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Proceedings of the European Conference on Computer Vision (ECCV) (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"13_CR3","doi-asserted-by":"crossref","unstructured":"Cascante-Bonilla, P., Shehada, K., Smith, J.S., Doveh, S., Kim, D., Panda, R., Varol, G., Oliva, A., Ordonez, V., Feris, R., Karlinsky, L.: Going beyond nouns with vision & language models using synthetic data. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2023)","DOI":"10.1109\/ICCV51070.2023.01844"},{"key":"13_CR4","unstructured":"Chen, X., Fang, H., Lin, T.Y., Vedantam, R., Gupta, S., Doll\u00e1r, P., Zitnick, C.L.: Microsoft coco captions: Data collection and evaluation server. arXiv:1504.00325 (2015)"},{"key":"13_CR5","doi-asserted-by":"crossref","unstructured":"Chen, Y.C., Li, L., Yu, L., Kholy, A.E., Ahmed, F., Gan, Z., Cheng, Y., Liu, J.: Uniter: Universal image-text representation learning. In: Proceedings of the European Conference on Computer Vision (ECCV) (2020)","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"13_CR6","unstructured":"Dou, Z.Y., Kamath, A., Gan, Z., Zhang, P., Wang, J., Li, L., Liu, Z., Liu, C., LeCun, Y., Peng, N., Gao, J., Wang, L.: Coarse-to-fine vision-language pre-training with fusion in the backbone. In: Advances in Neural Information Processing Systems (NeurIPS) (2022)"},{"key":"13_CR7","doi-asserted-by":"crossref","unstructured":"Dou, Z.Y., Xu, Y., Gan, Z., Wang, J., Wang, S., Wang, L., Zhu, C., Zhang, P., Yuan, L., Peng, N., Liu, Z., Zeng, M.: An empirical study of training end-to-end vision-and-language transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01763"},{"key":"13_CR8","doi-asserted-by":"crossref","unstructured":"Doveh, S., Arbelle, A., Harary, S., Schwartz, E., Herzig, R., Giryes, R., Feris, R., Panda, R., Ullman, S., Karlinsky, L.: Teaching structured vision & language concepts to vision & language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.00261"},{"key":"13_CR9","doi-asserted-by":"crossref","unstructured":"Duan, J., Chen, L., Tran, S., Yang, J., Xu, Y., Zeng, B., Chilimbi, T.: Multi-modal alignment using representation codebook. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01520"},{"key":"13_CR10","doi-asserted-by":"crossref","unstructured":"Fang, Z., Wang, J., Hu, X., Liang, L., Gan, Z., Wang, L., Yang, Y., Liu, Z.: Injecting semantic concepts into end-to-end image captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01748"},{"key":"13_CR11","unstructured":"Gan, Z., Chen, Y.C., Li, L., Zhu, C., Cheng, Y., Liu, J.: Large-scale adversarial training for vision-and-language representation learning. In: Advances in Neural Information Processing Systems (NeurIPS) (2020)"},{"key":"13_CR12","unstructured":"Gao, Y., Liu, J., Xu, Z., Zhang, J., Li, K., Ji, R., Shen, C.: Pyramidclip: Hierarchical feature alignment for vision-language model pretraining. In: Advances in Neural Information Processing Systems (NeurIPS) (2022)"},{"key":"13_CR13","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\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.670"},{"key":"13_CR14","unstructured":"Gutmann, M., Hyv\u00e4rinen, A.: Noise-contrastive estimation: A new estimation principle for unnormalized statistical models. In: Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics (AISTATS). PMLR (2010)"},{"key":"13_CR15","unstructured":"Gutmann, M.U., Hyv\u00e4rinen, A.: Noise-contrastive estimation of unnormalized statistical models, with applications to natural image statistics. Journal of Machine Learning Research (JMLR) (2012)"},{"key":"13_CR16","unstructured":"Hu, E.J., yelong shen, Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., Wang, L., Chen, W.: LoRA: Low-rank adaptation of large language models. In: International Conference on Learning Representations (ICLR) (2022)"},{"key":"13_CR17","doi-asserted-by":"crossref","unstructured":"Huang, Z., Zeng, Z., Huang, Y., Liu, B., Fu, D., Fu, J.: Seeing out of the box: End-to-end pre-training for vision-language representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.01278"},{"key":"13_CR18","unstructured":"Huang, Z., Zeng, Z., Liu, B., Fu, D., Fu, J.: Pixel-bert: Aligning image pixels with text by deep multi-modal transformers. arXiv:2004.00849 (2020)"},{"key":"13_CR19","doi-asserted-by":"crossref","unstructured":"Jiang, C., Xu, H., Ye, W., Ye, Q., Li, C., Yan, M., Bi, B., Zhang, S., Zhang, J., Huang, F.: Copa: Efficient vision-language pre-training through collaborative object-and patch-text alignment. In: Proceedings of the 31th ACM International Conference on Multimedia (2023)","DOI":"10.1145\/3581783.3611826"},{"key":"13_CR20","doi-asserted-by":"crossref","unstructured":"J\u00e4rvelin, A., J\u00e4rvelin, A., J\u00e4rvelin, K.: s-grams: Defining generalized n-grams for information retrieval. Information Processing & Management (IPM) (2007)","DOI":"10.1016\/j.ipm.2006.09.016"},{"key":"13_CR21","doi-asserted-by":"crossref","unstructured":"Kamath, A., Singh, M., LeCun, Y., Synnaeve, G., Misra, I., Carion, N.: Mdetr-modulated detection for end-to-end multi-modal understanding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"13_CR22","doi-asserted-by":"crossref","unstructured":"Kamath, A., Clark, C., Gupta, T., Kolve, E., Hoiem, D., Kembhavi, A.: Webly supervised concept expansion for general purpose vision models. In: Proceedings of the European Conference on Computer Vision (ECCV) (2022)","DOI":"10.1007\/978-3-031-20059-5_38"},{"key":"13_CR23","doi-asserted-by":"crossref","unstructured":"Kazemzadeh, S., Ordonez, V., Matten, M., Berg, T.: ReferItGame: Referring to objects in photographs of natural scenes. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) (2014)","DOI":"10.3115\/v1\/D14-1086"},{"key":"13_CR24","doi-asserted-by":"crossref","unstructured":"Khan, Z., Vijay\u00a0Kumar, B.G., Yu, X., Schulter, S., Chandraker, M., Fu, Y.: Single-stream multi-level alignment for vision-language pretraining. In: Proceedings of the European Conference on Computer Vision (ECCV) (2022)","DOI":"10.1007\/978-3-031-20059-5_42"},{"key":"13_CR25","unstructured":"Kim, W., Son, B., Kim, I.: Vilt: Vision-and-language transformer without convolution or region supervision. In: International Conference on Machine Learning (ICML) (2021)"},{"key":"13_CR26","unstructured":"Kong, L., de\u00a0Masson\u00a0d\u2019Autume, C., Yu, L., Ling, W., Dai, Z., Yogatama, D.: A mutual information maximization perspective of language representation learning. In: International Conference on Learning Representations (ICLR) (2020)"},{"key":"13_CR27","doi-asserted-by":"crossref","unstructured":"Krishna, R., Zhu, Y., Groth, O., Johnson, J., Hata, K., Kravitz, J., Chen, S., Kalantidis, Y., Li, L.J., Shamma, D.A., et\u00a0al.: Visual genome: Connecting language and vision using crowdsourced dense image annotations. International journal of computer vision (IJCV) (2017)","DOI":"10.1007\/s11263-016-0981-7"},{"key":"13_CR28","doi-asserted-by":"crossref","unstructured":"Li, D., Li, J., Li, H., Niebles, J.C., Hoi, S.C.: Align and prompt: Video-and-language pre-training with entity prompts. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.00490"},{"key":"13_CR29","unstructured":"Li, J., Selvaraju, R., Gotmare, A., Joty, S., Xiong, C., Hoi, S.C.H.: Align before fuse: Vision and language representation learning with momentum distillation. In: Advances in Neural Information Processing Systems (NeurIPS) (2021)"},{"key":"13_CR30","doi-asserted-by":"crossref","unstructured":"Li*, L.H., Zhang*, P., Zhang*, H., Yang, J., Li, C., Zhong, Y., Wang, L., Yuan, L., Zhang, L., Hwang, J.N., Chang, K.W., Gao, J.: Grounded language-image pre-training. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"13_CR31","doi-asserted-by":"crossref","unstructured":"Li, W., Gao, C., Niu, G., Xiao, X., Liu, H., Liu, J., Wu, H., Wang, H.: UNIMO: Towards unified-modal understanding and generation via cross-modal contrastive learning. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) (2021)","DOI":"10.18653\/v1\/2021.acl-long.202"},{"key":"13_CR32","doi-asserted-by":"crossref","unstructured":"Li, X., Yin, X., Li, C., Hu, X., Zhang, P., Zhang, L., Wang, L., Hu, H., Dong, L., Wei, F., Choi, Y., Gao, J.: Oscar: Object-semantics aligned pre-training for vision-language tasks. Proceedings of the European Conference on Computer Vision (ECCV) (2020)","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"13_CR33","volume-title":"Uni-eden: Universal encoder-decoder network by multi-granular vision-language pre-training","author":"Y Li","year":"2022","unstructured":"Li, Y., Fan, J., Pan, Y., Yao, T., Lin, W., Mei, T.: Uni-eden: Universal encoder-decoder network by multi-granular vision-language pre-training. Communications, and Applications, ACM Transactions on Multimedia Computing (2022)"},{"key":"13_CR34","doi-asserted-by":"crossref","unstructured":"Li, Z., Fan, Z., Tou, H., Chen, J., Wei, Z., Huang, X.: Mvptr: Multi-level semantic alignment for vision-language pre-training via multi-stage learning. In: Proceedings of the 30th ACM International Conference on Multimedia (2022)","DOI":"10.1145\/3503161.3548341"},{"key":"13_CR35","unstructured":"Liu, B., Rosenfeld, E., Ravikumar, P.K., Risteski, A.: Analyzing and improving the optimization landscape of noise-contrastive estimation. In: International Conference on Learning Representations (ICLR) (2022)"},{"key":"13_CR36","doi-asserted-by":"crossref","unstructured":"Liu, Y., Wu, C., Tseng, S.Y., Lal, V., He, X., Duan, N.: KD-VLP: Improving end-to-end vision-and-language pretraining with object knowledge distillation. In: Findings of the Association for Computational Linguistics: NAACL 2022 (2022)","DOI":"10.18653\/v1\/2022.findings-naacl.119"},{"key":"13_CR37","doi-asserted-by":"crossref","unstructured":"Mao, J., Huang, J., Toshev, A., Camburu, O., Yuille, A.L., Murphy, K.: Generation and comprehension of unambiguous object descriptions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.9"},{"key":"13_CR38","unstructured":"Oord, A.v.d., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv:1807.03748 (2018)"},{"key":"13_CR39","unstructured":"Ordonez, V., Kulkarni, G., Berg, T.: Im2text: Describing images using 1 million captioned photographs. In: Advances in Neural Information Processing Systems (NeurIPS) (2011)"},{"key":"13_CR40","doi-asserted-by":"crossref","unstructured":"Plummer, B.A., Wang, L., Cervantes, C.M., Caicedo, J.C., Hockenmaier, J., Lazebnik, S.: Flickr30k entities: Collecting region-to-phrase correspondences for richer image-to-sentence models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2015)","DOI":"10.1109\/ICCV.2015.303"},{"key":"13_CR41","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., Krueger, G., Sutskever, I.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning (ICML) (2021)"},{"key":"13_CR42","unstructured":"Rae, J.W., Borgeaud, S., Cai, T., Millican, K., Hoffmann, J., Song, F., Aslanides, J., Henderson, S., Ring, R., Young, S., et\u00a0al.: Scaling language models: Methods, analysis & insights from training gopher. arXiv:2112.11446 (2021)"},{"key":"13_CR43","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) (2018)","DOI":"10.18653\/v1\/P18-1238"},{"key":"13_CR44","unstructured":"Shen, S., Li, L.H., Tan, H., Bansal, M., Rohrbach, A., Chang, K.W., Yao, Z., Keutzer, K.: How much can CLIP benefit vision-and-language tasks? In: International Conference on Learning Representations (ICLR) (2022)"},{"key":"13_CR45","doi-asserted-by":"crossref","unstructured":"Singh, A., Hu, R., Goswami, V., Couairon, G., Galuba, W., Rohrbach, M., Kiela, D.: Flava: A foundational language and vision alignment model. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01519"},{"key":"13_CR46","unstructured":"Su, W., Zhu, X., Cao, Y., Li, B., Lu, L., Wei, F., Dai, J.: Vl-bert: Pre-training of generic visual-linguistic representations. In: International Conference on Learning Representations (ICLR) (2020)"},{"key":"13_CR47","doi-asserted-by":"crossref","unstructured":"Su, W., Zhu, X., Tao, C., Lu, L., Li, B., Huang, G., Qiao, Y., Wang, X., Zhou, J., Dai, J.: Towards all-in-one pre-training via maximizing multi-modal mutual information. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.01525"},{"key":"13_CR48","doi-asserted-by":"crossref","unstructured":"Suhr, A., Zhou, S., Zhang, A., Zhang, I., Bai, H., Artzi, Y.: A corpus for reasoning about natural language grounded in photographs. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (2019)","DOI":"10.18653\/v1\/P19-1644"},{"key":"13_CR49","doi-asserted-by":"crossref","unstructured":"Wang, W., Bao, H., Dong, L., Bjorck, J., Peng, Z., Liu, Q., Aggarwal, K., Mohammed, O.K., Singhal, S., Som, S., Wei, F.: Image as a foreign language: BEiT pretraining for vision and vision-language tasks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.01838"},{"key":"13_CR50","doi-asserted-by":"crossref","unstructured":"Wang, X., McCallum, A., Wei, X.: Topical n-grams: Phrase and topic discovery, with an application to information retrieval. In: Seventh IEEE International Conference on Data Mining (ICDM 2007) (2007)","DOI":"10.1109\/ICDM.2007.86"},{"key":"13_CR51","unstructured":"Wang, Z., Yu, J., Yu, A.W., Dai, Z., Tsvetkov, Y., Cao, Y.: SimVLM: Simple visual language model pretraining with weak supervision. In: International Conference on Learning Representations (ICLR) (2022)"},{"key":"13_CR52","unstructured":"Xie, N., Lai, F., Doran, D., Kadav, A.: Visual entailment: A novel task for fine-grained image understanding. arXiv:1901.06706 (2019)"},{"key":"13_CR53","doi-asserted-by":"crossref","unstructured":"Xu, H., Yan, M., Li, C., Bi, B., Huang, S., Xiao, W., Huang, F.: E2E-VLP: End-to-end vision-language pre-training enhanced by visual learning. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) (2021)","DOI":"10.18653\/v1\/2021.acl-long.42"},{"key":"13_CR54","unstructured":"Xue, H., Huang, Y., Liu, B., Peng, H., Fu, J., Li, H., Luo, J.: Probing inter-modality: Visual parsing with self-attention for vision-and-language pre-training. In: Advances in Neural Information Processing Systems (NeurIPS) (2021)"},{"key":"13_CR55","unstructured":"Yan, M., Xu, H., Li, C., Bi, B., Tian, J., Gui, M., Wang, W.: Grid-vlp: Revisiting grid features for vision-language pre-training. arXiv:2108.09479 (2021)"},{"key":"13_CR56","doi-asserted-by":"crossref","unstructured":"Yang, J., Duan, J., Tran, S., Xu, Y., Chanda, S., Chen, L., Zeng, B., Chilimbi, T., Huang, J.: Vision-language pre-training with triple contrastive learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01522"},{"key":"13_CR57","doi-asserted-by":"crossref","unstructured":"Yao, L., Han, J., Liang, X., Xu, D., Zhang, W., Li, Z., Xu, H.: Detclipv2: Scalable open-vocabulary object detection pre-training via word-region alignment. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.02250"},{"key":"13_CR58","unstructured":"Yao, L., Huang, R., Hou, L., Lu, G., Niu, M., Xu, H., Liang, X., Li, Z., Jiang, X., Xu, C.: FILIP: Fine-grained interactive language-image pre-training. In: International Conference on Learning Representations (ICLR) (2022)"},{"key":"13_CR59","doi-asserted-by":"crossref","unstructured":"Yu, L., Poirson, P., Yang, S., Berg, A.C., Berg, T.L.: Modeling context in referring expressions. In: Proceedings of the European Conference on Computer Vision (ECCV) (2016)","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"13_CR60","unstructured":"Zeng, Y., Zhang, X., Li, H.: Multi-grained vision language pre-training: Aligning texts with visual concepts. In: International Conference on Machine Learning (ICML) (2022)"},{"key":"13_CR61","doi-asserted-by":"crossref","unstructured":"Zhang, P., Li, X., Hu, X., Yang, J., Zhang, L., Wang, L., Choi, Y., Gao, J.: Vinvl: Revisiting visual representations in vision-language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"13_CR62","doi-asserted-by":"crossref","unstructured":"Zhao, T., Zhang, T., Zhu, M., Shen, H., Lee, K., Lu, X., Yin, J.: An explainable toolbox for evaluating pre-trained vision-language models. In: Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations (2022)","DOI":"10.18653\/v1\/2022.emnlp-demos.4"},{"key":"13_CR63","doi-asserted-by":"crossref","unstructured":"Zhou, M., Yu, L., Singh, A., Wang, M., Yu, Z., Zhang, N.: Unsupervised vision-and-language pre-training via retrieval-based multi-granular alignment. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01599"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-0908-6_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,6]],"date-time":"2024-12-06T20:13:05Z","timestamp":1733515985000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-0908-6_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,7]]},"ISBN":["9789819609079","9789819609086"],"references-count":63,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-0908-6_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,12,7]]},"assertion":[{"value":"7 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hanoi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vietnam","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":"8 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 December 2024","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":"accv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}