Filters








29,862 Hits in 5.1 sec

Keep It Simple and Sparse: Real-Time Action Recognition [chapter]

Sean Ryan Fanello, Ilaria Gori, Giorgio Metta, Francesca Odone
2017 Gesture Recognition  
In this paper we show that sparse representation plays a fundamental role in achieving one-shot learning and real-time recognition of actions.  ...  The main contribution of the paper is an effective realtime system for one-shot action modeling and recognition; the paper highlights the effectiveness of sparse coding techniques to represent 3D actions  ...  Acknowledgments This work was supported by the European FP7 ICT projects N. 270490 (EFAA) and N. 270273 (Xperience).  ... 
doi:10.1007/978-3-319-57021-1_10 fatcat:yxitbm4nsnhhjlef3azje4j2zi

Real-Time Human Action Recognition using Stacked Sparse Autoencoders

Adnan Farooq, Emad U Din Mohammad, Abdullah Ahmad Zarir, Amelia Ritahani Ismail, Suriani Sulaiman
2018 Indian Journal of Science and Technology  
Objectives: In this paper, an automated real-time human and human-action detection system is developed using Histogram of Oriented Gradients (HOG) and Stacked Sparse Auto-encoders respectively.  ...  Stacked Sparse autoencoders are a category of deep neural networks, and in the proposed work is used for the feature extraction of human actions from the human action video dataset.  ...  Results We trained and tested our model on the data samples selected from the WEIZMANN Dataset of human action recognition and also applied real-time classification on it.  ... 
doi:10.17485/ijst/2018/v11i4/121090 fatcat:76mfn3egwnhofm7lvkqbth7jdi

Study on Recent Approaches for Human Action Recognition in Real Time

R. Rajitha Jasmine, Dr. K. K. Thyagharajan
2015 International Journal of Engineering Research and  
In this paper, we focus our attention to various modern approaches to human action recognition in real time.  ...  The challenge is to recognize human actions with more accuracy and efficiency in recognition time.  ...  Research on action recognition is very much important to enable a wide range of real time applications.  ... 
doi:10.17577/ijertv4is080577 fatcat:hikmv56t6jc5la7ipcny5u4kha

Marginalised Stacked Denoising Autoencoders for Robust Representation of Real-Time Multi-View Action Recognition

Feng Gu, Francisco Flórez-Revuelta, Dorothy Monekosso, Paolo Remagnino
2015 Sensors  
It is also capable of performing real-time action recognition at a frame rate ranging from 33 to 45, which could be further improved by using more powerful machines in future applications.  ...  action recognition.  ...  Acknowledgments This work has been supported by the Ambient Assisted Living Joint Programme and Innovate UK under project "BREATHE-Platform for self-assessment and efficient management for informal caregivers  ... 
doi:10.3390/s150717209 pmid:26193271 pmcid:PMC4541930 fatcat:i7xoki6rzjej5l63docv26kx6a

Real-Time Exact Graph Matching with Application in Human Action Recognition [chapter]

Oya Çeliktutan, Christian Wolf, Bülent Sankur, Eric Lombardi
2012 Lecture Notes in Computer Science  
We derive an exact minimization algorithm and successfully applied to action recognition in videos.  ...  In this context, we take advantage of special properties of the time domain, in particular causality and the linear order of time, and propose a novel spatio-temporal graphical structure.  ...  Introduction In many applications involving the recognition of complex visual patterns, as for instance recognition of object classes or actions in video scenes, salient local features collected on sparse  ... 
doi:10.1007/978-3-642-34014-7_2 fatcat:tyv5oocjpnf4lbx66qufgmsila

Sliding Dictionary Based Sparse Representation For Action Recognition [article]

Yashas Annadani, D L Rakshith, Soma Biswas
2016 arXiv   pre-print
The task of action recognition has been in the forefront of research, given its applications in gaming, surveillance and health care.  ...  In this work, we propose a simple, yet very effective approach which works seamlessly for both offline and online action recognition using the skeletal joints.  ...  [14] , which estimates the 3D joint locations of humans in real time from a single depth image.  ... 
arXiv:1611.00218v1 fatcat:lfvesqynfjec3gomsjc2yclcga

Sparse Black-box Video Attack with Reinforcement Learning [article]

Xingxing Wei, Huanqian Yan, Bo Li
2022 arXiv   pre-print
By continuously querying the recognition models and receiving the attacking feedback, the agent gradually adjusts its frame selection strategy and adversarial perturbations become smaller and smaller.  ...  We conduct a series of experiments with two mainstream video recognition models: C3D and LRCN on the public UCF-101 and HMDB-51 datasets.  ...  The 3D universal perturbation [17] is generated by Generative Adversarial Networks offline and then used with unseen input for the real-time video recognition model.  ... 
arXiv:2001.03754v3 fatcat:pcxcwqkpbjerje4jauoh5ljszq

STAR: Sparse Transformer-based Action Recognition [article]

Feng Shi, Chonghan Lee, Liang Qiu, Yizhou Zhao, Tianyi Shen, Shivran Muralidhar, Tian Han, Song-Chun Zhu, Vijaykrishnan Narayanan
2021 arXiv   pre-print
This work proposes a novel skeleton-based human action recognition model with sparse attention on the spatial dimension and segmented linear attention on the temporal dimension of data.  ...  The cognitive system for human action and behavior has evolved into a deep learning regime, and especially the advent of Graph Convolution Networks has transformed the field in recent years.  ...  In particular, skeleton-based human action recognition has attracted much attention in recent years and has shown its effectiveness.  ... 
arXiv:2107.07089v1 fatcat:g2ko62ahbvfftay3ocghmw7rmy

Spontaneous Facial Expression Recognition using Sparse Representation

Dawood Al Chanti, Alice Caplier
2017 Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications  
Sparse codes are then used to train an SVM classifier dedicated to the recognition task.  ...  It is also estimated on the well-known acted facial expressions JAFFE database for a purpose of comparison with state-of-the-art methods.  ...  Our pre-training step allows us to avoid high computational resources (memory usage and training time) required during dictionary training which is an important requirement for developing a real-time automatic  ... 
doi:10.5220/0006118000640074 dblp:conf/visapp/ChantiC17 fatcat:54kdte3tl5b3fkmkizzn3i76sq

Event Transformer. A sparse-aware solution for efficient event data processing [article]

Alberto Sabater and Luis Montesano and Ana C. Murillo
2022 arXiv   pre-print
We introduce a new patch-based event representation and a compact transformer-like architecture to process it. EvT is evaluated on different event-based benchmarks for action and gesture recognition.  ...  They log sparse illumination changes with high temporal resolution and high dynamic range, while they present minimal power consumption.  ...  EvT evaluation is run on three public real event data benchmarks of different complexity for long and short event-stream classification (i.e., action and gesture recognition).  ... 
arXiv:2204.03355v2 fatcat:wmuzanmvwjccpgknxsdpovhe4i

Weakly Supervised Action Localization by Sparse Temporal Pooling Network [article]

Phuc Nguyen, Ting Liu, Gautam Prasad, Bohyung Han
2018 arXiv   pre-print
At inference time, we extract and score temporal proposals using temporal class activations and class-agnostic attentions to estimate the time intervals that correspond to target actions.  ...  We design our network to identify a sparse subset of key segments associated with target actions in a video using an attention module and fuse the key segments through adaptive temporal pooling.  ...  Related Work Action recognition aims to identify a single or multiple actions per video and is often formulated as a simple classification problem.  ... 
arXiv:1712.05080v2 fatcat:grqtahaqibhcpcxcim6dzpxoca

Saliency-based selection of sparse descriptors for action recognition

Eleonora Vig, Michael Dorr, David D. Cox
2012 2012 19th IEEE International Conference on Image Processing  
Local spatiotemporal descriptors are being successfully used as a powerful video representation for action recognition.  ...  We here combine advantages of both dense and sparse sampling. Once descriptors are extracted on a dense grid, we prune them either randomly or based on a sparse saliency mask of the underlying video.  ...  real-time constraints with limited resources.  ... 
doi:10.1109/icip.2012.6467132 dblp:conf/icip/VigDC12 fatcat:ujurwwo63zdznhlbwwe3g4mcli

An enhanced sparse representation strategy for signal classification

Yin Zhou, Jinglun Gao, Kenneth E. Barner
2012 Compressive Sensing  
Sparse representation based classification (SRC) has achieved state-of-the-art results on face recognition.  ...  It is hence desired to extend its power to a broader range of classification tasks in pattern recognition.  ...  INTRODUCTION Sparse representation has achieved state-of-the-art results in many fields, such as image compression and denoising, 1, 2 texture analysis, 3 face recognition, 4, 5 objection recognition,  ... 
doi:10.1117/12.919469 fatcat:3p47xyzj7nggxb322lifsikbmq

Performance Improvement of Hand Gesture Recognition By using Sparse Coding With Kinect V2 Sensors

2019 VOLUME-8 ISSUE-10, AUGUST 2019, REGULAR ISSUE  
Here the important technique which is sparse coding representation acts as a major ROLE in achiveving One-short learning and real recognition of actions[1].  ...  With this data then suggest a instantaneous to get video segmentation and video gratitude of hand gesture action by using linear SVMs.This paper mainly highlights the major role of sparse coding technique  ...  Xiang, Recognising action as clouds of space-time interest points, in IEEE Conference on Computer Vision and Pattern Recognition, 2009 4. M.J. Burden, D.B.  ... 
doi:10.35940/ijitee.k1976.0981119 fatcat:cycc37cop5fujdhchnnk6gvxra

Stabilized Sparse Online Learning for Sparse Data [article]

Yuting Ma, Tian Zheng
2017 arXiv   pre-print
With high-dimensional sparse data, however, the method suffers from slow convergence and high variance due to the heterogeneity in feature sparsity.  ...  To facilitate better convergence, we adopt an annealing strategy on the truncation rate, which leads to a balanced trade-off between exploration and exploitation in learning a sparse weight vector.  ...  In an online learning algorithm, one sample instance is processed at a time to obtain a simple update, and the process is repeated via multiple passes over the entire training set.  ... 
arXiv:1604.06498v3 fatcat:ppuswbpn2jb25nkbvb6wvnsxam
« Previous Showing results 1 — 15 out of 29,862 results