{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T16:09:44Z","timestamp":1780675784792,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":51,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,10,12]],"date-time":"2020-10-12T00:00:00Z","timestamp":1602460800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Key R&D Program of China","award":["2016YFB1001402"],"award-info":[{"award-number":["2016YFB1001402"]}]},{"name":"National Natural Science Foundation of China","award":["U19B2038,61620106009"],"award-info":[{"award-number":["U19B2038,61620106009"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,10,12]]},"DOI":"10.1145\/3394171.3413975","type":"proceedings-article","created":{"date-parts":[[2020,10,12]],"date-time":"2020-10-12T13:12:00Z","timestamp":1602508320000},"page":"4116-4124","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":58,"title":["Dual Path Interaction Network for Video Moment Localization"],"prefix":"10.1145","author":[{"given":"Hao","family":"Wang","sequence":"first","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zheng-Jun","family":"Zha","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuejin","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiwei","family":"Xiong","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiebo","family":"Luo","sequence":"additional","affiliation":[{"name":"University of Rochester, Rochester, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2020,10,12]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"crossref","unstructured":"Lisa Anne Hendricks Oliver Wang Eli Shechtman Josef Sivic Trevor Darrell and Bryan Russell. 2017. Localizing moments in video with natural language. In ICCV.  Lisa Anne Hendricks Oliver Wang Eli Shechtman Josef Sivic Trevor Darrell and Bryan Russell. 2017. Localizing moments in video with natural language. In ICCV.","DOI":"10.1109\/ICCV.2017.618"},{"key":"e_1_3_2_2_2_1","volume-title":"SST: Single-Stream Temporal Action Proposals. In CVPR.","author":"Buch Shyamal","year":"2017","unstructured":"Shyamal Buch , Victor Escorcia , Chuanqi Shen , Bernard Ghanem , and Juan Carlos Niebles . 2017 . SST: Single-Stream Temporal Action Proposals. In CVPR. Shyamal Buch, Victor Escorcia, Chuanqi Shen, Bernard Ghanem, and Juan Carlos Niebles. 2017. SST: Single-Stream Temporal Action Proposals. In CVPR."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"crossref","unstructured":"Yuwei Chao Sudheendra Vijayanarasimhan Bryan Seybold David A Ross Jia Deng and Rahul Sukthankar. 2018. Rethinking the Faster R-CNN Architecture for Temporal Action Localization. In CVPR.  Yuwei Chao Sudheendra Vijayanarasimhan Bryan Seybold David A Ross Jia Deng and Rahul Sukthankar. 2018. Rethinking the Faster R-CNN Architecture for Temporal Action Localization. In CVPR.","DOI":"10.1109\/CVPR.2018.00124"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"crossref","unstructured":"Jingyuan Chen Xinpeng Chen Lin Ma Zequn Jie and Tat-Seng Chua. 2018. Temporally grounding natural sentence in video. In EMNLP.  Jingyuan Chen Xinpeng Chen Lin Ma Zequn Jie and Tat-Seng Chua. 2018. Temporally grounding natural sentence in video. In EMNLP.","DOI":"10.18653\/v1\/D18-1015"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"crossref","unstructured":"Jingyuan Chen Lin Ma Xinpeng Chen Zequn Jie and Jiebo Luo. 2019. Localizing natural language in videos. In AAAI.  Jingyuan Chen Lin Ma Xinpeng Chen Zequn Jie and Jiebo Luo. 2019. Localizing natural language in videos. In AAAI.","DOI":"10.1609\/aaai.v33i01.33018175"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"crossref","unstructured":"Long Chen Chujie Lu Siliang Tang Jun Xiao Dong Zhang Chilie Tan and Xiaolin Li. 2020. Rethinking the Bottom-Up Framework for Query-based Video Localization. In AAAI.  Long Chen Chujie Lu Siliang Tang Jun Xiao Dong Zhang Chilie Tan and Xiaolin Li. 2020. Rethinking the Bottom-Up Framework for Query-based Video Localization. In AAAI.","DOI":"10.1609\/aaai.v34i07.6627"},{"key":"e_1_3_2_2_7_1","unstructured":"Shaoxiang Chen and Yu-Gang Jiang. 2019. Semantic Proposal for Activity Localization in Videos via Sentence Query. In AAAI.  Shaoxiang Chen and Yu-Gang Jiang. 2019. Semantic Proposal for Activity Localization in Videos via Sentence Query. In AAAI."},{"key":"e_1_3_2_2_8_1","volume-title":"Caglar Gulcehre, Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, and Yoshua Bengio.","author":"Cho Kyunghyun","year":"2014","unstructured":"Kyunghyun Cho , Bart Van Merrienboer , Caglar Gulcehre, Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, and Yoshua Bengio. 2014 . Learning Phrase Representations using RNN Encoder--Decoder for Statistical Machine Translation. In EMNLP. Kyunghyun Cho, Bart Van Merrienboer, Caglar Gulcehre, Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, and Yoshua Bengio. 2014. Learning Phrase Representations using RNN Encoder--Decoder for Statistical Machine Translation. In EMNLP."},{"key":"e_1_3_2_2_9_1","volume-title":"Tall: Temporal activity localization via language query. In ICCV.","author":"Gao Jiyang","year":"2017","unstructured":"Jiyang Gao , Chen Sun , Zhenheng Yang , and Ram Nevatia . 2017 . Tall: Temporal activity localization via language query. In ICCV. Jiyang Gao, Chen Sun, Zhenheng Yang, and Ram Nevatia. 2017. Tall: Temporal activity localization via language query. In ICCV."},{"key":"e_1_3_2_2_10_1","volume-title":"MAC: Mining Activity Concepts for Language-based Temporal Localization. In WACV.","author":"Ge Runzhou","year":"2019","unstructured":"Runzhou Ge , Jiyang Gao , Kan Chen , and Ram Nevatia . 2019 . MAC: Mining Activity Concepts for Language-based Temporal Localization. In WACV. Runzhou Ge, Jiyang Gao, Kan Chen, and Ram Nevatia. 2019. MAC: Mining Activity Concepts for Language-based Temporal Localization. In WACV."},{"key":"e_1_3_2_2_11_1","volume-title":"ExCL: Extractive Clip Localization Using Natural Language Descriptions. arXiv preprint arXiv:1904.02755","author":"Ghosh Soham","year":"2019","unstructured":"Soham Ghosh , Anuva Agarwal , Zarana Parekh , and Alexander Hauptmann . 2019. ExCL: Extractive Clip Localization Using Natural Language Descriptions. arXiv preprint arXiv:1904.02755 ( 2019 ). Soham Ghosh, Anuva Agarwal, Zarana Parekh, and Alexander Hauptmann. 2019. ExCL: Extractive Clip Localization Using Natural Language Descriptions. arXiv preprint arXiv:1904.02755 (2019)."},{"key":"e_1_3_2_2_12_1","volume-title":"Reinforcement Learning for Temporally Grounding Natural Language Descriptions in Videos. arXiv preprint arXiv:1901.06829","author":"He Dongliang","year":"2019","unstructured":"Dongliang He , Xiang Zhao , Jizhou Huang , Fu Li , Xiao Liu , and Shilei Wen . 2019. Read, Watch, and Move : Reinforcement Learning for Temporally Grounding Natural Language Descriptions in Videos. arXiv preprint arXiv:1901.06829 ( 2019 ). Dongliang He, Xiang Zhao, Jizhou Huang, Fu Li, Xiao Liu, and Shilei Wen. 2019. Read, Watch, and Move: Reinforcement Learning for Temporally Grounding Natural Language Descriptions in Videos. arXiv preprint arXiv:1901.06829 (2019)."},{"key":"e_1_3_2_2_13_1","unstructured":"Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2016. Deep residual learning for image recognition. In CVPR.  Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2016. Deep residual learning for image recognition. In CVPR."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"crossref","unstructured":"Fabian Caba Heilbron Victor Escorcia Bernard Ghanem and Juan Carlos Niebles. 2015. ActivityNet: A large-scale video benchmark for human activity understanding. In CVPR.  Fabian Caba Heilbron Victor Escorcia Bernard Ghanem and Juan Carlos Niebles. 2015. ActivityNet: A large-scale video benchmark for human activity understanding. In CVPR.","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"e_1_3_2_2_15_1","volume-title":"Long Short-Term Memory. Neural Computation","author":"Hochreiter S","unstructured":"S Hochreiter and J Schmidhuber . [n.d.]. Long Short-Term Memory. Neural Computation , Vol. 9 , 8 ( [n.,d.]), 1735--1780. S Hochreiter and J Schmidhuber. [n.d.]. Long Short-Term Memory. Neural Computation, Vol. 9, 8 ( [n.,d.]), 1735--1780."},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"crossref","unstructured":"Bin Jiang Xin Huang Chao Yang and Junsong Yuan. 2019. Cross-Modal Video Moment Retrieval with Spatial and Language-Temporal Attention. In ICMR.  Bin Jiang Xin Huang Chao Yang and Junsong Yuan. 2019. Cross-Modal Video Moment Retrieval with Spatial and Language-Temporal Attention. In ICMR.","DOI":"10.1145\/3323873.3325019"},{"key":"e_1_3_2_2_17_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba . 2014 . Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014). Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"crossref","unstructured":"Ranjay Krishna Kenji Hata Frederic Ren Li Fei-Fei and Juan Carlos Niebles. 2017. Dense-captioning events in videos. In ICCV.  Ranjay Krishna Kenji Hata Frederic Ren Li Fei-Fei and Juan Carlos Niebles. 2017. Dense-captioning events in videos. In ICCV.","DOI":"10.1109\/ICCV.2017.83"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"crossref","unstructured":"Hei Law and Jia Deng. 2018. CornerNet: Detecting Objects as Paired Keypoints. In ECCV.  Hei Law and Jia Deng. 2018. CornerNet: Detecting Objects as Paired Keypoints. In ECCV.","DOI":"10.1007\/978-3-030-01264-9_45"},{"key":"e_1_3_2_2_20_1","volume-title":"BMN: Boundary-Matching Network for Temporal Action Proposal Generation. In ICCV.","author":"Lin Tianwei","year":"2019","unstructured":"Tianwei Lin , Xiao Liu , Xin Li , Errui Ding , and Shilei Wen . 2019 . BMN: Boundary-Matching Network for Temporal Action Proposal Generation. In ICCV. Tianwei Lin, Xiao Liu, Xin Li, Errui Ding, and Shilei Wen. 2019. BMN: Boundary-Matching Network for Temporal Action Proposal Generation. In ICCV."},{"key":"e_1_3_2_2_21_1","unstructured":"Bingbin Liu Serena Yeung Edward Chou De-An Huang Li Fei-Fei and Juan Carlos Niebles. 2018c. Temporal modular networks for retrieving complex compositional activities in videos. In ECCV.  Bingbin Liu Serena Yeung Edward Chou De-An Huang Li Fei-Fei and Juan Carlos Niebles. 2018c. Temporal modular networks for retrieving complex compositional activities in videos. In ECCV."},{"key":"e_1_3_2_2_22_1","unstructured":"Daqing Liu Zheng-Jun Zha Hanwang Zhang Yongdong Zhang and Feng Wu. 2018. Context-Aware Visual Policy Network for Sequence-Level Image Captioning. In ACM MM.  Daqing Liu Zheng-Jun Zha Hanwang Zhang Yongdong Zhang and Feng Wu. 2018. Context-Aware Visual Policy Network for Sequence-Level Image Captioning. In ACM MM."},{"key":"e_1_3_2_2_23_1","unstructured":"Daqing Liu Hanwang Zhang Zheng-Jun Zha and Feng Wu. 2019 b. Learning to Assemble Neural Module Tree Networks for Visual Grounding. In ICCV.  Daqing Liu Hanwang Zhang Zheng-Jun Zha and Feng Wu. 2019 b. Learning to Assemble Neural Module Tree Networks for Visual Grounding. In ICCV."},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"crossref","unstructured":"Meng Liu Xiang Wang Liqiang Nie Xiangnan He Baoquan Chen and Tat-Seng Chua. 2018a. Attentive moment retrieval in videos. In SIGIR.  Meng Liu Xiang Wang Liqiang Nie Xiangnan He Baoquan Chen and Tat-Seng Chua. 2018a. Attentive moment retrieval in videos. In SIGIR.","DOI":"10.1145\/3209978.3210003"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"crossref","unstructured":"Meng Liu Xiang Wang Liqiang Nie Qi Tian Baoquan Chen and Tat-Seng Chua. 2018b. Cross-modal moment localization in videos. In ACM MM.  Meng Liu Xiang Wang Liqiang Nie Qi Tian Baoquan Chen and Tat-Seng Chua. 2018b. Cross-modal moment localization in videos. In ACM MM.","DOI":"10.1145\/3240508.3240549"},{"key":"e_1_3_2_2_26_1","unstructured":"Xuejing Liu Liang Li Shuhui Wang Zheng-Jun Zha Dechao Meng and Qingming Huang. 2019 a. Adaptive Reconstruction Network for Weakly Supervised Referring Expression Grounding. In ICCV.  Xuejing Liu Liang Li Shuhui Wang Zheng-Jun Zha Dechao Meng and Qingming Huang. 2019 a. Adaptive Reconstruction Network for Weakly Supervised Referring Expression Grounding. In ICCV."},{"key":"e_1_3_2_2_27_1","volume-title":"DEBUG: A Dense Bottom-Up Grounding Approach for Natural Language Video Localization. In EMNLP.","author":"Lu Chujie","year":"2019","unstructured":"Chujie Lu , Long Chen , Chilie Tan , Xiaolin Li , and Jun Xiao . 2019 . DEBUG: A Dense Bottom-Up Grounding Approach for Natural Language Video Localization. In EMNLP. Chujie Lu, Long Chen, Chilie Tan, Xiaolin Li, and Jun Xiao. 2019. DEBUG: A Dense Bottom-Up Grounding Approach for Natural Language Video Localization. In EMNLP."},{"key":"e_1_3_2_2_28_1","volume-title":"Santiago Pascual, and Xavier Giro I Nieto.","author":"Montes Alberto","year":"2016","unstructured":"Alberto Montes , Amaia Salvador Aguilera , Santiago Pascual, and Xavier Giro I Nieto. 2016 . Temporal activity detection in untrimmed videos with recurrent neural networks. In NIPS. Alberto Montes, Amaia Salvador Aguilera, Santiago Pascual, and Xavier Giro I Nieto. 2016. Temporal activity detection in untrimmed videos with recurrent neural networks. In NIPS."},{"key":"e_1_3_2_2_29_1","volume-title":"Hongdong Li, and Stephen Gould.","author":"Opazo Cristian Rodriguez","year":"2020","unstructured":"Cristian Rodriguez Opazo , Edison Marresetaylor , Fatemeh Sadat Saleh , Hongdong Li, and Stephen Gould. 2020 . Proposal-free Temporal Moment Localization of a Natural-Language Query in Video using Guided Attention. In WACV. Cristian Rodriguez Opazo, Edison Marresetaylor, Fatemeh Sadat Saleh, Hongdong Li, and Stephen Gould. 2020. Proposal-free Temporal Moment Localization of a Natural-Language Query in Video using Guided Attention. In WACV."},{"key":"e_1_3_2_2_30_1","volume-title":"Glove: Global vectors for word representation. In EMNLP.","author":"Pennington Jeffrey","year":"2014","unstructured":"Jeffrey Pennington , Richard Socher , and Christopher Manning . 2014 . Glove: Global vectors for word representation. In EMNLP. Jeffrey Pennington, Richard Socher, and Christopher Manning. 2014. Glove: Global vectors for word representation. In EMNLP."},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00207"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"crossref","unstructured":"Zheng Shou Dongang Wang and Shihfu Chang. 2016. Temporal Action Localization in Untrimmed Videos via Multi-stage CNNs. In CVPR.  Zheng Shou Dongang Wang and Shihfu Chang. 2016. Temporal Action Localization in Untrimmed Videos via Multi-stage CNNs. In CVPR.","DOI":"10.1109\/CVPR.2016.119"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"crossref","unstructured":"Gunnar A. Sigurdsson G\u00fcl Varol Xiaolong Wang Ali Farhadi Ivan Laptev and Abhinav Gupta. 2016. Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding. In ECCV.  Gunnar A. Sigurdsson G\u00fcl Varol Xiaolong Wang Ali Farhadi Ivan Laptev and Abhinav Gupta. 2016. Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding. In ECCV.","DOI":"10.1007\/978-3-319-46448-0_31"},{"key":"e_1_3_2_2_34_1","volume-title":"Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman . 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 ( 2014 ). Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)."},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"crossref","unstructured":"Du Tran Lubomir Bourdev Rob Fergus Lorenzo Torresani and Manohar Paluri. 2015. Learning spatiotemporal features with 3d convolutional networks. In ICCV.  Du Tran Lubomir Bourdev Rob Fergus Lorenzo Torresani and Manohar Paluri. 2015. Learning spatiotemporal features with 3d convolutional networks. In ICCV.","DOI":"10.1109\/ICCV.2015.510"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"crossref","unstructured":"Jingwen Wang Lin Ma and Wenhao Jiang. 2020. Temporally Grounding Language Queries in Videos by Contextual Boundary-aware Prediction. In AAAI.  Jingwen Wang Lin Ma and Wenhao Jiang. 2020. Temporally Grounding Language Queries in Videos by Contextual Boundary-aware Prediction. In AAAI.","DOI":"10.1609\/aaai.v34i07.6897"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"crossref","unstructured":"Weining Wang Yan Huang and Liang Wang. 2019 a. Language-Driven Temporal Activity Localization: A Semantic Matching Reinforcement Learning Model. In CVPR.  Weining Wang Yan Huang and Liang Wang. 2019 a. Language-Driven Temporal Activity Localization: A Semantic Matching Reinforcement Learning Model. In CVPR.","DOI":"10.1109\/CVPR.2019.00042"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3326362"},{"key":"e_1_3_2_2_39_1","unstructured":"Aming Wu and Yahong Han. 2018. Multi-modal Circulant Fusion for Video-to-Language and Backward. In IJCAI.  Aming Wu and Yahong Han. 2018. Multi-modal Circulant Fusion for Video-to-Language and Backward. In IJCAI."},{"key":"e_1_3_2_2_40_1","unstructured":"Huijuan Xu Abir Das and Kate Saenko. 2017. R-C3D: Region Convolutional 3D Network for Temporal Activity Detection. In ICCV.  Huijuan Xu Abir Das and Kate Saenko. 2017. R-C3D: Region Convolutional 3D Network for Temporal Activity Detection. In ICCV."},{"key":"e_1_3_2_2_41_1","unstructured":"Huijuan Xu Kun He Bryan A Plummer Leonid Sigal Stan Sclaroff and Kate Saenko. 2019. Multilevel language and vision integration for text-to-clip retrieval. In AAAI.  Huijuan Xu Kun He Bryan A Plummer Leonid Sigal Stan Sclaroff and Kate Saenko. 2019. Multilevel language and vision integration for text-to-clip retrieval. In AAAI."},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"crossref","unstructured":"Tianhao Yang Zheng-Jun Zha and Hanwang Zhang. 2019. Making History Matter: History-Advantage Sequence Training for Visual Dialog. In ICCV.  Tianhao Yang Zheng-Jun Zha and Hanwang Zhang. 2019. Making History Matter: History-Advantage Sequence Training for Visual Dialog. In ICCV.","DOI":"10.1109\/ICCV.2019.00265"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"crossref","unstructured":"Yitian Yuan Lin Ma Jingwen Wang Wei Liu and Wenwu Zhu. 2019 a. Semantic Conditioned Dynamic Modulation for Temporal Sentence Grounding in Videos. In NIPS.  Yitian Yuan Lin Ma Jingwen Wang Wei Liu and Wenwu Zhu. 2019 a. Semantic Conditioned Dynamic Modulation for Temporal Sentence Grounding in Videos. In NIPS.","DOI":"10.1109\/TPAMI.2020.3038993"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"crossref","unstructured":"Yitian Yuan Tao Mei and Wenwu Zhu. 2019 b. To find where you talk: Temporal sentence localization in video with attention based location regression. In AAAI.  Yitian Yuan Tao Mei and Wenwu Zhu. 2019 b. To find where you talk: Temporal sentence localization in video with attention based location regression. In AAAI.","DOI":"10.1609\/aaai.v33i01.33019159"},{"key":"e_1_3_2_2_45_1","volume-title":"Context-Aware Visual Policy Network for Fine-Grained Image Captioning","author":"Zha Zheng-Jun","year":"2020","unstructured":"Zheng-Jun Zha , Daqing Liu , Hanwang Zhang , Yongdong Zhang , and Feng Wu. 2020. Context-Aware Visual Policy Network for Fine-Grained Image Captioning . IEEE Transactions on Pattern Analysis and Machine Intelligence ( 2020 ), 1--1. Zheng-Jun Zha, Daqing Liu, Hanwang Zhang, Yongdong Zhang, and Feng Wu. 2020. Context-Aware Visual Policy Network for Fine-Grained Image Captioning. IEEE Transactions on Pattern Analysis and Machine Intelligence (2020), 1--1."},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3320061"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"crossref","unstructured":"Da Zhang Xiyang Dai Xin Wang Yuan-Fang Wang and Larry S Davis. 2019 a. Man: Moment alignment network for natural language moment retrieval via iterative graph adjustment. In CVPR.  Da Zhang Xiyang Dai Xin Wang Yuan-Fang Wang and Larry S Davis. 2019 a. Man: Moment alignment network for natural language moment retrieval via iterative graph adjustment. In CVPR.","DOI":"10.1109\/CVPR.2019.00134"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"crossref","unstructured":"Songyang Zhang Houwen Peng Jianlong Fu and Jiebo Luo. 2020. Learning 2D Temporal Adjacent Networks for Moment Localization with Natural Language. In AAAI.  Songyang Zhang Houwen Peng Jianlong Fu and Jiebo Luo. 2020. Learning 2D Temporal Adjacent Networks for Moment Localization with Natural Language. In AAAI.","DOI":"10.1609\/aaai.v34i07.6984"},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"crossref","unstructured":"Songyang Zhang Jinsong Su and Jiebo Luo. 2019 c. Exploiting Temporal Relationships in Video Moment Localization with Natural Language. In ACM MM.  Songyang Zhang Jinsong Su and Jiebo Luo. 2019 c. Exploiting Temporal Relationships in Video Moment Localization with Natural Language. In ACM MM.","DOI":"10.1145\/3343031.3350879"},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"crossref","unstructured":"Zhu Zhang Zhijie Lin Zhou Zhao and Zhenxin Xiao. 2019 b. Cross-Modal Interaction Networks for Query-Based Moment Retrieval in Videos. In SIGIR.  Zhu Zhang Zhijie Lin Zhou Zhao and Zhenxin Xiao. 2019 b. Cross-Modal Interaction Networks for Query-Based Moment Retrieval in Videos. In SIGIR.","DOI":"10.1145\/3331184.3331235"},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"crossref","unstructured":"Yue Zhao Yuanjun Xiong Limin Wang Zhirong Wu Xiaoou Tang and Dahua Lin. 2017. Temporal Action Detection with Structured Segment Networks. In ICCV.  Yue Zhao Yuanjun Xiong Limin Wang Zhirong Wu Xiaoou Tang and Dahua Lin. 2017. Temporal Action Detection with Structured Segment Networks. In ICCV.","DOI":"10.1109\/ICCV.2017.317"}],"event":{"name":"MM '20: The 28th ACM International Conference on Multimedia","location":"Seattle WA USA","acronym":"MM '20","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 28th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3394171.3413975","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3394171.3413975","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T21:32:07Z","timestamp":1750195927000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3394171.3413975"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,12]]},"references-count":51,"alternative-id":["10.1145\/3394171.3413975","10.1145\/3394171"],"URL":"https:\/\/doi.org\/10.1145\/3394171.3413975","relation":{},"subject":[],"published":{"date-parts":[[2020,10,12]]},"assertion":[{"value":"2020-10-12","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}