Po-Yao (Bernie) Huang, Vaibhav, Xiaojun Chang, Alexander Hauptmann
{"title":"改进跨模态检索模型通过面向对象的模态间和模态内注意网络学习","authors":"Po-Yao (Bernie) Huang, Vaibhav, Xiaojun Chang, Alexander Hauptmann","doi":"10.1145/3323873.3325043","DOIUrl":null,"url":null,"abstract":"Although significant progress has been made for cross-modal retrieval models in recent years, few have explored what those models truly learn and what makes one model superior to another. Start by training two state-of-the-art text-to-image retrieval models with adversarial text inputs, we investigate and quantify the importance of syntactic structure and lexical information in learning the joint visual-semantic embedding space for cross-modal retrieval. The results show that the retrieval power mainly comes from localizing and connecting the visual objects and their cross-modal counter-parts, the textual phrases. Inspired by this observation, we propose a novel model which employs object-oriented encoders along with inter- and intra-modal attention networks to improve inter-modal dependencies for cross-modal retrieval. In addition, we develop a new multimodal structure-preserving objective which additionally emphasizes intra-modal hard negative examples to promote intra-modal discrepancies. Extensive experiments show that the proposed approach outperforms the existing best method by a large margin (16.4% and 6.7% relatively with Recall@1 in the text-to-image retrieval task on the Flickr30K dataset and the MS-COCO dataset respectively).","PeriodicalId":149041,"journal":{"name":"Proceedings of the 2019 on International Conference on Multimedia Retrieval","volume":"12 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2019-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"15","resultStr":"{\"title\":\"Improving What Cross-Modal Retrieval Models Learn through Object-Oriented Inter- and Intra-Modal Attention Networks\",\"authors\":\"Po-Yao (Bernie) Huang, Vaibhav, Xiaojun Chang, Alexander Hauptmann\",\"doi\":\"10.1145/3323873.3325043\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Although significant progress has been made for cross-modal retrieval models in recent years, few have explored what those models truly learn and what makes one model superior to another. Start by training two state-of-the-art text-to-image retrieval models with adversarial text inputs, we investigate and quantify the importance of syntactic structure and lexical information in learning the joint visual-semantic embedding space for cross-modal retrieval. The results show that the retrieval power mainly comes from localizing and connecting the visual objects and their cross-modal counter-parts, the textual phrases. Inspired by this observation, we propose a novel model which employs object-oriented encoders along with inter- and intra-modal attention networks to improve inter-modal dependencies for cross-modal retrieval. In addition, we develop a new multimodal structure-preserving objective which additionally emphasizes intra-modal hard negative examples to promote intra-modal discrepancies. Extensive experiments show that the proposed approach outperforms the existing best method by a large margin (16.4% and 6.7% relatively with Recall@1 in the text-to-image retrieval task on the Flickr30K dataset and the MS-COCO dataset respectively).\",\"PeriodicalId\":149041,\"journal\":{\"name\":\"Proceedings of the 2019 on International Conference on Multimedia Retrieval\",\"volume\":\"12 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2019-06-05\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"15\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of the 2019 on International Conference on Multimedia Retrieval\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1145/3323873.3325043\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 2019 on International Conference on Multimedia Retrieval","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3323873.3325043","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Improving What Cross-Modal Retrieval Models Learn through Object-Oriented Inter- and Intra-Modal Attention Networks
Although significant progress has been made for cross-modal retrieval models in recent years, few have explored what those models truly learn and what makes one model superior to another. Start by training two state-of-the-art text-to-image retrieval models with adversarial text inputs, we investigate and quantify the importance of syntactic structure and lexical information in learning the joint visual-semantic embedding space for cross-modal retrieval. The results show that the retrieval power mainly comes from localizing and connecting the visual objects and their cross-modal counter-parts, the textual phrases. Inspired by this observation, we propose a novel model which employs object-oriented encoders along with inter- and intra-modal attention networks to improve inter-modal dependencies for cross-modal retrieval. In addition, we develop a new multimodal structure-preserving objective which additionally emphasizes intra-modal hard negative examples to promote intra-modal discrepancies. Extensive experiments show that the proposed approach outperforms the existing best method by a large margin (16.4% and 6.7% relatively with Recall@1 in the text-to-image retrieval task on the Flickr30K dataset and the MS-COCO dataset respectively).