請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/54844完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 陳銘憲 | |
| dc.contributor.author | Kuan-Ting Lai | en |
| dc.contributor.author | 賴冠廷 | zh_TW |
| dc.date.accessioned | 2021-06-16T03:39:44Z | - |
| dc.date.available | 2015-03-16 | |
| dc.date.copyright | 2015-03-16 | |
| dc.date.issued | 2015 | |
| dc.date.submitted | 2015-02-23 | |
| dc.identifier.citation | [1] Li Fei-Fei, Rob Fergus, and Antonio Torralba. Recognizing and learning object categories. CVPR Short Course, 2, 2007.
[2] Mark Everingham, Luc Van Gool, Christopher KI Williams, John Winn, and Andrew Zisserman. The pascal visual object classes (voc) challenge. International journal of computer vision, 88(2):303–338, 2010. [3] Pedro F Felzenszwalb, Ross B Girshick, David McAllester, and Deva Ramanan. Object detection with discriminatively trained part-based models. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 32(9):1627–1645, 2010. [4] Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, and Li Fei-Fei. Imagenet: A large-scale hierarchical image database. In CVPR. IEEE, 2009. [5] Jinjun Wang, Jianchao Yang, Kai Yu, Fengjun Lv, Thomas Huang, and Yihong Gong. Locality-constrained linear coding for image classification. In CVPR. IEEE, 2010. [6] Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems, pages 1097–1105, 2012. [7] Aude Oliva and Antonio Torralba. Modeling the shape of the scene: A holistic representation of the spatial envelope. International journal of computer vision, 42(3):145–175, 2001. [8] Li-Jia Li, Hao Su, Li Fei-Fei, and Eric P Xing. Object bank: A high-level image representation for scene classification & semantic feature sparsification. In Advances in neural information processing systems, pages 1378–1386, 2010. [9] Jianxiong Xiao, James Hays, Krista A Ehinger, Aude Oliva, and Antonio Torralba. Sun database: Large-scale scene recognition from abbey to zoo. In CVPR, pages 3485–3492. IEEE, 2010. [10] Christian Schuldt, Ivan Laptev, and Barbara Caputo. Recognizing human actions: a local svm approach. In ICPR. IEEE, 2004. [11] Ivan Laptev, Marcin Marszalek, Cordelia Schmid, and Benjamin Rozenfeld. Learning realistic human actions from movies. In CVPR, pages 1–8. IEEE, 2008. [12] Heng Wang, Alexander Klaser, Cordelia Schmid, and Cheng-Lin Liu. Action recognition by dense trajectories. In CVPR. IEEE, 2011. [13] Cees GM Snoek, Marcel Worring, and Arnold WM Smeulders. Early versus late fusion in semantic video analysis. In ACM Multimedia. ACM, 2005. [14] Pradeep Natarajan, Shuang Wu, Shiv Vitaladevuni, Xiaodan Zhuang, Stavros Tsakalidis, Unsang Park, and Rohit Prasad. Multimodal feature fusion for robust event detection in web videos. In CVPR. IEEE, 2012. [15] 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. IEEE, 2012. [16] Yu-Gang Jiang, Guangnan Ye, Shih-Fu Chang, Daniel Ellis, and Alexander C Loui. Consumer video understanding: A benchmark database and an evaluation of human and machine performance. In ICMR, 2011. [17] Yu-Gang Jiang, Subhabrata Bhattacharya, Shih-Fu Chang, and Mubarak Shah. Highlevel event recognition in unconstrained videos. International Journal of Multimedia Information Retrieval, 2(2):73–101, 2013. [18] Dan Oneata, Jakob Verbeek, and Cordelia Schmid. Action and event recognition with fisher vectors on a compact feature set. In ICCV. IEEE, 2013. [19] Christopher Poultney, Sumit Chopra, Yann L Cun, et al. Efficient learning of sparse representations with an energy-based model. In Advances in neural information processing systems, pages 1137–1144, 2006. [20] Yoshua Bengio, Pascal Lamblin, Dan Popovici, and Hugo Larochelle. Greedy layerwise training of deep networks. Advances in neural information processing systems, 19:153, 2007. [21] Geoffrey Hinton, Simon Osindero, and Yee-Whye Teh. A fast learning algorithm for deep belief nets. Neural computation, 18(7):1527–1554, 2006. [22] Dan Ciresan, Ueli Meier, and Jürgen Schmidhuber. Multi-column deep neural networks for image classification. In Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on, pages 3642–3649. IEEE, 2012. [23] Josef Sivic and Andrew Zisserman. Video google: A text retrieval approach to object matching in videos. In ICCV. IEEE, 2003. [24] Karthik Nandakumar, Yi Chen, Sarat C Dass, and Anil K Jain. Likelihood ratiobased biometric score fusion. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 30(2):342–347, 2008. [25] Oriol Ramos Terrades, Ernest Valveny, and Salvatore Tabbone. Optimal classifier fusion in a non-bayesian probabilistic framework. IEEE transactions on pattern analysis and machine intelligence, 31(9):1630–1644, 2009. [26] Guangnan Ye, Dong Liu, I-Hong Jhuo, and Shih-Fu Chang. Robust late fusion with rank minimization. In CVPR. IEEE, 2012. [27] Jingchen Liu, Scott McCloskey, and Yanxi Liu. Local expert forest of score fusion for video event classification. In ECCV. Springer, 2012. [28] Dong Liu, Kuan-Ting Lai, Guangnan Ye, Ming-Syan Chen, and Shih-Fu Chang. Sample-specific late fusion for visual category recognition. In CVPR. IEEE, 2013. [29] F. X. Yu, D. Liu, Sanjiv K., T. Jebara, and S.-F. Chang. /SVM for learning with label proportions. In ICML, 2013. [30] Subhabrata Bhattacharya, F. X. Yu, and Shih-Fu Chang. Minimally needed evidence for complex event recognition in unconstrained videos. In ICMR, 2014. [31] Thomas G Dietterich, Richard H Lathrop, and Tomas Lozano-Perez. Solving the multiple instance problem with axis-parallel rectangles. Artificial Intelligence, 89(1): 31–71, 1997. [32] Oded Maron and Aparna Lakshmi Ratan. Multiple-instance learning for natural scene classification. In ICML, 1998. [33] Stuart Andrews, Ioannis Tsochantaridis, and Thomas Hofmann. Support vector machines for multiple-instance learning. In NIPS, 2002. [34] Qi Zhang, Sally A Goldman, Wei Yu, and Jason E Fritts. Content-based image retrieval using multiple-instance learning. In ICML, 2002. [35] Yixin Chen, Jinbo Bi, and James Ze Wang. Miles: Multiple-instance learning via embedded instance selection. IEEE transactions on pattern analysis and machine intelligence, 28(12):1931–1947, 2006. [36] Shivani Agarwal. The infinite push: A new support vector ranking algorithm that directly optimizes accuracy at the absolute top of the list. In SDM, pages 839–850. Society for Industrial and Applied Mathematics, 2011. [37] Alain Rakotomamonjy. Sparse support vector infinite push. In ICML, 2012. [38] Olga Russakovsky, Jia Deng, Hao Su, Jonathan Krause, Sanjeev Satheesh, Sean Ma, Zhiheng Huang, Andrej Karpathy, Aditya Khosla, Michael Bernstein, Alexander C. Berg, and Li Fei-Fei. ImageNet Large Scale Visual Recognition Challenge, 2014. [39] H. Kuehne, H. Jhuang, E. Garrote, T. Poggio, and T. Serre. HMDB: a large video database for human motion recognition. In Proceedings of the International Conference on Computer Vision (ICCV), 2011. [40] Paul Over, George Awad, Martial Michel, Jonathan Fiscus, Greg Sanders, Wessel Kraaij, Alan F. Smeaton, and Georges Queenot. Trecvid 2013 – an overview of the goals, tasks, data, evaluation mechanisms and metrics. In TRECVID. NIST, 2013. [41] Lorenzo Torresani, Martin Szummer, and Andrew Fitzgibbon. Efficient object category recognition using classemes. In ECCV. Springer, 2010. [42] Navneet Dalal and Bill Triggs. Histograms of oriented gradients for human detection. In CVPR, 2005. [43] David G Lowe. Distinctive image features from scale-invariant keypoints. International journal of computer vision, 60(2):91–110, 2004. [44] Timo Ahonen, Abdenour Hadid, and Matti Pietikainen. Face description with local binary patterns: Application to face recognition. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 28(12):2037–2041, 2006. [45] Florent Perronnin and Christopher Dance. Fisher kernels on visual vocabularies for image categorization. In CVPR. IEEE, 2007. [46] Jasper RR Uijlings, Koen EA van de Sande, Theo Gevers, and Arnold WM Smeulders. Selective search for object recognition. International journal of computer vision, 104(2):154–171, 2013. [47] Khurram Soomro, Amir Roshan Zamir, and Mubarak Shah. Ucf101: A dataset of 101 human actions classes from videos in the wild. CRCV-TR-12-01, 2012. [48] Heng Wang, Alexander Klaser, Cordelia Schmid, and Cheng-Lin Liu. Dense trajectories and motion boundary descriptors for action recognition. International journal of computer vision, pages 1–20, 2013. [49] Heng Wang and Cordelia Schmid. Action recognition with improved trajectories. In ICCV. IEEE, 2013. [50] Geoffrey E Hinton and Ruslan R Salakhutdinov. Reducing the dimensionality of data with neural networks. Science, 313(5786):504–507, 2006. [51] Arjun Jain, Jonathan Tompson, Yann LeCun, and Christoph Bregler. Modeep: A deep learning framework using motion features for human pose estimation. arXiv preprint arXiv:1409.7963, 2014. [52] Yixin Chen and James Z Wang. Image categorization by learning and reasoning with regions. JMLR, 5:913–939, 2004. [53] Kuan-Ting Lai, X Yu Felix, Ming-Syan Chen, and Shih-Fu Chang. Video event detection by inferring temporal instance labels. In CVPR. IEEE, 2014. [54] Jianchao Yang, Kai Yu, Yihong Gong, and Thomas Huang. Linear spatial pyramid matching using sparse coding for image classification. In CVPR, 2009. [55] Dan Zhang, Jingrui He, Luo Si, and Richard D Lawrence. Mileage: Multiple instance learning with global embedding. In ICML, 2013. [56] S. Rüeping. SVM classifier estimation from group probabilities. In ICML, 2010. [57] Rong-En Fan, Kai-Wei Chang, Cho-Jui Hsieh, Xiang-Rui Wang, and Chih-Jen Lin. LIBLINEAR: A library for large linear classification. JMLR, 9:1871–1874, 2008. [58] Jun Yang. Mill: A multiple instance learning library, 2009. [59] Alistair Shilton, Marimuthu Palaniswami, Daniel Ralph, and Ah Chung Tsoi. Incremental training of support vector machines. IEEE Transactions on Neural Networks, 16(1):114–131, 2005. [60] Andrea Vedaldi and Andrew Zisserman. Efficient additive kernels via explicit feature maps. IEEE transactions on pattern analysis and machine intelligence, 34(3):480–492, 2012. [61] INRIA. Yael library: Optimized implementations of computationally demanding functions, 2009. [62] Kuan-Ting Lai, Dong Liu, Ming-Syan Chen, and Shih-Fu Chang. Recognizing complex events in videos by learning key static-dynamic evidences. In ECCV, pages 675–688. Springer, 2014. [63] A. Vedaldi and B. Fulkerson. Vlfeat: An open and portable library of computer vision algorithms, 2008. [64] Juan Carlos Niebles, Chih-Wei Chen, and Li Fei-Fei. Modeling temporal structure of decomposable motion segments for activity classification. In ECCV, pages 392–405. Springer, 2010. [65] Kevin Tang, Li Fei-Fei, and Daphne Koller. Learning latent temporal structure for complex event detection. In CVPR. IEEE, 2012. [66] Weixin Li, Qian Yu, Ajay Divakaran, and Nuno Vasconcelos. Dynamic pooling for complex event recognition. In ICCV. IEEE, 2013. [67] Mayank Juneja, Andrea Vedaldi, CV Jawahar, and Andrew Zisserman. Blocks that shout: Distinctive parts for scene classification. In CVPR. IEEE, 2013. [68] C. Vondrick, A. Khosla, T. Malisiewicz, and A. Torralba. HOGgles: Visualizing Object Detection Features. ICCV, 2013. [69] Danila Potapov, Matthijs Douze, Zaid Harchaoui, and Cordelia Schmid. Category specific video summarization. In ECCV, pages 540–555. Springer, 2014. [70] Michael Gygli, Helmut Grabner, Hayko Riemenschneider, and Luc Van Gool. Creating summaries from user videos. In ECCV, pages 505–520. Springer, 2014. [71] Gunhee Kim, Leonid Sigal, and Eric P Xing. Joint summarization of large-scale collections of web images and videos for storyline reconstruction. 2014. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/54844 | - |
| dc.description.abstract | 視頻事件偵測是電腦科學中最重要的研究課題之一，非常有挑戰性•其中偵測複雜事件，例如“生日派對”、“結婚典禮”、“腳踏車特技”等又更加地困難•複雜事件是由許多人對各種物品，在不同的環境下進行時間長短不一的動作所組成的•目前最常用的方法是從一個視頻中的每幀影像的或影段中抽取特徵值，量化和區域取樣後，由一
個向量代表一整個視頻•此方式雖然簡單有效，但是最後區域取樣的步驟常會導致重要的局部訊息喪失和引入不相干的背景特徵•相較於之前的方法，我們注意到了實際上人類只需要幾個重要的證據就可以辨識視頻中的事件•例如，只要看到了“生日蛋糕”或“吹蠟燭”的事件，就可以辨識出“生日派對”的事件•受到這個啟發，我們提出了 新的演算法，可以自動從影片範例中學習關鍵證據和利用關鍵證據來辨識視頻事件•在我們的架構中，每個視頻都被分割成許多的短視頻,稱為“事例”, 然用自動學習哪些事例可以用來作為辨識事件的證據• 在此篇論文中，我們提出了兩種機器學習的方法•第一種方法稱為最大證據學習法(Maximal Evidence Learning, MEL)，是基於大邊量架構，將所有的事例視為未知，並同時學習所有事例和視頻的分類標籤•我們的架構可以在正樣本中學習出最多的正事例，和在負樣本中學習出最多的負事例•第二種方法叫做證據選擇排序法(Evidence Selective Ranking, ESR)，是基於靜態動態事例嵌入法和無限推進排序法來選出重要的證據•實驗證實在大量的視頻資料中兩種方法皆可顯著的提升辨識的正確率•除此之外，實驗結果顯示使用我們的方法學習出來的證據對人是有意義的，可以用來找出事件視頻中的重要的證據影段• | zh_TW |
| dc.description.abstract | Video event detection is one of the most important, yet very challenging, research topics in computer science. The recognition of complex events, e.g. “birthday party”, “wedding ceremony” or “attempting a bike trick”, is even more difficult since complex events consist of various human interactions with different objects in diverse environments with variable time intervals.
Currently the most common approach is to extract features from frames or video clips, and then to quantize and pool these features to form a single vector representation for the entire video. While this method is simple and efficient, the final pooling step may lead to the loss of temporally local information, and include many irrelevant features from noisy background. To approach this problem in a different way than in previous methods, we noticed that humans require only a small amount of evidence to recognize an event in a video. For example, a “birthday party” event can be identified by discovering “birthday cake” and “blowing candles”. Inspired by this idea, we propose a novel way to detect complex events, whereby one first identifies the key evidence that can prove the existence of an event, and then utilizes the evidence to recognize videos. Under our framework, each video is represented as multiple “instances”, which are defined as video segments of different temporal intervals. Then we apply learning methods to identify evidence (positive instances) first and utilize the evidence to recognize complex video events. In this thesis, we propose two learning methods. The first proposed method, called maximal evidence learning (MEL), is based on a large-margin formulation that treats instance labels as hidden latent variables, and infers the instance labels and the instance-level classification model simultaneously. MEL can infer optimal solutions by learning as many positive instances as possible from positive videos, and negative instances from negative videos. The second proposed method is called evidence selective ranking (ESR). ESR is based on static-dynamic instance embedding, and employs infinite push ranking to select the most distinctive evidence. Extensive analysis on large-scale video event datasets shows significant performance gains by both methods. In this study, we also demonstrate key selected evidence is meaningful to humans and can be used to locate video segments that signify an event. | en |
| dc.description.provenance | Made available in DSpace on 2021-06-16T03:39:44Z (GMT). No. of bitstreams: 1 ntu-104-D98921025-1.pdf: 3219268 bytes, checksum: 0ab2f914926fbdf1db3f8f2518858c7e (MD5) Previous issue date: 2015 | en |
| dc.description.tableofcontents | 1 Introduction 1
1.1 Complex (High-level) Events . . . . . . . . . . . . . . . . . . . . . . . . 3 1.2 Evidence Used to Prove the Existence of an Event . . . . . . . . . . . . . 7 1.3 Learning Key Evidence for Detecting Complex Events . . . . . . . . . . 9 1.4 Outline of the Dissertation . . . . . . . . . . . . . . . . . . . . . . . . . 10 2 Overview of Video Event Detection 12 2.1 Recognition of Objects, Actions and Scenes . . . . . . . . . . . . . . . . 13 2.2 Video Event Detection . . . . . . . . . . . . . . . . . . . . . . . . . . . 16 2.3 Deep Learning . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 18 2.4 Multiple Instance Learning . . . . . . . . . . . . . . . . . . . . . . . . . 20 vi 3 Maximal Evidence Learning 22 3.1 Learning with Label Proportions . . . . . . . . . . . . . . . . . . . . . . 24 3.2 Acquiring Maximal Amounts of Evidence in Training Videos . . . . . . . 27 3.3 Instances with Multiple Granularities . . . . . . . . . . . . . . . . . . . . 29 3.4 Optimization Procedure . . . . . . . . . . . . . . . . . . . . . . . . . . . 30 3.5 Instance-based Video Event Detection . . . . . . . . . . . . . . . . . . . 32 3.6 Experimental Results . . . . . . . . . . . . . . . . . . . . . . . . . . . . 33 3.6.1 Columbia Consumer Videos (CCV) . . . . . . . . . . . . . . . . 34 3.6.2 TRECVID MED 2011 . . . . . . . . . . . . . . . . . . . . . . . 34 3.6.3 TRECVID MED 2012 . . . . . . . . . . . . . . . . . . . . . . . 37 3.7 Discussions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 40 3.7.1 Computational Cost . . . . . . . . . . . . . . . . . . . . . . . . 40 3.7.2 Learning with Heterogeneous Instances . . . . . . . . . . . . . . 42 4 Evidence Selective Ranking 44 4.1 Heterogeneous Instance Embedding . . . . . . . . . . . . . . . . . . . . 46 4.2 Evidence Selective Ranking (ESR) . . . . . . . . . . . . . . . . . . . . . 47 4.3 Optimization Procedure . . . . . . . . . . . . . . . . . . . . . . . . . . . 49 4.4 Experimental Results . . . . . . . . . . . . . . . . . . . . . . . . . . . . 51 4.4.1 TRECVID MED 2011 . . . . . . . . . . . . . . . . . . . . . . . 52 4.4.2 TRECVID MED 2012 . . . . . . . . . . . . . . . . . . . . . . . 55 4.5 Discussions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 57 5 Conclusions and Future Work 58 5.1 Maximal Evidence Learning vs. Evidence Selective Ranking . . . . . . . 59 5.2 Future Work . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 59 5.2.1 Learning Object Evidence . . . . . . . . . . . . . . . . . . . . . 59 5.2.2 Video Summarization . . . . . . . . . . . . . . . . . . . . . . . . 60 Bibliography 62 | |
| dc.language.iso | en | |
| dc.subject | 視頻事件偵測 | zh_TW |
| dc.subject | 大邊量架構 | zh_TW |
| dc.subject | 比例支持向量機 | zh_TW |
| dc.subject | 多事例學習 | zh_TW |
| dc.subject | 無限推進 排序法 | zh_TW |
| dc.subject | video event detection | en |
| dc.subject | multiple instance learning | en |
| dc.subject | infinite push ranking | en |
| dc.subject | proportional SVM | en |
| dc.subject | large-margin framework | en |
| dc.title | 機器學習偵測複雜視頻事件的關鍵證據 | zh_TW |
| dc.title | Learning Key Evidence for Detecting Complex Events in Videos | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 103-1 | |
| dc.description.degree | 博士 | |
| dc.contributor.oralexamcommittee | 洪一平,林彥宇,謝朝和,徐宏民 | |
| dc.subject.keyword | 視頻事件偵測; 大邊量架構; 比例支持向量機; 無限推進 排序法; 多事例學習 | zh_TW |
| dc.subject.keyword | video event detection; large-margin framework; proportional SVM; infinite push ranking; multiple instance learning | en |
| dc.relation.page | 68 | |
| dc.rights.note | 有償授權 | |
| dc.date.accepted | 2015-02-23 | |
| dc.contributor.author-college | 電機資訊學院 | zh_TW |
| dc.contributor.author-dept | 電機工程學研究所 | zh_TW |
| 顯示於系所單位： | 電機工程學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-104-1.pdf 未授權公開取用 | 3.14 MB | Adobe PDF |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。