{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T00:43:13Z","timestamp":1783039393962,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":42,"publisher":"ACM","license":[{"start":{"date-parts":[[2018,6,5]],"date-time":"2018-06-05T00:00:00Z","timestamp":1528156800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1746031,1544969"],"award-info":[{"award-number":["1746031,1544969"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2018,6,5]]},"DOI":"10.1145\/3206025.3206064","type":"proceedings-article","created":{"date-parts":[[2018,6,11]],"date-time":"2018-06-11T12:36:20Z","timestamp":1528720580000},"page":"19-27","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":191,"title":["Learning Joint Embedding with Multimodal Cues for Cross-Modal Video-Text Retrieval"],"prefix":"10.1145","author":[{"given":"Niluthpol Chowdhury","family":"Mithun","sequence":"first","affiliation":[{"name":"University of California, Riverside, Riverside, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Juncheng","family":"Li","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University & Bosch Research and Technology Center, Pittsburgh, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Florian","family":"Metze","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Amit K.","family":"Roy-Chowdhury","sequence":"additional","affiliation":[{"name":"University of California, Riverside, Riverside, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2018,6,5]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Soundnet: Learning sound representations from unlabeled video Advances in Neural Information Processing Systems. 892--900.","author":"Aytar Yusuf","year":"2016","unstructured":"Yusuf Aytar , Carl Vondrick , and Antonio Torralba . 2016 . Soundnet: Learning sound representations from unlabeled video Advances in Neural Information Processing Systems. 892--900. Yusuf Aytar, Carl Vondrick, and Antonio Torralba. 2016. Soundnet: Learning sound representations from unlabeled video Advances in Neural Information Processing Systems. 892--900."},{"key":"e_1_3_2_1_2_1","volume-title":"Deep Aligned Representations. arXiv preprint arXiv:1706.00932","year":"2017","unstructured":"Yusuf Aytar, Carl Vondrick, and Antonio Torralba. 2017. See, Hear, and Read : Deep Aligned Representations. arXiv preprint arXiv:1706.00932 ( 2017 ). Yusuf Aytar, Carl Vondrick, and Antonio Torralba. 2017. See, Hear, and Read: Deep Aligned Representations. arXiv preprint arXiv:1706.00932 (2017)."},{"key":"e_1_3_2_1_3_1","volume-title":"Quo vadis, action recognition? a new model and the kinetics dataset IEEE Conference on Computer Vision and Pattern Recognition","author":"Carreira Joao","unstructured":"Joao Carreira and Andrew Zisserman . 2017. Quo vadis, action recognition? a new model and the kinetics dataset IEEE Conference on Computer Vision and Pattern Recognition . IEEE , 4724--4733. Joao Carreira and Andrew Zisserman. 2017. Quo vadis, action recognition? a new model and the kinetics dataset IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 4724--4733."},{"key":"e_1_3_2_1_4_1","unstructured":"David L Chen and William B Dolan. 2011. Collecting highly parallel data for paraphrase evaluation Annual Meeting of the Association for Computational Linguistics: Human Language Technologies-Volume 1. ACL 190--200.   David L Chen and William B Dolan. 2011. Collecting highly parallel data for paraphrase evaluation Annual Meeting of the Association for Computational Linguistics: Human Language Technologies-Volume 1. ACL 190--200."},{"key":"e_1_3_2_1_5_1","volume-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555","author":"Chung Junyoung","year":"2014","unstructured":"Junyoung Chung , Caglar Gulcehre , KyungHyun Cho , and Yoshua Bengio . 2014. Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555 ( 2014 ). Junyoung Chung, Caglar Gulcehre, KyungHyun Cho, and Yoshua Bengio. 2014. Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555 (2014)."},{"key":"e_1_3_2_1_6_1","volume-title":"Word2VisualVec: Image and Video to Sentence Matching by Visual Feature Prediction. arXiv preprint arXiv:1604.06838","author":"Dong Jianfeng","year":"2016","unstructured":"Jianfeng Dong , Xirong Li , and Cees GM Snoek . 2016. Word2VisualVec: Image and Video to Sentence Matching by Visual Feature Prediction. arXiv preprint arXiv:1604.06838 ( 2016 ). Jianfeng Dong, Xirong Li, and Cees GM Snoek. 2016. Word2VisualVec: Image and Video to Sentence Matching by Visual Feature Prediction. arXiv preprint arXiv:1604.06838 (2016)."},{"key":"e_1_3_2_1_7_1","volume-title":"Jamie Ryan Kiros, and Sanja Fidler","author":"Faghri Fartash","year":"2017","unstructured":"Fartash Faghri , David J Fleet , Jamie Ryan Kiros, and Sanja Fidler . 2017 . VSE : Improved Visual-Semantic Embeddings . arXiv preprint arXiv:1707.05612 (201 Fartash Faghri, David J Fleet, Jamie Ryan Kiros, and Sanja Fidler. 2017. VSE: Improved Visual-Semantic Embeddings. arXiv preprint arXiv:1707.05612 (201"},{"key":"e_1_3_2_1_8_1","volume-title":"Peter Young, Cyrus Rashtchian, Julia Hockenmaier, and David Forsyth.","author":"Farhadi Ali","year":"2010","unstructured":"Ali Farhadi , Mohsen Hejrati , Mohammad Amin Sadeghi , Peter Young, Cyrus Rashtchian, Julia Hockenmaier, and David Forsyth. 2010 . Every picture tells a story: Generating sentences from images European Conference on Computer Vision. Springer , 15--29. Ali Farhadi, Mohsen Hejrati, Mohammad Amin Sadeghi, Peter Young, Cyrus Rashtchian, Julia Hockenmaier, and David Forsyth. 2010. Every picture tells a story: Generating sentences from images European Conference on Computer Vision. Springer, 15--29."},{"key":"e_1_3_2_1_9_1","volume-title":"et almbox","author":"Frome Andrea","year":"2013","unstructured":"Andrea Frome , Greg S Corrado , Jon Shlens , Samy Bengio , Jeff Dean , Tomas Mikolov , et almbox .. 2013 . Devise : A deep visual-semantic embedding model. In Advances in Neural Information Processing Systems . 2121--2129. Andrea Frome, Greg S Corrado, Jon Shlens, Samy Bengio, Jeff Dean, Tomas Mikolov, et almbox.. 2013. Devise: A deep visual-semantic embedding model. In Advances in Neural Information Processing Systems. 2121--2129."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0658-4"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3078971.3078991"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.5555\/2566972.2566993"},{"key":"e_1_3_2_1_14_1","volume-title":"Instance-aware image and sentence matching with selective multimodal lstm IEEE Conference on Computer Vision and Pattern Recognition","author":"Huang Yan","unstructured":"Yan Huang , Wei Wang , and Liang Wang . 2017. Instance-aware image and sentence matching with selective multimodal lstm IEEE Conference on Computer Vision and Pattern Recognition . IEEE , 2310--2318. Yan Huang, Wei Wang, and Liang Wang. 2017. Instance-aware image and sentence matching with selective multimodal lstm IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 2310--2318."},{"key":"e_1_3_2_1_15_1","volume-title":"Deep visual-semantic alignments for generating image descriptions IEEE Conference on Computer Vision and Pattern Recognition","author":"Karpathy Andrej","unstructured":"Andrej Karpathy and Li Fei-Fei . 2015. Deep visual-semantic alignments for generating image descriptions IEEE Conference on Computer Vision and Pattern Recognition . IEEE , 3128--3137. Andrej Karpathy and Li Fei-Fei. 2015. Deep visual-semantic alignments for generating image descriptions IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 3128--3137."},{"key":"e_1_3_2_1_16_1","unstructured":"Andrej Karpathy Armand Joulin and Fei Fei F Li. 2014. Deep fragment embeddings for bidirectional image sentence mapping Advances in Neural Information Processing Systems. 1889--1897.   Andrej Karpathy Armand Joulin and Fei Fei F Li. 2014. Deep fragment embeddings for bidirectional image sentence mapping Advances in Neural Information Processing Systems. 1889--1897."},{"key":"e_1_3_2_1_17_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik","year":"2014","unstructured":"Diederik Kingma and Jimmy Ba . 2014 . Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014). Diederik Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_1_18_1","volume-title":"Unifying visual-semantic embeddings with multimodal neural language models. arXiv preprint arXiv : 1411.2539","author":"Kiros Ryan","year":"2014","unstructured":"Ryan Kiros , Ruslan Salakhutdinov , and Richard S Zemel . 2014. Unifying visual-semantic embeddings with multimodal neural language models. arXiv preprint arXiv : 1411.2539 ( 2014 ). Ryan Kiros, Ruslan Salakhutdinov, and Richard S Zemel. 2014. Unifying visual-semantic embeddings with multimodal neural language models. arXiv preprint arXiv : 1411.2539 (2014)."},{"key":"e_1_3_2_1_19_1","unstructured":"Ryan Kiros Yukun Zhu Ruslan R Salakhutdinov Richard Zemel Raquel Urtasun Antonio Torralba and Sanja Fidler. 2015. Skip-thought vectors Advances in Neural Information Processing Systems. 3294--3302.   Ryan Kiros Yukun Zhu Ruslan R Salakhutdinov Richard Zemel Raquel Urtasun Antonio Torralba and Sanja Fidler. 2015. Skip-thought vectors Advances in Neural Information Processing Systems. 3294--3302."},{"key":"e_1_3_2_1_20_1","volume-title":"Associating neural word embeddings with deep image representations using fisher vectors IEEE Conference on Computer Vision and Pattern Recognition","author":"Klein Benjamin","unstructured":"Benjamin Klein , Guy Lev , Gil Sadeh , and Lior Wolf . 2015. Associating neural word embeddings with deep image representations using fisher vectors IEEE Conference on Computer Vision and Pattern Recognition . IEEE , 4437--4446. Benjamin Klein, Guy Lev, Gil Sadeh, and Lior Wolf. 2015. Associating neural word embeddings with deep image representations using fisher vectors IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 4437--4446."},{"key":"e_1_3_2_1_21_1","volume-title":"Sampling Matters in Deep Embedding Learning. In 2017 IEEE International Conference on Computer Vision. IEEE, 2859--2867","author":"Manmatha R","year":"2017","unstructured":"R Manmatha , Chao-Yuan Wu , Alexander J Smola , and Philipp Krahenbuhl . 2017 . Sampling Matters in Deep Embedding Learning. In 2017 IEEE International Conference on Computer Vision. IEEE, 2859--2867 . R Manmatha, Chao-Yuan Wu, Alexander J Smola, and Philipp Krahenbuhl. 2017. Sampling Matters in Deep Embedding Learning. In 2017 IEEE International Conference on Computer Vision. IEEE, 2859--2867."},{"key":"e_1_3_2_1_22_1","volume-title":"Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781","author":"Mikolov Tomas","year":"2013","unstructured":"Tomas Mikolov , Kai Chen , Greg Corrado , and Jeffrey Dean . 2013. Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781 ( 2013 ). Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013. Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781 (2013)."},{"key":"e_1_3_2_1_23_1","volume-title":"Dual Attention Networks for Multimodal Reasoning and Matching IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 299--307","author":"Nam Hyeonseob","year":"2017","unstructured":"Hyeonseob Nam , Jung-Woo Ha , and Jeonghee Kim . 2017 . Dual Attention Networks for Multimodal Reasoning and Matching IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 299--307 . Hyeonseob Nam, Jung-Woo Ha, and Jeonghee Kim. 2017. Dual Attention Networks for Multimodal Reasoning and Matching IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 299--307."},{"key":"e_1_3_2_1_24_1","volume-title":"Learning joint representations of videos and sentences with web image search European Conference on Computer Vision","author":"Otani Mayu","unstructured":"Mayu Otani , Yuta Nakashima , Esa Rahtu , Janne Heikkil\u00e4 , and Naokazu Yokoya . 2016. Learning joint representations of videos and sentences with web image search European Conference on Computer Vision . Springer , 651--667. Mayu Otani, Yuta Nakashima, Esa Rahtu, Janne Heikkil\u00e4, and Naokazu Yokoya. 2016. Learning joint representations of videos and sentences with web image search European Conference on Computer Vision. Springer, 651--667."},{"key":"e_1_3_2_1_25_1","volume-title":"Jointly modeling embedding and translation to bridge video and language IEEE Conference on Computer Vision and Pattern Recognition","author":"Pan Yingwei","unstructured":"Yingwei Pan , Tao Mei , Ting Yao , Houqiang Li , and Yong Rui . 2016. Jointly modeling embedding and translation to bridge video and language IEEE Conference on Computer Vision and Pattern Recognition . IEEE , 4594--4602. Yingwei Pan, Tao Mei, Ting Yao, Houqiang Li, and Yong Rui. 2016. Jointly modeling embedding and translation to bridge video and language IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 4594--4602."},{"key":"e_1_3_2_1_26_1","volume-title":"Enhancing Video Summarization via Vision-Language Embedding IEEE Conference on Computer Vision and Pattern Recognition","author":"Plummer Bryan","unstructured":"Bryan Plummer , Matthew Brown , and Svetlana Lazebnik . 2017. Enhancing Video Summarization via Vision-Language Embedding IEEE Conference on Computer Vision and Pattern Recognition . IEEE. Bryan Plummer, Matthew Brown, and Svetlana Lazebnik. 2017. Enhancing Video Summarization via Vision-Language Embedding IEEE Conference on Computer Vision and Pattern Recognition. IEEE."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2984066"},{"key":"e_1_3_2_1_28_1","volume-title":"Facenet: A unified embedding for face recognition and clustering IEEE Conference on Computer Vision and Pattern Recognition","author":"Schroff Florian","year":"2015","unstructured":"Florian Schroff , Dmitry Kalenichenko , and James Philbin . 2015 . Facenet: A unified embedding for face recognition and clustering IEEE Conference on Computer Vision and Pattern Recognition . IEEE , 815--823. Florian Schroff, Dmitry Kalenichenko, and James Philbin. 2015. Facenet: A unified embedding for face recognition and clustering IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 815--823."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540112"},{"key":"e_1_3_2_1_30_1","volume-title":"Learning language-visual embedding for movie understanding with natural-language. arXiv preprint arXiv:1609.08124","author":"Torabi Atousa","year":"2016","unstructured":"Atousa Torabi , Niket Tandon , and Leonid Sigal . 2016. Learning language-visual embedding for movie understanding with natural-language. arXiv preprint arXiv:1609.08124 ( 2016 ). Atousa Torabi, Niket Tandon, and Leonid Sigal. 2016. Learning language-visual embedding for movie understanding with natural-language. arXiv preprint arXiv:1609.08124 (2016)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553509"},{"key":"e_1_3_2_1_32_1","volume-title":"International Conference on Learning Representations.","author":"Vendrov Ivan","year":"2016","unstructured":"Ivan Vendrov , Ryan Kiros , Sanja Fidler , and Raquel Urtasun . 2016 . Order-embeddings of images and language . In International Conference on Learning Representations. Ivan Vendrov, Ryan Kiros, Sanja Fidler, and Raquel Urtasun. 2016. Order-embeddings of images and language. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"},{"key":"e_1_3_2_1_34_1","volume-title":"Learning two-branch neural networks for image-text matching tasks","author":"Wang Liwei","year":"2018","unstructured":"Liwei Wang , Yin Li , Jing Huang , and Svetlana Lazebnik . 2018. Learning two-branch neural networks for image-text matching tasks . IEEE Transactions on Pattern Analysis and Machine Intelligence ( 2018 ). Liwei Wang, Yin Li, Jing Huang, and Svetlana Lazebnik. 2018. Learning two-branch neural networks for image-text matching tasks. IEEE Transactions on Pattern Analysis and Machine Intelligence (2018)."},{"key":"e_1_3_2_1_35_1","volume-title":"Learning deep structure-preserving image-text embeddings IEEE Conference on Computer Vision and Pattern Recognition","author":"Wang Liwei","unstructured":"Liwei Wang , Yin Li , and Svetlana Lazebnik . 2016. Learning deep structure-preserving image-text embeddings IEEE Conference on Computer Vision and Pattern Recognition . IEEE , 5005--5013. Liwei Wang, Yin Li, and Svetlana Lazebnik. 2016. Learning deep structure-preserving image-text embeddings IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 5005--5013."},{"key":"e_1_3_2_1_36_1","volume-title":"Msr-vtt: A large video description dataset for bridging video and language IEEE Conference on Computer Vision and Pattern Recognition. 5288--5296.","author":"Xu Jun","year":"2016","unstructured":"Jun Xu , Tao Mei , Ting Yao , and Yong Rui . 2016 . Msr-vtt: A large video description dataset for bridging video and language IEEE Conference on Computer Vision and Pattern Recognition. 5288--5296. Jun Xu, Tao Mei, Ting Yao, and Yong Rui. 2016. Msr-vtt: A large video description dataset for bridging video and language IEEE Conference on Computer Vision and Pattern Recognition. 5288--5296."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.5555\/2886521.2886647"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298966"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/1027527.1027661"},{"key":"e_1_3_2_1_40_1","volume-title":"End-To-End Concept Word Detection for Video Captioning, Retrieval, and Question Answering IEEE Conference on Computer Vision and Pattern Recognition","author":"Yu Youngjae","unstructured":"Youngjae Yu , Hyungjin Ko , Jongwook Choi , and Gunhee Kim . 2017. End-To-End Concept Word Detection for Video Captioning, Retrieval, and Question Answering IEEE Conference on Computer Vision and Pattern Recognition . IEEE , 3165--3173. Youngjae Yu, Hyungjin Ko, Jongwook Choi, and Gunhee Kim. 2017. End-To-End Concept Word Detection for Video Captioning, Retrieval, and Question Answering IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 3165--3173."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123317"},{"key":"e_1_3_2_1_42_1","volume-title":"Task-Driven Dynamic Fusion: Reducing Ambiguity in Video Description IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 3713--3721","author":"Zhang Xishan","year":"2017","unstructured":"Xishan Zhang , Ke Gao , Yongdong Zhang , Dongming Zhang , Jintao Li , and Qi Tian . 2017 a . Task-Driven Dynamic Fusion: Reducing Ambiguity in Video Description IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 3713--3721 . Xishan Zhang, Ke Gao, Yongdong Zhang, Dongming Zhang, Jintao Li, and Qi Tian. 2017 a. Task-Driven Dynamic Fusion: Reducing Ambiguity in Video Description IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 3713--3721."}],"event":{"name":"ICMR '18: International Conference on Multimedia Retrieval","location":"Yokohama Japan","acronym":"ICMR '18","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 2018 ACM on International Conference on Multimedia Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3206025.3206064","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3206025.3206064","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3206025.3206064","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T01:08:15Z","timestamp":1750208895000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3206025.3206064"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,6,5]]},"references-count":42,"alternative-id":["10.1145\/3206025.3206064","10.1145\/3206025"],"URL":"https:\/\/doi.org\/10.1145\/3206025.3206064","relation":{},"subject":[],"published":{"date-parts":[[2018,6,5]]},"assertion":[{"value":"2018-06-05","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}