Filters








321 Hits in 5.3 sec

Subspace Clustering for Action Recognition with Covariance Representations and Temporal Pruning [article]

Giancarlo Paoletti, Jacopo Cavazza, Cigdem Beyan, Alessio Del Bue
2020 arXiv   pre-print
To this end, we propose a novel subspace clustering method, which exploits covariance matrix to enhance the action's discriminability and a timestamp pruning approach that allow us to better handle the  ...  This paper tackles the problem of human action recognition, defined as classifying which action is displayed in a trimmed sequence, from skeletal data.  ...  Once the temporal pruning is performed, the covariance representation is applied to the new data and subspace clustering is adopted as in Section III-A. C.  ... 
arXiv:2006.11812v1 fatcat:d5pdt6dmlzehboxavtw4fmnz4e

Joint Sparsity-Based Representation and Analysis of Unconstrained Activities

Raghuraman Gopalan
2013 2013 IEEE Conference on Computer Vision and Pattern Recognition  
We demonstrate the efficacy of our approach for activity classification and clustering by reporting competitive results on standard datasets such as, HMDB, UCF-50, Olympic Sports and KTH.  ...  By decomposing the content of a video sequence into that observed by multiple spatially and/or temporally distributed receivers, we first recover a collection of common and innovative components pertaining  ...  As with other visual recognition tasks, there has been emphasis on both designing features to represent action patterns and learning strategies to derive pertinent information from features to perform  ... 
doi:10.1109/cvpr.2013.353 dblp:conf/cvpr/Gopalan13a fatcat:hdzjdfml7jfapaauu3vhlluyde

2021 Index IEEE Signal Processing Letters Vol. 28

2021 IEEE Signal Processing Letters  
Departments and other items may also be covered if they have been judged to have archival value. The Author Index contains the primary entry for each item, listed under the first author's name.  ...  The primary entry includes the coauthors' names, the title of the paper or other item, and its location, specified by the publication abbreviation, year, month, and inclusive pagination.  ...  Song, Q., +, LSP 2021 479-483 Spatial Temporal Graph Deconvolutional Network for Skeleton-Based Human Action Recognition.  ... 
doi:10.1109/lsp.2022.3145253 fatcat:a3xqvok75vgepcckwnhh2mty74

Unsupervised view and rate invariant clustering of video sequences

Pavan Turaga, Ashok Veeraraghavan, Rama Chellappa
2009 Computer Vision and Image Understanding  
Second, we also derive methods to incorporate view and rate-invariance into these models so that similar actions are clustered together irrespective of the viewpoint or the rate of execution of the activity  ...  This necessitates the development of efficient indexing and retrieval algorithms for video data.  ...  Daniel Weinland for his kind help in providing us with the dataset from [21] and also the code for their recognition and temporal segmentation algorithms. Thanks are also due to Mr.  ... 
doi:10.1016/j.cviu.2008.08.009 fatcat:t7oac4zaxzegxdfkhjdhy2jdwy

From Videos to Verbs: Mining Videos for Activities using a Cascade of Dynamical Systems

Pavan K. Turaga, Ashok Veeraraghavan, Rama Chellappa
2007 2007 IEEE Conference on Computer Vision and Pattern Recognition  
discovery and event recognition.  ...  We also propose a novel technique to build affine, view, rate invariance of the activity into the distance metric for clustering.  ...  Naresh Cuntoor and Mr. Aswin Sankaranayanan for useful discussions.  ... 
doi:10.1109/cvpr.2007.383170 dblp:conf/cvpr/TuragaVC07 fatcat:qf6kosqku5cozexcvlx5fjgpju

Complex Activity Recognition Via Attribute Dynamics

Wei-Xin Li, Nuno Vasconcelos
2016 International Journal of Computer Vision  
Short-term video segments are then quantized with a WAD codebook, allowing the representation of video as a bagof-words for attribute dynamics (BoWAD).  ...  Experiments show that this representation achieves stateof-the-art performance on the tasks of complex activity recognition and event identification.  ...  of an action recognition system.  ... 
doi:10.1007/s11263-016-0918-1 fatcat:yceautxluja5tij2jg2r5dpa2e

Table of Contents

2021 IEEE Signal Processing Letters  
Xu, and L. Wang POLO: Learning Explicit Cross-Modality Fusion for Temporal Action Localization . . . . . B. Wang, L. Yang, and Y.  ...  Li Spatial Temporal Graph Deconvolutional Network for Skeleton-Based Human Action Recognition . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .  ... 
doi:10.1109/lsp.2021.3134549 fatcat:m6obtl7k7zdqvd62eo3c4tptfy

Table of Contents

2021 IEEE Signal Processing Letters  
Murala, and A. B. Gonde POLO: Learning Explicit Cross-Modality Fusion for Temporal Action Localization . . . . . B. Wang, L. Yang, and Y.  ...  Li Spatial Temporal Graph Deconvolutional Network for Skeleton-Based Human Action Recognition . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .  ... 
doi:10.1109/lsp.2021.3134551 fatcat:ab4b4tb5rrcu5cq6aifdekrizq

2021 Index IEEE Transactions on Image Processing Vol. 30

2021 IEEE Transactions on Image Processing  
Departments and other items may also be covered if they have been judged to have archival value. The Author Index contains the primary entry for each item, listed under the first author's name.  ...  The primary entry includes the coauthors' names, the title of the paper or other item, and its location, specified by the publication abbreviation, year, month, and inclusive pagination.  ...  ., +, TIP 2021 8847-8860 Clustering methods Generalized Nonconvex Low-Rank Tensor Approximation for Multi-View Subspace Clustering.  ... 
doi:10.1109/tip.2022.3142569 fatcat:z26yhwuecbgrnb2czhwjlf73qu

Developing dually optimal LCA features in sensory and action spaces for classification

Nikita Wagle, Juyang Weng
2012 2012 IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL)  
., type and location), a DN treats these meanings in a unified way for both detection and recognition for objects in dynamic cluttered backgrounds.  ...  However, the DN method has not been applied to publicly available datasets and compared with well-known major techniques. In this work, we fill this void.  ...  ACKNOWLEDGMENT The authors would like to thank Matthew Luciw and Yuekai Wang for providing some of their programs.  ... 
doi:10.1109/devlrn.2012.6400885 dblp:conf/icdl-epirob/WagleW12 fatcat:4h3taeqtyvgm5j5glissewklte

2020 Index IEEE Transactions on Pattern Analysis and Machine Intelligence Vol. 42

2021 IEEE Transactions on Pattern Analysis and Machine Intelligence  
., and Nishino, K., Recognizing Material Properties from Images; 1981-1995 Sebe, N., see Pilzer, A., 2380-2395 Seddik, M., see Tamaazousti, Y., 2212-2224 Shah, M., see Kalayeh, M.M., TPAMI June 2020  ...  Expression and Action Recognition; 2594-2607 Tang, P., Wang, X., Bai, S., Shen, W., Bai, X., Liu, W., and Yuille, A., PCL: Proposal Cluster Learning for Weakly Supervised Object Detection; TPAMI Jan  ...  ., +, TPAMI Sept. 2020 2133-2147 Learning Low-Dimensional Temporal Representations with Latent Alignments.  ... 
doi:10.1109/tpami.2020.3036557 fatcat:3j6s2l53x5eqxnlsptsgbjeebe

Mid-level Representation for Visual Recognition [article]

Moin Nabi
2015 arXiv   pre-print
This thesis targets employing mid-level representations for different high-level visual recognition tasks, namely (i)image understanding and (ii)video understanding.  ...  Employing mid-level representation, in particular, shifted the paradigm in visual recognition.  ...  Learning hierarchical invariant spatio-temporal features for action recognition with independent subspace analysis. In CVPR 2011. [92] J. Li, S. Gong, and T. Xiang.  ... 
arXiv:1512.07314v1 fatcat:knmhkwxqk5aczis7ce6g2sv2wm

Going Deeper into Action Recognition: A Survey [article]

Samitha Herath, Mehrtash Harandi, Fatih Porikli
2017 arXiv   pre-print
To this end, we start our discussion with the pioneering methods that use handcrafted representations, and then, navigate into the realm of deep learning based approaches.  ...  for the reader.  ...  Basura Fernando for fruitful discussions and encouragement comments given for this work.  ... 
arXiv:1605.04988v2 fatcat:7727tjctgfffzlnig5rvicxjgq

Incremental Hierarchical Discriminant Regression

Juyang Weng, Wey-Shiuan Hwang
2007 IEEE Transactions on Neural Networks  
Biologically motivated, it is an approximate computational model for automatic development of associative cortex, with both bottom-up sensory inputs and top-down motor projections.  ...  The IHDR tree dynamically assigns long-term memory to avoid the loss-of-memory problem typical with a global-fitting learning algorithm for neural networks.  ...  HDR was used for vision-based motion detection, object recognition (appearance classification), and size dependent action (appearance regression) in [31] .  ... 
doi:10.1109/tnn.2006.889942 pmid:17385628 fatcat:fjfjv3vzvbemto5xe52n342yla

Classification of single trial motor imagery EEG recordings with subject adapted non-dyadic arbitrary time–frequency tilings

Nuri Finodotrat Ince, Sami Arica, Ahmed Tewfik
2006 Journal of Neural Engineering  
For comparison, we also implemented an adaptive autoregressive model based classification procedure that achieved an average error rate of 76.3% on the same subjects, and higher error rates than the proposed  ...  This reduced feature set is finally fed to a linear discriminant for classification.  ...  This full tree is pruned to minimize a cost function, such as entropy, by a divide and conquer algorithm. Traditionally, the BB method has been used for signal representation.  ... 
doi:10.1088/1741-2560/3/3/006 pmid:16921207 fatcat:r3yjzgxavbavxnlshd3gyyc2cm
« Previous Showing results 1 — 15 out of 321 results