Filters








99 Hits in 5.0 sec

Learning zeroth class dictionary for human action recognition [article]

Jia-xin Cai, Xin Tang, Lifang Zhang, Guocan Feng
2016 arXiv   pre-print
In this paper, a discriminative two-phase dictionary learning framework is proposed for classifying human action by sparse shape representations, in which the first-phase dictionary is learned on the selected  ...  We propose a "zeroth class" trick for detecting undiscriminating frames of the test video and eliminating them before voting on the action categories.  ...  Sect.3 presents the zeroth class dictionary learning framework for human action recognition.  ... 
arXiv:1603.04015v3 fatcat:e5zzrvgzqnewnfaqycliwewsy4

Going Deeper into Action Recognition: A Survey [article]

Samitha Herath, Mehrtash Harandi, Fatih Porikli
2017 arXiv   pre-print
Understanding human actions in visual data is tied to advances in complementary research areas including object recognition, human dynamics, domain adaptation and semantic segmentation.  ...  Over the last decade, human action analysis evolved from earlier schemes that are often limited to controlled environments to nowadays advanced solutions that can learn from millions of videos and apply  ...  Basura Fernando for fruitful discussions and encouragement comments given for this work.  ... 
arXiv:1605.04988v2 fatcat:7727tjctgfffzlnig5rvicxjgq

Action recognition via spatio-temporal local features: A comprehensive study

Xiantong Zhen, Ling Shao
2016 Image and Vision Computing  
In this paper, we provide a comprehensive study on these local methods for human action recognition.  ...  Local methods based on spatio-temporal interest points (STIPs) have shown their effectiveness for human action recognition.  ...  human action recognition.  ... 
doi:10.1016/j.imavis.2016.02.006 fatcat:yqk3jumipvaorfh2ozvzb326lu

Complex Activity Recognition Via Attribute Dynamics

Wei-Xin Li, Nuno Vasconcelos
2016 International Journal of Computer Vision  
An algorithm is introduced for learning a BDS codebook, enabling the use of the BDS as a visual word for attribute dynamics (WAD).  ...  To enable the recognition of highly non-stationary activities, the BDS is embedded in a bag of words.  ...  Lately, semantic attributes have been used for action recognition (Liu et al, 2011; Jhuang et al, 2013) , demonstrating the benefits of mid-level semantic representations for the analysis of complex human  ... 
doi:10.1007/s11263-016-0918-1 fatcat:yceautxluja5tij2jg2r5dpa2e

Deep Multi View Spatio Temporal Spectral Feature Embedding on Skeletal Sign Language Videos for Recognition

SK. Ashraf Ali, M. V. D. Prasad, P. Praveen Kumar, P. V. V. Kishore
2022 International Journal of Advanced Computer Science and Applications  
Subsequently, the constructed global view is applied as training data for sign language recognition.  ...  This is achieved by learning the weights of the linear combination of Laplacian eigenmaps of multiple views.  ...  SLR is considered an extension of human action recognition (HAR) [2] .  ... 
doi:10.14569/ijacsa.2022.0130494 fatcat:hhy77tzmzjdwjn6uk2ocli7tqi

Learning spatial relations in object recognition

Thang V. Pham, Arnold W.M. Smeulders
2006 Pattern Recognition Letters  
Two datasets are used, one being human faces in frontal view as an example for the class of objects with a fixed spatial layout, and the other being horses faced to the right with large variations in action  ...  As a consequence, these approaches are not yet suitable for learning and recognition of object classes.  ... 
doi:10.1016/j.patrec.2006.03.016 fatcat:lqmhwarhqndjxkrdo6gp6ni5jm

Efficient Automated Processing of the Unstructured Documents using Artificial Intelligence: A Systematic Literature Review and Future Directions

Dipali Baviskar, Swati Ahirrao, Vidyasagar Potdar, Ketan Kotecha
2021 IEEE Access  
This method requires humans to write simple rules to perform repetitive actions with a software bot.  ...  It shows how RPA mimics human actions while executing various tasks within a process, such as clicking on the help or file menu button.  ... 
doi:10.1109/access.2021.3072900 fatcat:lrbzlmo5gnczhadnrxd2aoqz4u

Sumienie maszyny? Sztuczna inteligencja i problem odpowiedzialności moralnej

Krzysztof Tomasz Wieczorek, Paweł Jędrzejko
2021 ER(R)GO / ERRGO : Teoria, Literatura, Kultura  
and their motives for action may turn out to be.  ...  While experiences related to social acts of rewarding individuals for particular actions or behaviors delineate the scope of the class of morally acceptable behaviors, the acts of punishment generate knowledge  ... 
doi:10.31261/errgo.10418 fatcat:wbo3k4bc4faf7ih6un7fa232ga

Recognition and understanding of meetings the AMI and AMIDA projects

Steve Renals, Thomas Hain, Herve Bourlard
2007 2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU)  
Within these projects we have: developed an infrastructure for recording meetings using multiple microphones and cameras; released a 100 hour annotated corpus of meetings; developed techniques for the  ...  recognition and interpretation of meetings based primarily on speech recognition and computer vision; and developed an evaluation framework at both component and system levels.  ...  Some of the core work of the AMI consortium has been the development of recognizers for audio and video modalities, including gesture and action recognition and audio-visual tracking.  ... 
doi:10.1109/asru.2007.4430116 dblp:conf/asru/RenalsHB07 fatcat:sfplfqyxynez7bpnmldzplpl3i

On the use of machine learning for computational imaging

George Barbastathis, Kishan Dholakia, Gabriel C. Spalding
2020 Optical Trapping and Optical Micromanipulation XVII  
Horn, and Lei Tian for helpful discussions and extensive comments on earlier versions of the paper.  ...  For highly ill-posed and noisy tasks, it is generally better to restrict the class so that stronger priors are learned.  ...  When the raw intensity data on the camera are not readily usable by a human or a traditional image interpretation algorithm for the purposes of recognition, an interesting dilemma occurs: does it make  ... 
doi:10.1117/12.2571322 fatcat:2rkgbdtgi5foln7ptwqanhncqu

Semantic Spaces [article]

Yuri Manin, Matilde Marcolli
2016 arXiv   pre-print
This tool for its description in turn requires other large databases (dictionaries, grammars etc.). Nowadays, the notion of database is associated with computer processing and computer memory.  ...  However, a natural language resides also in human brains and functions in human communication, from interpersonal to intergenerational one.  ...  Unsupervised Learning.  ... 
arXiv:1605.04238v1 fatcat:qw7ebna3zrbi7iljiaxhbhfd3i

Definition and recovery of kinematic features for recognition of American sign language movements

Konstantinos G. Derpanis, Richard P. Wildes, John K. Tsotsos
2008 Image and Vision Computing  
The approach has been implemented in software and evaluated on a database of 592 gesture sequences with an overall recognition rate of 86% for fully automated processing and 97% for manually initialized  ...  An approach to recognizing human hand gestures from a monocular temporal sequence of images is presented.  ...  The 3D world velocities for this class of movements are as follows.  ... 
doi:10.1016/j.imavis.2008.04.007 fatcat:jdbvoxmkdraizbpw3eybjo6a3u

Deep Online Convex Optimization with Gated Games [article]

David Balduzzi
2016 arXiv   pre-print
Methods from convex optimization are widely used as building blocks for deep learning algorithms.  ...  Corollaries of the main result include: (i) a game-theoretic description of the representations learned by a neural network; (ii) a logarithmic-regret algorithm for training neural nets; and (iii) a formal  ...  ACKNOWLEDGEMENTS I am grateful to Jacob Abernethy, Samory Kpotufe and Brian McWilliams for useful conversations.  ... 
arXiv:1604.01952v1 fatcat:oh62dtvztrbd7mendv7io5is5i

Artificial Intelligence [article]

John Paul Mueller Luca Massaron
2018 Zenodo  
In addition, the human tendency to anthropomorphize (give human characteristics to) technology makes it seem as if AI must do more than it can hope to accomplish.  ...  For example, consider a spam filter. Say that your dictionary contains 100,000 words (a small dictionary).  ...  Feed the processed cropped faces as learning examples to a neural network for image recognition.  ... 
doi:10.5281/zenodo.5599660 fatcat:rn6nyx5xinehzpwfy3knurtzgy

Data science applications to string theory

Fabian Ruehle
2019 Physics reports  
We first introduce various algorithms and techniques for machine learning and data science.  ...  While there is a strong focus on neural network applications in unsupervised, supervised and reinforcement learning, other machine learning techniques are discussed as well.  ...  Center for Geometry and Physics, USA for financial support for schools and conferences we organized on machine learning.  ... 
doi:10.1016/j.physrep.2019.09.005 fatcat:i5jtac7qpfgyrmsmvsylyinaba
« Previous Showing results 1 — 15 out of 99 results