{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T10:45:19Z","timestamp":1776681919704,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":68,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,7,11]],"date-time":"2021-07-11T00:00:00Z","timestamp":1625961600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,7,11]]},"DOI":"10.1145\/3404835.3462838","type":"proceedings-article","created":{"date-parts":[[2021,7,12]],"date-time":"2021-07-12T02:41:52Z","timestamp":1626057712000},"page":"1379-1388","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":37,"title":["GilBERT: Generative Vision-Language Pre-Training for Image-Text Retrieval"],"prefix":"10.1145","author":[{"given":"Weixiang","family":"Hong","sequence":"first","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kaixiang","family":"Ji","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiajia","family":"Liu","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Wang","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingdong","family":"Chen","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Chu","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2021,7,11]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00904"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1219"},{"key":"e_1_3_2_1_3_1","volume-title":"The inverted multi-index. TPAMI","author":"Babenko A.","year":"2014","unstructured":"Babenko, A., and Lempitsky, V. The inverted multi-index. TPAMI (2014)."},{"key":"e_1_3_2_1_4_1","volume-title":"Microsoft coco captions: Data collection and evaluation server. arXiv preprint arXiv:1504.00325","author":"Chen X.","year":"2015","unstructured":"Chen, X., Fang, H., Lin, T.-Y., Vedantam, R., Gupta, S., Doll\u00e1r, P., and Zitnick, C. L. Microsoft coco captions: Data collection and evaluation server. arXiv preprint arXiv:1504.00325 (2015)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01092"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2007.4408891"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_9_1","volume-title":"NAACL HLT","author":"Devlin J.","year":"2019","unstructured":"Devlin, J., Chang, M.-W., Lee, K., and Toutanova, K. Bert: Pre-training of deep bidirectional transformers for language understanding. In NAACL HLT (2019)."},{"key":"e_1_3_2_1_10_1","volume-title":"Vse+: Improving visual-semantic embeddings with hard negatives. arXiv:1707.05612","author":"Faghri F.","year":"2017","unstructured":"Faghri, F., Fleet, D. J., Kiros, J. R., and Fidler, S. Vse+: Improving visual-semantic embeddings with hard negatives. arXiv:1707.05612 (2017)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00750"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12266"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00833"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093487"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11294"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11292"},{"key":"e_1_3_2_1_18_1","volume-title":"Asymmetric mapping quantization for nearest neighbor search. TPAMI","author":"Hong W.","year":"2019","unstructured":"Hong, W., Tang, X., Meng, J., and Yuan, J. Asymmetric mapping quantization for nearest neighbor search. TPAMI (2019)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00145"},{"key":"e_1_3_2_1_20_1","volume-title":"Fried binary embedding: From high-dimensional visual features to high-dimensional binary codes. TIP","author":"Hong W.","year":"2018","unstructured":"Hong, W., and Yuan, J. Fried binary embedding: From high-dimensional visual features to high-dimensional binary codes. TIP (2018)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.659"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00473"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"e_1_3_2_1_25_1","volume-title":"Visual genome: Connecting language and vision using crowdsourced dense image annotations. IJCV","author":"Krishna R.","year":"2017","unstructured":"Krishna, R., Zhu, Y., Groth, O., Johnson, J., Hata, K., Kravitz, J., Chen, S., Kalantidis, Y., Li, L.-J., Shamma, D. A., et al. Visual genome: Connecting language and vision using crowdsourced dense image annotations. IJCV (2017)."},{"key":"e_1_3_2_1_26_1","volume-title":"The open images dataset v4: Unified image classification, object detection, and visual relationship detection at scale. arXiv:1811.00982","author":"Kuznetsova A.","year":"2018","unstructured":"Kuznetsova, A., Rom, H., Alldrin, N., Uijlings, J., Krasin, I., Pont-Tuset, J., Kamali, S., Popov, S., Malloci, M., Duerig, T., et al. The open images dataset v4: Unified image classification, object detection, and visual relationship detection at scale. arXiv:1811.00982 (2018)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"e_1_3_2_1_28_1","volume-title":"Unicoder-vl: A universal encoder for vision and language by cross-modal pre-training. arXiv preprint arXiv:1908.06066","author":"Li G.","year":"2019","unstructured":"Li, G., Duan, N., Fang, Y., Jiang, D., and Zhou, M. Unicoder-vl: A universal encoder for vision and language by cross-modal pre-training. arXiv preprint arXiv:1908.06066 (2019)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00475"},{"key":"e_1_3_2_1_30_1","volume-title":"-W. Visualbert: A simple and performant baseline for vision and language. arXiv:1908.03557","author":"Li L. H.","year":"2019","unstructured":"Li, L. H., Yatskar, M., Yin, D., Hsieh, C.-J., and Chang, K.-W. Visualbert: A simple and performant baseline for vision and language. arXiv:1908.03557 (2019)."},{"key":"e_1_3_2_1_31_1","volume-title":"-W. Weakly-supervised visualbert: Pre-training without parallel images and captions. arXiv:2010.12831","author":"Li L. H.","year":"2020","unstructured":"Li, L. H., You, H., Wang, Z., Zareian, A., Chang, S.-F., and Chang, K.-W. Weakly-supervised visualbert: Pre-training without parallel images and captions. arXiv:2010.12831 (2020)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01245"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01245"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_1_36_1","volume-title":"NIPS","author":"Lu J.","year":"2019","unstructured":"Lu, J., Batra, D., Parikh, D., and Lee, S. Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. In NIPS (2019)."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01045"},{"key":"e_1_3_2_1_38_1","volume-title":"Conditional generative adversarial nets. arXiv:1411.1784","author":"Mirza M.","year":"2014","unstructured":"Mirza, M., and Osindero, S. Conditional generative adversarial nets. arXiv:1411.1784 (2014)."},{"key":"e_1_3_2_1_39_1","volume-title":"NIPS","author":"Ordonez V.","year":"2011","unstructured":"Ordonez, V., Kulkarni, G., and Berg, T. L. Im2text: Describing images using 1 million captioned photographs. In NIPS (2011)."},{"key":"e_1_3_2_1_40_1","volume-title":"CVPR","author":"Qi C. R.","year":"2017","unstructured":"Qi, C. R., Su, H., Mo, K., and Guibas, L. J. Pointnet: Deep learning on point sets for 3d classification and segmentation. In CVPR (2017)."},{"key":"e_1_3_2_1_41_1","volume-title":"ICML","author":"Reed S.","year":"2016","unstructured":"Reed, S., Akata, Z., Yan, X., Logeswaran, L., Schiele, B., and Lee, H. Generative adversarial text to image synthesis. In ICML (2016)."},{"key":"e_1_3_2_1_42_1","volume-title":"NIPS","author":"Ren S.","year":"2015","unstructured":"Ren, S., He, K., Girshick, R., and Sun, J. Faster r-cnn: Towards real-time object detection with region proposal networks. In NIPS (2015)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.128"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540112"},{"key":"e_1_3_2_1_46_1","volume-title":"ECCV","author":"Song Y.","year":"2020","unstructured":"Song, Y., and Soleymani, M. Oscar: Object-semantics aligned pre-training for vision-language tasks. In ECCV (2020)."},{"key":"e_1_3_2_1_47_1","volume-title":"ICLR","author":"Su W.","year":"2019","unstructured":"Su, W., Zhu, X., Cao, Y., Li, B., Lu, L., Wei, F., and Dai, J. Vl-bert: Pre-training of generic visual-linguistic representations. In ICLR (2019)."},{"key":"e_1_3_2_1_48_1","volume-title":"A corpus for reasoning about natural language grounded in photographs. arXiv:1811.00491","author":"Suhr A.","year":"2018","unstructured":"Suhr, A., Zhou, S., Zhang, A., Zhang, I., Bai, H., and Artzi, Y. A corpus for reasoning about natural language grounded in photographs. arXiv:1811.00491 (2018)."},{"key":"e_1_3_2_1_49_1","volume-title":"Contrastive bidirectional transformer for temporal representation learning. arXiv:1906.05743","author":"Sun C.","year":"2019","unstructured":"Sun, C., Baradel, F., Murphy, K., and Schmid, C. Contrastive bidirectional transformer for temporal representation learning. arXiv:1906.05743 (2019)."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00756"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"e_1_3_2_1_52_1","volume-title":"NIPS","author":"Vaswani A.","year":"2017","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, \u0141., and Polosukhin, I. Attention is all you need. In NIPS (2017)."},{"key":"e_1_3_2_1_53_1","volume-title":"Order matters: Sequence to sequence for sets. arXiv:1511.06391","author":"Vinyals O.","year":"2015","unstructured":"Vinyals, O., Bengio, S., and Kudlur, M. Order matters: Sequence to sequence for sets. arXiv:1511.06391 (2015)."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"e_1_3_2_1_55_1","volume-title":"Pruning 3d filters for accelerating 3d convnets. TMM","author":"Wang Z.","year":"2019","unstructured":"Wang, Z., Hong, W., Tan, Y.-P., and Yuan, J. Pruning 3d filters for accelerating 3d convnets. TMM (2019)."},{"key":"e_1_3_2_1_56_1","volume-title":"Deep reinforcement learning with label embedding reward for supervised image hashing. arXiv preprint arXiv:2008.03973","author":"Wang Z.","year":"2020","unstructured":"Wang, Z., Hong, W., and Yuan, J. Deep reinforcement learning with label embedding reward for supervised image hashing. arXiv preprint arXiv:2008.03973 (2020)."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00586"},{"key":"e_1_3_2_1_58_1","volume-title":"What value do explicit high level concepts have in vision to language problems? In CVPR","author":"Wu Q.","year":"2016","unstructured":"Wu, Q., Shen, C., Liu, L., Dick, A., and Van Den Hengel, A. What value do explicit high level concepts have in vision to language problems? In CVPR (2016)."},{"key":"e_1_3_2_1_59_1","volume-title":"NIPS","author":"Xingjian S.","year":"2015","unstructured":"Xingjian, S., Chen, Z., Wang, H., Yeung, D.-Y., Wong, W.-K., and Woo, W.-c. Convolutional lstm network: A machine learning approach for precipitation nowcasting. In NIPS (2015)."},{"key":"e_1_3_2_1_60_1","volume-title":"From image descriptions to visual denotations: New similarity metrics for semantic inference over event descriptions. Transactions of the Association for Computational Linguistics","author":"Young P.","year":"2014","unstructured":"Young, P., Lai, A., Hodosh, M., and Hockenmaier, J. From image descriptions to visual denotations: New similarity metrics for semantic inference over event descriptions. Transactions of the Association for Computational Linguistics (2014)."},{"key":"e_1_3_2_1_61_1","volume-title":"Product quantization network for fast visual search. IJCV","author":"Yu T.","year":"2020","unstructured":"Yu, T., Meng, J., Fang, C., Jin, H., and Yuan, J. Product quantization network for fast visual search. IJCV (2020)."},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.85"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11192"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.340"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462924"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_12"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.629"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7005"}],"event":{"name":"SIGIR '21: The 44th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Virtual Event Canada","acronym":"SIGIR '21","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3404835.3462838","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3404835.3462838","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:47:17Z","timestamp":1750193237000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3404835.3462838"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,11]]},"references-count":68,"alternative-id":["10.1145\/3404835.3462838","10.1145\/3404835"],"URL":"https:\/\/doi.org\/10.1145\/3404835.3462838","relation":{},"subject":[],"published":{"date-parts":[[2021,7,11]]},"assertion":[{"value":"2021-07-11","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}