Feature sampling and partitioning for visual vocabulary generation on large action classification datasets

Keywords

Computer science, Feature (linguistics), Artificial intelligence, Vocabulary, Sampling (signal processing)

References

• UCF101: A Dataset of 101 Human Actions Classes From Videos in The WildKhurram Soomro, Amir Zamir, Mubarak Shah — 2012
• Improving "bag-of-keypoints" image categorisation: Generative Models and PDF-KernelsJason Farquhar, Sándor Szedmák, Hongying Meng — 2005
• The devil is in the details: an evaluation of recent feature encoding methodsKen Chatfield, Victor Lempitsky, Andrea Vedaldi — 2011
• Aggregating Local Image Descriptors into Compact CodesH. Jegou, Florent Perronnin, Matthijs Douze — 2012
• Towards optimal bag-of-features for object categorization and semantic video retrievalYu–Gang Jiang, Chong‐Wah Ngo, Jun Yang — 2007
• Evaluation of Local Spatio-temporal Features for Action RecognitionHeng Wang, Muhammad Muneeb Ullah, Alexander Kläser — 2009
• Learning hierarchical invariant spatio-temporal features for action recognition with independent subspace analysisQuoc V. Le, Will Y. Zou, Serena Yeung — 2011
• Learning Discriminative Space–Time Action Parts from Weakly Labelled VideosMichael Sapienza, Fabio Cuzzolin, Philip H. S. Torr — 2014
• On Space-Time Interest PointsIvan Laptev — 2005
• A Spatio-Temporal Descriptor Based on 3D-GradientsAlexander Klaeser, Marcin Marszałek, C. Schmid — 2008
• A Randomized Algorithm for Principal Component AnalysisVladimir Rokhlin, Arthur Szlam, Mark Tygert — 2008
• Vlfeat: an open and portable library of computer vision algorithmsAndrea Vedaldi, Brian Fulkerson — 2010
• Dense Trajectories and Motion Boundary Descriptors for Action RecognitionHeng Wang, Alexander Kläser, Cordelia Schmid — 2013
• Large-scale image retrieval with compressed Fisher vectorsFlorent Perronnin, Yan Liu, Jorge Sánchez — 2010
• A Biologically Inspired System for Action RecognitionHueihan Jhuang, T. Serre, Lior Wolf — 2007
• Recognizing realistic actions from videos “in the wild”Jingen Liu, Jiebo Luo, Mubarak Shah — 2009
• Local Features and Kernels for Classification of Texture and Object Categories: A Comprehensive StudyJianguo Zhang, M. Marszałek, Svetlana Lazebnik — 2006
• LIBLINEAR: A Library for Large Linear ClassificationRong-En Fan, Kai‐Wei Chang, Cho‐Jui Hsieh — 2008
• Action recognition by dense trajectoriesHeng Wang, Alexander Kläser, Cordelia Schmid — 2011
• HMDB: A large video database for human motion recognitionHilde Kuehne, Hueihan Jhuang, Estíbaliz Garrote — 2011

Cited by

• The Best of BothWorlds: Combining Data-Independent and Data-Driven Approaches for Action RecognitionZhenzhong Lan, Shoou-I Yu, Dezhong Yao — 2015
• Long-short Term Motion Feature for Action Classification and RetrievalZhenzhong Lan, Xuanchong Li, Ming Lin — 2015
• Beyond Gaussian Pyramid: Multi-skip Feature Stacking for action recognitionZhenzhong Lan, Ming Lin, Xuanchong Li — 2014
• Pooling the Convolutional Layers in Deep ConvNets for Action RecognitionShichao Zhao, Yanbin Liu, Yahong Han — 2015
• ARCH: Adaptive recurrent-convolutional hybrid networks for long-term action recognitionMiao Xin, Hong Zhang, Helong Wang — 2015
• Handcrafted Local Features are Convolutional Neural NetworksZhenzhong Lan, Shoou-I Yu, Ming Lin — 2015
• Improving Human Activity Recognition Through Ranking and Re-rankingZhenzhong Lan, Shoou-I Yu, Alexander G. Hauptmann — 2015
• Multi-class Support Vector Machine classifiers using intrinsic and penalty graphsAlexandros Iosifidis, Moncef Gabbouj — 2016
• Beyond Spatial Pyramid Matching: Space-time Extended Descriptor for Action RecognitionZhenzhong Lan, Alexander G. Hauptmann — 2015
• Introducing temporal order of dominant visual word sub-sequences for human action recognitionNikolaos Kardaris, Vassilis Pitsikalis, Effrosyni Mavroudi — 2016
• Combining multi-class maximum margin classification with linear discriminant analysis for human action recognitionAlexandros Iosifidis, Moncef Gabbouj — 2016
• Deep Local Video Feature for Action RecognitionZhenzhong Lan, Yi Zhu, Alexander G. Hauptmann — 2017
• Deep Learning for Fixed Model ReuseYang Yang, De‐Chuan Zhan, Ying Fan — 2017
• A compact pairwise trajectory representation for action recognitionQingya Huang, Shan Sun, Feng Wang — 2017
• Analyse et reconnaissance de séquences vidéos d'activités humaines dans l'espace sémantique. (Analysis and recognition of human activities in video sequences in the semantic space)Cyrille Beaudry — 2015
• Pooling the Convolutional Layers in Deep ConvNets for Video Action RecognitionShichao Zhao, Yanbin Liu, Yahong Han — 2018
• Feature sampling strategies for action recognitionYoujie Zhou, Hongkai Yu, Song Wang — 2015
• Towards Usable Multimedia Event DetectionZhenzhong Lan — 2022
• Recognising and localising human actionsMichael Sapienza — 2014
• PAIRWISE TRAJECTORY REPRESENTATION FOR ACTION RECOGNITIONQingya Huang, Shan Sun, Feng Wang — 2017

Related papers

• The Influence of Frequency on the Acquisition and Textbooks Design of Second Language VocabularyAnwar Saad Aljadani — 2020
• A study on measuring vocabulary knowledge and vocabulary size of Korean language learners.연세대학교, Mi-Jin Won — 2017
• The Use of Vocabulary Notebooks for EFL Non-majors ESP Vocabulary AcquisitionThi Cuc Tran, Manh Cuong — 2023
• Comment on College English Vocabulary TeachingUtebaliyeva Ge — 2002
• Face Recognition Based on Gppbtf and LBP with Classifier FusionGang Xu, Huchuan Lu, Zunyi Wang — 2012
• Gradient feature extraction for classification-based face detectionLin-Lin Huang, Akinobu Shimizu, Yoshihoro Hagihara — 2003
• Feature Bias Correction: A Feature Augmentation Method for Long-tailed RecognitionJiaxin Yang, Xiaofei Li, Jun Zhang — 2023