{"type":"ScholarlyArticle","title":"How Unlabeled Web Videos Help Complex Event Detection?","authors":[{"name":"Huan Liu","slug":"huan-liu","given":"Huan","family":"Liu","affiliation":"MOEKLINNS Lab , Department of Computer Science , Xi'an Jiaotong University , Shaanxi , China"},{"name":"Qinghua Zheng","slug":"qinghua-zheng","given":"Qinghua","family":"Zheng","affiliation":"MOEKLINNS Lab , Department of Computer Science , Xi'an Jiaotong University , Shaanxi , China"},{"name":"Minnan Luo","slug":"minnan-luo","given":"Minnan","family":"Luo","affiliation":"MOEKLINNS Lab , Department of Computer Science , Xi'an Jiaotong University , Shaanxi , China"},{"name":"Dingwen Zhang","slug":"dingwen-zhang","given":"Dingwen","family":"Zhang","affiliation":"School of Automation , Northwestern Polytechnical University , Shaanxi , China"},{"name":"Xiaojun Chang","slug":"xiaojun-chang","given":"Xiaojun","family":"Chang","affiliation":"School of Computer Science , Carnegie Mellon University , PA , USA"},{"name":"Cheng Deng","slug":"cheng-deng","given":"Cheng","family":"Deng","affiliation":"School of Electronic Engineering , Xidian University , Shaanxi , China"}],"abstract":"The lack of labeled exemplars is an important factor that makes the task of multimedia event detection (MED) complicated and challenging. Utilizing artificially picked and labeled external sources is an effective way to enhance the performance of MED. However, building these data usually requires professional human annotators, and the procedure is too time-consuming and costly to scale. In this paper, we propose a new robust dictionary learning framework for complex event detection, which is able to handle both labeled and easy-to-get unlabeled web videos by sharing the same dictionary. By employing the lq-norm based loss jointly with the structured sparsity based regularization, our model shows strong robustness against the substantial noisy and outlier videos from open source. We exploit an effective optimization algorithm to solve the proposed highly non-smooth and non-convex problem. Extensive experiment results over standard datasets of TRECVID MEDTest 2013 and TRECVID MEDTest 2014 demonstrate the effectiveness and superiority of the proposed framework on complex event detection.","doi":"10.24963/ijcai.2017/564","url":"https://ijcai.org/proceedings/2017/564","pdf":"https://ijcai.org/proceedings/2017/0564.pdf","markdown":"https://ijcai.org/proceedings/2017/564.md","bibtex":"https://ijcai.org/proceedings/2017/bibtex/564","volume":{"slug":"2017","title":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2017","url":"https://ijcai.org/proceedings/2017/","year":2017,"location":"Melbourne, Australia","dates":"19-25 August 2017","editors":"Carles Sierra","isbn":"978-0-9992411-0-3","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2017"},"section":"Natural Language Processing","track":"Main track","number":564,"pages":{"first":4040,"last":4046},"keywords":["Natural Language Processing: Information Retrieval","Robotics and Vision: Vision and Perception"],"videos":[],"references":[{"position":1,"raw":"[Amini and Gallinari, 2002] Massih-Reza Amini and Patrick Galli- nari. The use of unlabeled data to improve supervised learning for text summarization. In SIGIR, 2002.","title":"The use of unlabeled data to improve supervised learning for text summarization","authors":"Massih-Reza Amini, Patrick Gallinari","year":"2002","venue":"SIGIR","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Chang et al., 2014] Xiaojun Chang, Feiping Nie, Yi Yang, and Heng Huang. A convex formulation for semi-supervised multi- label feature selection. In AAAI, 2014.","title":"A convex formulation for semi-supervised multilabel feature selection","authors":"Xiaojun Chang, Feiping Nie, Yi Yang, Heng Huang","year":"2014","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Chang et al., 2015a] Xiaojun Chang, Yi Yang, Alexander Haupt- mann, Eric P Xing, and Yao-Liang Yu. Semantic concept discov- ery for large-scale zero-shot event detection. In IJCAI, 2015.","title":"Semantic concept discovery for large-scale zero-shot event detection","authors":"Chang","year":"2015","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2015/316"},{"position":4,"raw":"[Chang et al., 2015b] Xiaojun Chang, Yi Yang, Eric P. Xing, and Yaoliang Yu. Complex event detection using semantic saliency and nearly-isotonic SVM. In ICML, 2015.","title":"Complex event detection using semantic saliency and nearly-isotonic SVM","authors":"Chang","year":"2015","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Chang et al., 2015c] Xiaojun Chang, Yao-Liang Yu, Yi Yang, and Alexander G Hauptmann. Searching persuasively: Joint event detection and evidence recounting with limited supervision. In ACM MM, 2015.","title":"Searching persuasively: Joint event detection and evidence recounting with limited supervision","authors":"Chang","year":"2015","venue":"ACM MM","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Chang et al., 2017] Xiaojun Chang, Zhigang Ma, Yi Yang, Zhiqiang Zeng, and Alexander G. Hauptmann. Bi-level seman- tic representation analysis for multimedia event detection. IEEE Trans. Cybernetics, 47(5):1180-1197, 2017.","title":"Bi-level semantic representation analysis for multimedia event detection","authors":"Xiaojun Chang, Zhigang Ma, Yi Yang, Zhiqiang Zeng, Alexander G Hauptmann","year":"2017","venue":"IEEE Trans. Cybernetics","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Duan et al., 2012] Lixin Duan, Dong Xu, Ivor Wai-Hung Tsang, and Jiebo Luo. Visual event recognition in videos by learn- ing from web data. IEEE Trans. Pattern Anal. Mach. Intell., 34(9):1667-1680, 2012.","title":"Visual event recognition in videos by learning from web data","authors":"Lixin Duan, Dong Xu, Ivor Wai-Hung, Jiebo Tsang, Luo","year":"2012","venue":"IEEE Trans. Pattern Anal. Mach. Intell","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Habibian et al., 2014] Amirhossein Habibian, Thomas Mensink, and Cees GM Snoek. Videostory: A new multimedia embed- ding for few-example recognition and translation of events. In ACM MM, 2014.","title":"Videostory: A new multimedia embedding for few-example recognition and translation of events","authors":"Habibian","year":"2014","venue":"ACM MM","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Hauptmann et al., 2007] Alexander Hauptmann, Rong Yan, Wei- Hao Lin, Michael Christel, and Howard Wactlar. Can high-level concepts fill the semantic gap in video retrieval? a case study with broadcast news. IEEE Trans. Multimedia, 9(5):958-966, 2007.","title":"Can high-level concepts fill the semantic gap in video retrieval? a case study with broadcast news","authors":"Alexander Hauptmann, Rong Yan, Wei-Hao Lin, Michael Christel, Howard Wactlar","year":"2007","venue":"IEEE Trans. Multimedia","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Jalali et al., 2010] Ali Jalali, Pradeep Ravikumar, Sujay Sanghavi, and Chao Ruan. A dirty model for multi-task learning. In NIPS, 2010.","title":"A dirty model for multi-task learning","authors":"Ali Jalali, Pradeep Ravikumar, Sujay Sanghavi, Chao Ruan","year":"2010","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Jiang et al., 2015] Wenhao Jiang, Feiping Nie, and Heng Huang. Robust dictionary learning with capped ℓ1-norm. In IJCAI, 2015.","title":"Robust dictionary learning with capped ℓ1-norm","authors":"Wenhao Jiang, Feiping Nie, Heng Huang","year":"2015","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2015/505"},{"position":12,"raw":"[Liang et al., 2015] Xiaodan Liang, Si Liu, Yunchao Wei, Luoqi Liu, Liang Lin, and Shuicheng Yan. Towards computational baby learning: A weakly-supervised approach for object detection. In ICCV, 2015.","title":"Towards computational baby learning: A weakly-supervised approach for object detection","authors":"Xiaodan Liang, Si Liu, Yunchao Wei, Luoqi Liu, Liang Lin, Shuicheng Yan","year":"2015","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Liu et al., 2016] Tianzhu Liu, Yanfeng Gu, Xiuping Jia, Jón Atli Benediktsson, and Jocelyn Chanussot. Class-specific sparse multiple kernel learning for spectral-spatial hyperspectral image classification. IEEE Trans. Geosci. Remote Sens., 54(12):7351- 7365, 2016.","title":"Class-specific sparse multiple kernel learning for spectral-spatial hyperspectral image classification","authors":"Tianzhu Liu, Yanfeng Gu, Xiuping Jia, Jón Atli Benediktsson, Jocelyn Chanussot","year":"2016","venue":"IEEE Trans. Geosci. Remote Sens","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Luo et al., 2011] Jie Luo, Tatiana Tommasi, and Barbara Caputo. Multiclass transfer learning from unconstrained priors. In ICCV, 2011.","title":"Multiclass transfer learning from unconstrained priors","authors":"Jie Luo, Tatiana Tommasi, Barbara Caputo","year":"2011","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Luo et al., 2017] Minnan Luo, Xiaojun Chang, Liqiang Nie, Yi Yang, Alexander G Hauptmann, and Qinghua Zheng. An adaptive semisupervised feature analysis for video semantic recognition. IEEE Trans. Cybern., PP(99):1-13, 2017.","title":"An adaptive semisupervised feature analysis for video semantic recognition","authors":"Luo","year":"2017","venue":"IEEE Trans. Cybern","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Mairal et al., 2009a] Julien Mairal, Francis Bach, Jean Ponce, and Guillermo Sapiro. Online dictionary learning for sparse coding. In ICML, 2009.","title":"Online dictionary learning for sparse coding","authors":"Mairal","year":"2009","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Mairal et al., 2009b] Julien Mairal, Jean Ponce, Guillermo Sapiro, Andrew Zisserman, and Francis R Bach. Supervised dictionary learning. In NIPS, 2009.","title":"Supervised dictionary learning","authors":"Mairal","year":"2009","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Misra et al., 2015] Ishan Misra, Abhinav Shrivastava, and Martial Hebert. Watch and learn: Semi-supervised learning for object detectors from video. In CVPR, 2015.","title":"Watch and learn: Semi-supervised learning for object detectors from video","authors":"Ishan Misra, Abhinav Shrivastava, Martial Hebert","year":"2015","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Natarajan et al., 2012] Pradeep Natarajan, Shuang Wu, Shiv Vita- ladevuni, Xiaodan Zhuang, Stavros Tsakalidis, Unsang Park, Ro- hit Prasad, and Premkumar Natarajan. Multimodal feature fusion for robust event detection in web videos. In CVPR, 2012.","title":"Multimodal feature fusion for robust event detection in web videos","authors":"Pradeep Natarajan, Shuang Wu, Shiv Vitaladevuni, Xiaodan Zhuang, Stavros Tsakalidis, Unsang Park, Rohit Prasad, Premkumar Natarajan","year":"2012","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Nie et al., 2010] Feiping Nie, Heng Huang, Xiao Cai, and Chris H Ding. Efficient and robust feature selection via joint ℓ2,1-norms minimization. In NIPS, 2010.","title":"Efficient and robust feature selection via joint ℓ2,1-norms minimization","authors":"Feiping Nie, Heng Huang, Xiao Cai, Chris H Ding","year":"2010","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Raina et al., 2007] Rajat Raina, Alexis Battle, Honglak Lee, Ben- jamin Packer, and Andrew Y Ng. Self-taught learning: transfer learning from unlabeled data. In ICML, 2007.","title":"Self-taught learning: transfer learning from unlabeled data","authors":"Rajat Raina, Alexis Battle, Honglak Lee, Benjamin Packer, Andrew Y Ng","year":"2007","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Ramirez et al., 2010] Ignacio Ramirez, Pablo Sprechmann, and Guillermo Sapiro. Classification and clustering via dictionary learning with structured incoherence and shared features. In CVPR, 2010.","title":"Classification and clustering via dictionary learning with structured incoherence and shared features","authors":"Ignacio Ramirez, Pablo Sprechmann, Guillermo Sapiro","year":"2010","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Sadanand and Corso, 2012] Sreemanananth Sadanand and Jason J Corso. Action bank: A high-level representation of activity in video. In CVPR, 2012.","title":"Action bank: A high-level representation of activity in video","authors":"Corso Sadanand, Sreemanananth Sadanand, Jason J Corso","year":"2012","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Snoek et al., 2006] Cees GM Snoek, Marcel Worring, Jan C Van Gemert, Jan-Mark Geusebroek, and Arnold WM Smeulders. The challenge problem for automated detection of 101 semantic concepts in multimedia. In ACM MM, 2006.","title":"The challenge problem for automated detection of 101 semantic concepts in multimedia","authors":"G M Cees, Marcel Snoek, Jan C Worring, Jan-Mark Van Gemert, Arnold Wm Geusebroek, Smeulders","year":"2006","venue":"ACM MM","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Tamrakar et al., 2012] Amir Tamrakar, Saad Ali, Qian Yu, Jingen Liu, Omar Javed, Ajay Divakaran, Hui Cheng, and Harpreet Sawhney. Evaluation of low-level features and their combinations for complex event detection in open source videos. In CVPR, 2012.","title":"Evaluation of low-level features and their combinations for complex event detection in open source videos","authors":"Amir Tamrakar, Saad Ali, Qian Yu, Jingen Liu, Omar Javed, Ajay Divakaran, Hui Cheng, Harpreet Sawhney","year":"2012","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Thomee et al., 2016] Bart Thomee, David A. Shamma, Gerald Friedland, Benjamin Elizalde, Karl Ni, Douglas Poland, Damian Borth, and Li-Jia Li. YFCC100M: the new data in multimedia research. Commun. ACM, 59(2):64-73, 2016.","title":"YFCC100M: the new data in multimedia research","authors":"Bart Thomee, David A Shamma, Gerald Friedland, Benjamin Elizalde, Karl Ni, Douglas Poland, Damian Borth, Li-Jia Li","year":"2016","venue":"Commun. ACM","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Vahdat et al., 2013] Arash Vahdat, Kevin J. Cannons, Greg Mori, Sangmin Oh, and Ilseo Kim. Compositional models for video event detection: A multiple kernel learning latent variable ap- proach. In ICCV, 2013.","title":"Compositional models for video event detection: A multiple kernel learning latent variable approach","authors":"Arash Vahdat, Kevin J Cannons, Greg Mori, Sangmin Oh, Ilseo Kim","year":"2013","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Wang et al., 2013] Hua Wang, Feiping Nie, Weidong Cai, and Heng Huang. Semi-supervised robust dictionary learning via ef- ficient ℓ 2,0 + -norms minimization. In ICCV, 2013.","title":"Semi-supervised robust dictionary learning via efficient ℓ 2,0 + -norms minimization","authors":"Hua Wang, Feiping Nie, Weidong Cai, Heng Huang","year":"2013","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Wang et al., 2015] Hua Wang, Feiping Nie, and Heng Huang. Learning robust locality preserving projection via p-order min- imization. In AAAI, 2015.","title":"Learning robust locality preserving projection via p-order minimization","authors":"Hua Wang, Feiping Nie, Heng Huang","year":"2015","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Yan et al., 2015] Yan Yan, Yi Yang, Deyu Meng, Gaowen Liu, Wei Tong, Alexander G Hauptmann, and Nicu Sebe. Event oriented dictionary learning for complex event detection. IEEE Trans. Image Process., 24(6):1867-1878, 2015.","title":"Event oriented dictionary learning for complex event detection","authors":"Yan Yan, Yi Yang, Deyu Meng, Gaowen Liu, Wei Tong, Alexander G Hauptmann, Nicu Sebe","year":"2015","venue":"IEEE Trans. Image Process","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Ye et al., 2015] Guangnan Ye, Yitong Li, Hongliang Xu, Dong Liu, and Shih-Fu Chang. Eventnet: A large scale structured con- cept library for complex event detection in video. In ACM MM, 2015.","title":"Eventnet: A large scale structured concept library for complex event detection in video","authors":"Guangnan Ye, Yitong Li, Hongliang Xu, Dong Liu, Shih-Fu Chang","year":"2015","venue":"ACM MM","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}