{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T12:13:24Z","timestamp":1767183204770,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":59,"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":"Office of Naval Research","award":["N00014-20-1-2170"],"award-info":[{"award-number":["N00014-20-1-2170"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,10,12]]},"DOI":"10.1145\/3394171.3413531","type":"proceedings-article","created":{"date-parts":[[2020,10,12]],"date-time":"2020-10-12T12:27:38Z","timestamp":1602505658000},"page":"3829-3837","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["Finding Achilles' Heel"],"prefix":"10.1145","author":[{"given":"Deepak","family":"Kumar","sequence":"first","affiliation":[{"name":"University of Massachusetts Dartmouth, Dartmouth, MA, USA"}]},{"given":"Chetan","family":"Kumar","sequence":"additional","affiliation":[{"name":"University of Massachusetts Dartmouth, Dartmouth, MA, USA"}]},{"given":"Chun Wei","family":"Seah","sequence":"additional","affiliation":[{"name":"University of Massachusetts, Dartmouth, MA, USA"}]},{"given":"Siyu","family":"Xia","sequence":"additional","affiliation":[{"name":"Southeast University, Nanjing, China"}]},{"given":"Ming","family":"Shao","sequence":"additional","affiliation":[{"name":"University of Massachusetts Dartmouth, Dartmouth, MA, USA"}]}],"member":"320","published-online":{"date-parts":[[2020,10,12]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"Qingyao Ai N. Daniel Hill V. N. S. Vishwanathan and Bruce W. Croft. 2019. A Zero Attention Model for Personalized Product Search. In ACM CIKM.  Qingyao Ai N. Daniel Hill V. N. S. Vishwanathan and Bruce W. Croft. 2019. A Zero Attention Model for Personalized Product Search. In ACM CIKM."},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2807385"},{"key":"e_1_3_2_2_3_1","unstructured":"Dzmitry Bahdanau Kyunghyun Cho and Yoshua Bengio. 2014. Neural machine translation by jointly learning to align and translate. arXiv (2014).  Dzmitry Bahdanau Kyunghyun Cho and Yoshua Bengio. 2014. Neural machine translation by jointly learning to align and translate. arXiv (2014)."},{"key":"e_1_3_2_2_4_1","unstructured":"Aleksandar Bojchevski and Stephan G\u00fcnnemann. 2019. Adversarial Attacks on Node Embeddings via Graph Poisoning. In ICML.  Aleksandar Bojchevski and Stephan G\u00fcnnemann. 2019. Adversarial Attacks on Node Embeddings via Graph Poisoning. In ICML."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"crossref","unstructured":"Joao Carreira and Andrew Zisserman. 2017. Quo vadis action recognition? a new model and the kinetics dataset. In IEEE CVPR.  Joao Carreira and Andrew Zisserman. 2017. Quo vadis action recognition? a new model and the kinetics dataset. In IEEE CVPR.","DOI":"10.1109\/CVPR.2017.502"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"crossref","unstructured":"Yinpeng Dong Fangzhou Liao Tianyu Pang Hang Su Jun Zhu Xiaolin Hu and Jianguo Li. 2018. Boosting Adversarial Attacks with Momentum. In IEEE CVPR.  Yinpeng Dong Fangzhou Liao Tianyu Pang Hang Su Jun Zhu Xiaolin Hu and Jianguo Li. 2018. Boosting Adversarial Attacks with Momentum. In IEEE CVPR.","DOI":"10.1109\/CVPR.2018.00957"},{"key":"e_1_3_2_2_7_1","first-page":"363","article-title":"Attention-Based Multiview Re-Observation Fusion Network for Skeletal Action Recognition","volume":"21","author":"Fan Zhaoxuan","year":"2018","journal-title":"IEEE TMM"},{"volume-title":"ICLR","author":"Goodfellow Ian","key":"e_1_3_2_2_8_1"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"crossref","unstructured":"Leo Hemamou Ghazi Felhi Vincent Vandenbussche Jean-Claude Martin and Chlo\u00e9 Clavel. 2019. HireNet: A Hierarchical Attention Model for the Automatic Analysis of Asynchronous Video Job Interviews. In AAAI.  Leo Hemamou Ghazi Felhi Vincent Vandenbussche Jean-Claude Martin and Chlo\u00e9 Clavel. 2019. HireNet: A Hierarchical Attention Model for the Automatic Analysis of Asynchronous Video Job Interviews. In AAAI.","DOI":"10.1109\/ACII.2019.8925439"},{"volume-title":"CVPR Workshops.","year":"2019","author":"Huang Tsung-Wei","key":"e_1_3_2_2_10_1"},{"key":"e_1_3_2_2_11_1","unstructured":"Yanli Ji Feixiang Xu Yang Yang Ning Xie Heng Tao Shen and Tatsuya Harada. 2019. Attention Transfer (ANT) Network for View-Invariant Action Recognition. In ACM MM.  Yanli Ji Feixiang Xu Yang Yang Ning Xie Heng Tao Shen and Tatsuya Harada. 2019. Attention Transfer (ANT) Network for View-Invariant Action Recognition. In ACM MM."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"crossref","unstructured":"Linxi Jiang Xingjun Ma Shaoxiang Chen James Bailey and Yu-Gang Jiang. 2019. Black-box Adversarial Attacks on Video Recognition Models. arXiv (2019).  Linxi Jiang Xingjun Ma Shaoxiang Chen James Bailey and Yu-Gang Jiang. 2019. Black-box Adversarial Attacks on Video Recognition Models. arXiv (2019).","DOI":"10.1145\/3343031.3351088"},{"key":"e_1_3_2_2_13_1","unstructured":"F. Karim S. Majumdar and H. Darabi. 2020. Adversarial Attacks on Time Series. IEEE TPAMI (2020).  F. Karim S. Majumdar and H. Darabi. 2020. Adversarial Attacks on Time Series. IEEE TPAMI (2020)."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"crossref","unstructured":"Evangelos Kazakos Arsha Nagrani Andrew Zisserman and Dima Damen. 2019. EPIC-Fusion: Audio-Visual Temporal Binding for Egocentric Action Recognition. In ICCV.  Evangelos Kazakos Arsha Nagrani Andrew Zisserman and Dima Damen. 2019. EPIC-Fusion: Audio-Visual Temporal Binding for Egocentric Action Recognition. In ICCV.","DOI":"10.1109\/ICCV.2019.00559"},{"volume-title":"ICLR","year":"2017","author":"Kurakin Alexey","key":"e_1_3_2_2_15_1"},{"key":"e_1_3_2_2_16_1","unstructured":"Dong Li Ting Yao Zhaofan Qiu Houqiang Li and Tao Mei. 2019. Long Short-Term Relation Networks for Video Action Detection. In ACM MM.  Dong Li Ting Yao Zhaofan Qiu Houqiang Li and Tao Mei. 2019. Long Short-Term Relation Networks for Video Action Detection. In ACM MM."},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"crossref","unstructured":"Linghui Li Sheng Tang Lixi Deng Yongdong Zhang and Qi Tian. 2017. Image caption with global-local attention. In AAAI.  Linghui Li Sheng Tang Lixi Deng Yongdong Zhang and Qi Tian. 2017. Image caption with global-local attention. In AAAI.","DOI":"10.1609\/aaai.v31i1.11236"},{"key":"e_1_3_2_2_18_1","unstructured":"Shasha Li Ajaya Neupane Sujoy Paul Chengyu Song Srikanth V Krishnamurthy Amit K Roy Chowdhury and Ananthram Swami. 2018. Adversarial perturbations against real-time video classification systems. arXiv preprint arXiv:1807.00458 (2018).  Shasha Li Ajaya Neupane Sujoy Paul Chengyu Song Srikanth V Krishnamurthy Amit K Roy Chowdhury and Ananthram Swami. 2018. Adversarial perturbations against real-time video classification systems. arXiv preprint arXiv:1807.00458 (2018)."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"crossref","unstructured":"Junwei Liang Lu Jiang Liangliang Cao Li-Jia Li and Alexander Hauptmann. 2018. Focal Visual-Text Attention for Visual Question Answering. In CVPR.  Junwei Liang Lu Jiang Liangliang Cao Li-Jia Li and Alexander Hauptmann. 2018. Focal Visual-Text Attention for Visual Question Answering. In CVPR.","DOI":"10.1109\/CVPR.2018.00642"},{"key":"e_1_3_2_2_20_1","unstructured":"Chunhui Liu Yueyu Hu Yanghao Li Sijie Song and Jiaying Liu. 2017. PKU-MMD: A large scale benchmark for continuous multi-modal human action understanding. arXiv preprint arXiv:1703.07475 (2017).  Chunhui Liu Yueyu Hu Yanghao Li Sijie Song and Jiaying Liu. 2017. PKU-MMD: A large scale benchmark for continuous multi-modal human action understanding. arXiv preprint arXiv:1703.07475 (2017)."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"crossref","unstructured":"Jun Liu Amir Shahroudy Mauricio Perez Gang Wang Ling-Yu Duan and Alex C. Kot. 2019 c. NTU RGBD 120: A Large-Scale Benchmark for 3D Human Activity Understanding. IEEE TPAMI (2019). https:\/\/doi.org\/10.1109\/TPAMI.2019.2916873  Jun Liu Amir Shahroudy Mauricio Perez Gang Wang Ling-Yu Duan and Alex C. Kot. 2019 c. NTU RGBD 120: A Large-Scale Benchmark for 3D Human Activity Understanding. IEEE TPAMI (2019). https:\/\/doi.org\/10.1109\/TPAMI.2019.2916873","DOI":"10.1109\/TPAMI.2019.2916873"},{"key":"e_1_3_2_2_22_1","volume-title":"RGB-D Action Recognition Using Multimodal Correlative Representation Learning Model. IEEE Sensors","volume":"19","author":"Liu Tianshan","year":"2019"},{"key":"e_1_3_2_2_23_1","unstructured":"Ziming Liu Guangyu Gao A. K. Qin Tong Wu and Chi Harold Liu. 2019 a. Action Recognition with Bootstrapping Based Long-Range Temporal Context Attention. In ACM MM.  Ziming Liu Guangyu Gao A. K. Qin Tong Wu and Chi Harold Liu. 2019 a. Action Recognition with Bootstrapping Based Long-Range Temporal Context Attention. In ACM MM."},{"key":"e_1_3_2_2_24_1","unstructured":"Jiasen Lu Jianwei Yang Dhruv Batra and Devi Parikh. 2016. Hierarchical Question-Image Co-Attention for Visual Question Answering. In NIPS.  Jiasen Lu Jianwei Yang Dhruv Batra and Devi Parikh. 2016. Hierarchical Question-Image Co-Attention for Visual Question Answering. In NIPS."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"crossref","unstructured":"Minh-Thang Luong Hieu Pham and Christopher D Manning. 2015. Effective approaches to attention-based neural machine translation. arXiv (2015).  Minh-Thang Luong Hieu Pham and Christopher D Manning. 2015. Effective approaches to attention-based neural machine translation. arXiv (2015).","DOI":"10.18653\/v1\/D15-1166"},{"key":"e_1_3_2_2_26_1","unstructured":"Chen Ma Chenxu Zhao Hailin Shi Li Chen Jun-Hai Yong and Dan Zeng. 2019. MetaAdvDet: Towards Robust Detection of Evolving Adversarial Attacks. In ACM MM.  Chen Ma Chenxu Zhao Hailin Shi Li Chen Jun-Hai Yong and Dan Zeng. 2019. MetaAdvDet: Towards Robust Detection of Evolving Adversarial Attacks. In ACM MM."},{"key":"e_1_3_2_2_27_1","unstructured":"Jonghwan Mun Minsu Cho and Bohyung Han. 2017. Text-guided attention model for image captioning. In AAAI.  Jonghwan Mun Minsu Cho and Bohyung Han. 2017. Text-guided attention model for image captioning. In AAAI."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2896880"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"crossref","unstructured":"Andras Rozsa Ethan M. Rudd and Terrance E. Boult. 2016. Adversarial Diversity and Hard Positive Generation. In CVPRWorkshops.  Andras Rozsa Ethan M. Rudd and Terrance E. Boult. 2016. Adversarial Diversity and Hard Positive Generation. In CVPRWorkshops.","DOI":"10.1109\/CVPRW.2016.58"},{"volume-title":"NTU RGBD: A Large Scale Dataset for 3D Human Activity Analysis. In CVPR.","year":"2016","author":"Shahroudy Amir","key":"e_1_3_2_2_30_1"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2691321"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"crossref","unstructured":"Amir Shahroudy Gang Wang and Tian-Tsong Ng. 2014. Multi-modal feature fusion for action recognition in rgb-d sequences. In ISCCSP.  Amir Shahroudy Gang Wang and Tian-Tsong Ng. 2014. Multi-modal feature fusion for action recognition in rgb-d sequences. In ISCCSP.","DOI":"10.1109\/ISCCSP.2014.6877819"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"crossref","unstructured":"Sijie Song Cuiling Lan Junliang Xing Wenjun Zeng and Jiaying Liu. 2017. An end-to-end spatio-temporal attention model for human action recognition from skeleton data. In AAAI.  Sijie Song Cuiling Lan Junliang Xing Wenjun Zeng and Jiaying Liu. 2017. An end-to-end spatio-temporal attention model for human action recognition from skeleton data. In AAAI.","DOI":"10.1609\/aaai.v31i1.11212"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRCICN.2018.8718718"},{"key":"e_1_3_2_2_35_1","unstructured":"Ilya Sutskever Oriol Vinyals and Quoc V Le. 2014. Sequence to sequence learning with neural networks. In Advances in neural information processing systems. 3104--3112.  Ilya Sutskever Oriol Vinyals and Quoc V Le. 2014. Sequence to sequence learning with neural networks. In Advances in neural information processing systems. 3104--3112."},{"key":"e_1_3_2_2_36_1","unstructured":"Christian Szegedy Wojciech Zaremba Ilya Sutskever Joan Bruna Dumitru Erhan Ian Goodfellow and Rob Fergus. 2013. Intriguing properties of neural networks. arXiv preprint arXiv:1312.6199 (2013).  Christian Szegedy Wojciech Zaremba Ilya Sutskever Joan Bruna Dumitru Erhan Ian Goodfellow and Rob Fergus. 2013. Intriguing properties of neural networks. arXiv preprint arXiv:1312.6199 (2013)."},{"key":"e_1_3_2_2_37_1","unstructured":"Florian Tram\u00e8 r Alexey Kurakin Nicolas Papernot Ian J. Goodfellow Dan Boneh and Patrick D. McDaniel. 2018. Ensemble Adversarial Training: Attacks and Defenses. In ICLR.  Florian Tram\u00e8 r Alexey Kurakin Nicolas Papernot Ian J. Goodfellow Dan Boneh and Patrick D. McDaniel. 2018. Ensemble Adversarial Training: Attacks and Defenses. In ICLR."},{"key":"e_1_3_2_2_38_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez \u0141 ukasz Kaiser and Illia Polosukhin. 2017. Attention is All you Need. In NIPS.  Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez \u0141 ukasz Kaiser and Illia Polosukhin. 2017. Attention is All you Need. In NIPS."},{"volume-title":"Graph Attention Networks. International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=rJXMpikCZ","year":"2018","author":"Petar Velivc","key":"e_1_3_2_2_39_1"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"crossref","unstructured":"Lichen Wang Zhengming Ding Zhiqiang Tao Yunyu Liu and Yun Fu. 2019. Generative Multi-View Human Action Recognition. In ICCV.  Lichen Wang Zhengming Ding Zhiqiang Tao Yunyu Liu and Yun Fu. 2019. Generative Multi-View Human Action Recognition. In ICCV.","DOI":"10.1109\/ICCV.2019.00631"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"crossref","unstructured":"Lichen Wang Bin Sun Joseph Robinson Taotao Jing and Yun Fu. 2020. EV-Action: Electromyography-Vision Multi-Modal Action Dataset. In IEEE FG.  Lichen Wang Bin Sun Joseph Robinson Taotao Jing and Yun Fu. 2020. EV-Action: Electromyography-Vision Multi-Modal Action Dataset. In IEEE FG.","DOI":"10.1109\/FG47880.2020.00018"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2018.04.007"},{"key":"e_1_3_2_2_43_1","unstructured":"Xingxing Wei Jun Zhu and Hang Su. 2018. Sparse adversarial perturbations for videos. arXiv (2018).  Xingxing Wei Jun Zhu and Hang Su. 2018. Sparse adversarial perturbations for videos. arXiv (2018)."},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"crossref","unstructured":"Yinwei Wei Xiang Wang Liqiang Nie Xiangnan He Richang Hong and Tat-Seng Chua. 2019 b. MMGCN: Multi-modal Graph Convolution Network for Personalized Recommendation of Micro-video. In ACM MM.  Yinwei Wei Xiang Wang Liqiang Nie Xiangnan He Richang Hong and Tat-Seng Chua. 2019 b. MMGCN: Multi-modal Graph Convolution Network for Personalized Recommendation of Micro-video. In ACM MM.","DOI":"10.1145\/3343031.3351034"},{"key":"e_1_3_2_2_45_1","unstructured":"Zhipeng Wei Jingjing Chen Xingxing Wei Linxi Jiang Tat-Seng Chua Fengfeng Zhou and Yu-Gang Jiang. 2019 a. Heuristic Black-box Adversarial Attacks on Video Recognition Models. arXiv preprint arXiv:1911.09449 (2019).  Zhipeng Wei Jingjing Chen Xingxing Wei Linxi Jiang Tat-Seng Chua Fengfeng Zhou and Yu-Gang Jiang. 2019 a. Heuristic Black-box Adversarial Attacks on Video Recognition Models. arXiv preprint arXiv:1911.09449 (2019)."},{"key":"e_1_3_2_2_46_1","unstructured":"Huijun Wu Chen Wang Yuriy Tyshetskiy Andrew Docherty Kai Lu and Liming Zhu. 2019 a. Adversarial Examples for Graph Data: Deep Insights into Attack and Defense. In IJCAI.  Huijun Wu Chen Wang Yuriy Tyshetskiy Andrew Docherty Kai Lu and Liming Zhu. 2019 a. Adversarial Examples for Graph Data: Deep Insights into Attack and Defense. In IJCAI."},{"key":"e_1_3_2_2_47_1","unstructured":"Haoze Wu Zheng-Jun Zha Xin Wen Zhenzhong Chen Dong Liu and Xuejin Chen. 2019 b. Cross-Fiber Spatial-Temporal Co-Enhanced Networks for Video Action Recognition. In ACM MM.  Haoze Wu Zheng-Jun Zha Xin Wen Zhenzhong Chen Dong Liu and Xuejin Chen. 2019 b. Cross-Fiber Spatial-Temporal Co-Enhanced Networks for Video Action Recognition. In ACM MM."},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"crossref","unstructured":"B. Xu Y. Zheng H. Ye C. Wu H. Wang and G. Sun. 2019. Video Emotion Recognition with Concept Selection. In IEEE ICME.  B. Xu Y. Zheng H. Ye C. Wu H. Wang and G. Sun. 2019. Video Emotion Recognition with Concept Selection. In IEEE ICME.","DOI":"10.1109\/ICME.2019.00077"},{"key":"e_1_3_2_2_49_1","unstructured":"Kelvin Xu Jimmy Ba Ryan Kiros Kyunghyun Cho Aaron Courville Ruslan Salakhudinov Rich Zemel and Yoshua Bengio. 2015. Show attend and tell: Neural image caption generation with visual attention. In ICML.  Kelvin Xu Jimmy Ba Ryan Kiros Kyunghyun Cho Aaron Courville Ruslan Salakhudinov Rich Zemel and Yoshua Bengio. 2015. Show attend and tell: Neural image caption generation with visual attention. In ICML."},{"key":"e_1_3_2_2_50_1","unstructured":"Wanru Xu Jian Yu Zhenjiang Miao Lili Wan and Qiang Ji. 2019. Prediction-CGAN: Human Action Prediction with Conditional Generative Adversarial Networks. In ACM MM.  Wanru Xu Jian Yu Zhenjiang Miao Lili Wan and Qiang Ji. 2019. Prediction-CGAN: Human Action Prediction with Conditional Generative Adversarial Networks. In ACM MM."},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"crossref","unstructured":"X. Xu T. Wang Y. Yang L. Zuo F. Shen and H. T. Shen. 2020. Cross-Modal Attention With Semantic Consistence for Image-Text Matching. IEEE TNNLS (2020).  X. Xu T. Wang Y. Yang L. Zuo F. Shen and H. T. Shen. 2020. Cross-Modal Attention With Semantic Consistence for Image-Text Matching. IEEE TNNLS (2020).","DOI":"10.1109\/TNNLS.2020.2967597"},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2924576"},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"crossref","unstructured":"M. Yu W. Zhang Q. Zeng C. Wang and J. Li. 2019. Human-Object Contour for Action Recognition with Attentional Multi-modal Fusion Network. In ICAIIC.  M. Yu W. Zhang Q. Zeng C. Wang and J. Li. 2019. Human-Object Contour for Action Recognition with Attentional Multi-modal Fusion Network. In ICAIIC.","DOI":"10.1109\/ICAIIC.2019.8669069"},{"volume-title":"Adversarial Examples: Attacks and Defenses for Deep Learning","year":"2019","author":"Yuan X.","key":"e_1_3_2_2_54_1"},{"volume-title":"Muvan: A multi-view attention network for multivariate temporal data. In ICDM.","year":"2018","author":"Yuan Ye","key":"e_1_3_2_2_55_1"},{"key":"e_1_3_2_2_56_1","unstructured":"Haokui Zhang Ying Li Peng Wang Yu Liu and etal 2018. RGB-D Based Action Recognition with Light-weight 3D Convolutional Networks. arXiv (2018).  Haokui Zhang Ying Li Peng Wang Yu Liu and et al. 2018. RGB-D Based Action Recognition with Light-weight 3D Convolutional Networks. arXiv (2018)."},{"key":"e_1_3_2_2_57_1","doi-asserted-by":"crossref","unstructured":"Shichuan Zhang Zengming Tang Hao Pan Xinyu Wei and Jun Huang. 2019. A Hierarchical Framwork with Improved Loss for Large-scale Multi-modal Video Identification. In ACM MM.  Shichuan Zhang Zengming Tang Hao Pan Xinyu Wei and Jun Huang. 2019. A Hierarchical Framwork with Improved Loss for Large-scale Multi-modal Video Identification. In ACM MM.","DOI":"10.1145\/3343031.3356074"},{"key":"e_1_3_2_2_58_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3374217","article-title":"Adversarial Attacks on Deep-learning Models in Natural Language Processing: A Survey","volume":"11","author":"Zhang Wei Emma","year":"2020","journal-title":"ACM TIST"},{"key":"e_1_3_2_2_59_1","doi-asserted-by":"crossref","unstructured":"Daniel Z\u00fcgner and Stephan G\u00fcnnemann. 2019. Adversarial Attacks on Graph Neural Networks via Meta Learning. In ICLR.  Daniel Z\u00fcgner and Stephan G\u00fcnnemann. 2019. Adversarial Attacks on Graph Neural Networks via Meta Learning. In ICLR.","DOI":"10.24963\/ijcai.2019\/872"}],"event":{"name":"MM '20: The 28th ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Seattle WA USA","acronym":"MM '20"},"container-title":["Proceedings of the 28th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3394171.3413531","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3394171.3413531","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3394171.3413531","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:47:13Z","timestamp":1750193233000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3394171.3413531"}},"subtitle":["Adversarial Attack on Multi-modal Action Recognition"],"short-title":[],"issued":{"date-parts":[[2020,10,12]]},"references-count":59,"alternative-id":["10.1145\/3394171.3413531","10.1145\/3394171"],"URL":"https:\/\/doi.org\/10.1145\/3394171.3413531","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"}}]}}