{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T11:16:26Z","timestamp":1730200586817,"version":"3.28.0"},"reference-count":77,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,12,17]],"date-time":"2022-12-17T00:00:00Z","timestamp":1671235200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,12,17]],"date-time":"2022-12-17T00:00:00Z","timestamp":1671235200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,12,17]]},"DOI":"10.1109\/bigdata55660.2022.10020922","type":"proceedings-article","created":{"date-parts":[[2023,1,26]],"date-time":"2023-01-26T19:35:23Z","timestamp":1674761723000},"page":"2150-2159","source":"Crossref","is-referenced-by-count":1,"title":["Tree-based Text-Vision BERT for Video Search in Baidu Video Advertising"],"prefix":"10.1109","author":[{"given":"Tan","family":"Yu","sequence":"first","affiliation":[{"name":"Baidu Inc.,Cognitive Computing Lab, Baidu Research Baidu Search Ads (Phoenix Nest),Washington,USA,98004"}]},{"given":"Jie","family":"Liu","sequence":"additional","affiliation":[{"name":"Baidu Inc.,Cognitive Computing Lab, Baidu Research Baidu Search Ads (Phoenix Nest),Washington,USA,98004"}]},{"given":"Yi","family":"Yang","sequence":"additional","affiliation":[{"name":"Baidu Inc.,Cognitive Computing Lab, Baidu Research Baidu Search Ads (Phoenix Nest),Washington,USA,98004"}]},{"given":"Yi","family":"Li","sequence":"additional","affiliation":[{"name":"Baidu Inc.,Cognitive Computing Lab, Baidu Research Baidu Search Ads (Phoenix Nest),Washington,USA,98004"}]},{"given":"Hongliang","family":"Fei","sequence":"additional","affiliation":[{"name":"Baidu Inc.,Cognitive Computing Lab, Baidu Research Baidu Search Ads (Phoenix Nest),Washington,USA,98004"}]},{"given":"Ping","family":"Li","sequence":"additional","affiliation":[{"name":"Baidu Inc.,Cognitive Computing Lab, Baidu Research Baidu Search Ads (Phoenix Nest),Washington,USA,98004"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.14778\/2856318.2856324"},{"article-title":"Layer normalization","year":"2016","author":"Ba","key":"ref2"},{"key":"ref3","first-page":"28","article-title":"The x-tree: An index structure for high-dimensional data","volume-title":"Proceedings of 22th International Conference on Very Large Data Bases (VLDB)","author":"Berchtold"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939812"},{"key":"ref5","first-page":"3123","article-title":"Binaryconnect: Training deep neural networks with binary weights during propagations","volume-title":"Advances in Neural Information Processing Systems (NIPS)","author":"Courbariaux"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/997817.997857"},{"key":"ref7","first-page":"6594","article-title":"Modulating early visual processing by language","volume-title":"Advances in Neural Information Processing Systems (NIPS)","author":"de Vries"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19\u20131423"},{"key":"ref9","first-page":"12","article-title":"VSE++: improving visual-semantic embeddings with hard negatives","volume-title":"Proceedings of British Machine Vision Conference (BMVC)","author":"Faghri"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330651"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15561-1_2"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.285"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463116"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/T-C.1975.224110"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/355744.355745"},{"key":"ref16","first-page":"2121","article-title":"Devise: A deep visual-semantic embedding model","volume-title":"Advances in Neural Information Processing Systems (NIPS)","author":"Frome"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.14778\/3303753.3303754"},{"article-title":"Deep retrieval: Learning a retrievable structure for large-scale recommendations","year":"2020","author":"Gao","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.379"},{"article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding","year":"2015","author":"Han","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"article-title":"Distilling the knowledge in a neural network","year":"2015","author":"Hinton","key":"ref22"},{"key":"ref23","first-page":"187:1","article-title":"Quantized neural networks: Training neural networks with low precision weights and activations","volume":"18","author":"Hubara","year":"2017","journal-title":"J. Mach. Learn. Res."},{"article-title":"Squeezenet: Alexnet-level accuracy with 50x fewer parameters and\u00a1 0.5 mb model size","year":"2016","author":"Iandola","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/276698.276876"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.57"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.372"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401238"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014205"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.3115\/1220575.1220664"},{"key":"ref33","first-page":"676","article-title":"Coding for random projections","volume-title":"Proceedings of the 31th International Conference on Machine Learning (ICML)","author":"Li"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/BF01231606"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298862"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.772"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-naacl.142"},{"key":"ref38","first-page":"13","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Lu"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.301"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889473"},{"article-title":"Recurrent neural networks with limited numerical precision","year":"2016","author":"Ott","key":"ref41"},{"article-title":"Model compression via distillation and quantization","volume-title":"Proceedings of the 6th International Conference on Learning Representations (ICLR)","author":"Polino","key":"ref42"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_32"},{"key":"ref44","first-page":"91","article-title":"Faster R-CNN: towards real-time object detection with region proposal networks","volume-title":"Advances in Neural Information Processing Systems (NIPS)","author":"Ren"},{"key":"ref45","first-page":"516","article-title":"The a-tree: An index structure for high-dimensional spaces using relative approximation","volume-title":"Proceedings of 26th International Conference on Very Large Data Bases (VLDB)","author":"Sakurai"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33460-3_36"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00756"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.14778\/3503585.3503589"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1527"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3336191.3371830"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/2623330.2623688"},{"key":"ref53","first-page":"1753","article-title":"Spectral hashing","volume-title":"Advances in Neural Information Processing Systems (NIPS)","author":"Weiss"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.5555\/3157096.3157329"},{"article-title":"Binarized neural networks on the imagenet classification task","year":"2016","author":"Wu","key":"ref55"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557710"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3448016.3457236"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449830"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557653"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539061"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482233"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403297"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462924"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3481937"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_12"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.347"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/s007780050069"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1145\/3446776"},{"key":"ref69","first-page":"4035","article-title":"ZipML: Training linear models with end-to-end low precision, and a little bit of deep learning","volume-title":"Proceedings of the 34th International Conference on Machine Learning (ICML)","author":"Zhang"},{"key":"ref70","first-page":"838","article-title":"Composite quantization for approximate nearest neighbor search","volume-title":"Proceedings of the 31th International Conference on Machine Learning (ICML)","author":"Zhang"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE48307.2020.00094"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3358045"},{"key":"ref73","first-page":"8216","article-title":"Mobius transformation for fast inner product search on graph","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Zhou"},{"key":"ref74","first-page":"3973","article-title":"Joint optimization of tree-based index and deep model for recommender systems","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Zhu"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219826"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10235"},{"key":"ref77","first-page":"11650","article-title":"Learning optimal tree models under beam search","volume-title":"Proceedings of the 37th International Conference on Machine Learning (ICML)","author":"Zhuo"}],"event":{"name":"2022 IEEE International Conference on Big Data (Big Data)","start":{"date-parts":[[2022,12,17]]},"location":"Osaka, Japan","end":{"date-parts":[[2022,12,20]]}},"container-title":["2022 IEEE International Conference on Big Data (Big Data)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10020192\/10020156\/10020922.pdf?arnumber=10020922","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T06:43:17Z","timestamp":1707806597000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10020922\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,17]]},"references-count":77,"URL":"https:\/\/doi.org\/10.1109\/bigdata55660.2022.10020922","relation":{},"subject":[],"published":{"date-parts":[[2022,12,17]]}}}