8,707 Hits in 7.3 sec

Boosted Multiple Kernel Learning for First-Person Activity Recognition [article]

Fatih Ozkan, Mehmet Ali Arabaci, Elif Surer, Alptekin Temizel
2017 arXiv   pre-print
Our experimental results show that use of Multiple Kernel Learning (MKL) and Boosted MKL in first-person activity recognition problem exhibits improved results in comparison to the state-of-the-art.  ...  In this study, we propose a data-driven framework for first-person activity recognition which effectively selects and combines features and their respective kernels during the training.  ...  Boosted Multiple Kernel Learning Boosted Multiple Kernel Learning (Boosted MKL) is an iterative approach to combine features and kernels effectively.  ... 
arXiv:1702.06799v2 fatcat:4kdn7ymdgrfu5krnhywlkom4zy

Boosted Multiple Kernel Learning For First-Person Activity Recognition

Mehmet Arabaci, Fatih Ozkan, Elif Surer, Alptekin Temizel
2018 Zenodo  
Boosted Multiple Kernel Learning Boosted Multiple Kernel Learning (Boosted MKL) is an iterative approach to combine features and kernels effectively.  ...  This study proposes an innovative approach for first-person activity recognition using MKL and Boosted MKL methods.  ... 
doi:10.5281/zenodo.1159451 fatcat:ksr2frb7xfas3gkcqhosxlewbu

Multi-modal Egocentric Activity Recognition using Audio-Visual Features [article]

Mehmet Ali Arabacı, Fatih Özkan, Elif Surer, Peter Jančovič, Alptekin Temizel
2019 arXiv   pre-print
In this work, we propose a new framework for egocentric activity recognition problem based on combining audio-visual features with multi-kernel learning (MKL) and multi-kernel boosting (MKBoost).  ...  Egocentric activity recognition in first-person videos has an increasing importance with a variety of applications such as lifelogging, summarization, assisted-living and activity tracking.  ...  Multiple-Kernel Boosting (MKBoost) each boosting trial, a distribution of weights is engaged to indicate the importance of the training examples for learning.  ... 
arXiv:1807.00612v2 fatcat:6bdk35purrfgnlraheavbbuodi

Robust Visual Tracking via Multiple Kernel Boosting With Affinity Constraints

Fan Yang, Huchuan Lu, Ming-Hsuan Yang
2014 IEEE transactions on circuits and systems for video technology (Print)  
We propose a novel algorithm by extending the multiple kernel learning framework with boosting for an optimal combination of features and kernels, thereby facilitating robust visual tracking in complex  ...  While spatial information has been taken into account in conventional multiple kernel learning algorithms, we impose novel affinity constraints to exploit the locality of support vectors from a different  ...  Multiple Kernel Boosting A. Multiple Kernel Learning Support vector machines have been successfully applied to numerous classification and regression problems.  ... 
doi:10.1109/tcsvt.2013.2276145 fatcat:z6x4qozsj5dytgstpdvphy4w4u

Learning Ensembles of Potential Functions for Structured Prediction with Latent Variables

Hossein Hajimirsadeghi, Greg Mori
2015 2015 IEEE International Conference on Computer Vision (ICCV)  
This paper presents HCRF-Boost, a novel and general framework for learning HCRFs in functional space.  ...  We validate the effectiveness of this method on tasks such as group activity recognition, human action recognition, and multi-instance learning of video events.  ...  Cardinality Models for Multi-Instance Learning: Multimedia Event Detection Multiple instance learning (MIL) aims to recognize patterns from weakly supervised data.  ... 
doi:10.1109/iccv.2015.462 dblp:conf/iccv/HajimirsadeghiM15 fatcat:z3yegkffybcfrhd6pe5zvtnh3y

Two-person interaction recognition via spatial multiple instance embedding

Fadime Sener, Nazli Ikizler-Cinbis
2015 Journal of Visual Communication and Image Representation  
Experimental results on two benchmark datasets validate that using two-person visual descriptors together with spatial multiple instance learning offers an effective way for inferring the type of the interaction  ...  between people into the multiple instance learning process.  ...  Conclusion In this study, we propose a multiple instance learning (MIL) based approach for two-person interaction recognition in videos.  ... 
doi:10.1016/j.jvcir.2015.07.016 fatcat:hq6dq2hs55gdjkv6hc4onqxzt4

A Comprehensive Study of Group Activity Recognition Methods in Video

S. A. Vahora, N. C. Chauhan
2017 Indian Journal of Science and Technology  
Findings: Different models of group activity recognition are characterized as per the capabilities of the defined model considering individual pose of person, atomic activity of person, person-person interaction  ...  Methods/Statistical Analysis: Different methods of group activity recognition categorized and analyzed according to hand-crafted and learned feature descriptors.  ...  In the proposed structure prediction function with the help of Boosted Hidden Conditional Random Fields (HCRFs) for group activity. 33 This function learn over the inputs, outputs and the discrete variables  ... 
doi:10.17485/ijst/2017/v10i23/113996 fatcat:5ltu45vqmvdgxgeasifu3fipry

Multi-view Recognition Using Weighted View Selection [chapter]

Scott Spurlock, Hui Wu, Richard Souvenir
2015 Lecture Notes in Computer Science  
Our method is built on top of 2D recognition algorithms and casts view selection as the problem of optimizing kernel weights in multiple kernel learning.  ...  In this paper, we present an algorithm for multi-view recognition in a distributed camera setting that learns which viewpoints are most discriminative for particular instances of ambiguity.  ...  Multiple kernel learning (MKL) has emerged as an alternative to simply selecting a single kernel function, with multiple approaches to learning weighted combinations of kernels [17] .  ... 
doi:10.1007/978-3-319-16817-3_35 fatcat:5zb2epknrvba3ehifkzlz4j2gi

Domain-Adaptive Discriminative One-Shot Learning of Gestures [chapter]

Tomas Pfister, James Charles, Andrew Zisserman
2014 Lecture Notes in Computer Science  
The domain adaptation and learning methods are evaluated on two large scale challenging gesture datasets: one for sign language, and the other for Italian hand gestures.  ...  We also show the benefits of using the recently introduced Global Alignment Kernel [12] , instead of the standard Dynamic Time Warping that is generally used for time alignment.  ...  Acknowledgements: We are grateful to Patrick Buehler and Sophia Pfister for help and discussions. Financial support was provided by Osk. Huttunen Foundation and EPSRC grant EP/I012001/1.  ... 
doi:10.1007/978-3-319-10599-4_52 fatcat:dosr662razhmxgbxotpuiprgqe

Image-Set Based Face Recognition Using Boosted Global and Local Principal Angles [chapter]

Xi Li, Kazuhiro Fukui, Nanning Zheng
2010 Lecture Notes in Computer Science  
The discriminative power of each principal angle for the global and each local sub-pattern is explicitly exploited by learning a strong classifier in a boosting manner.  ...  Inspired by the work of [4, 14] , this paper presents a robust framework for image-set based face recognition using boosted global and local principal angles.  ...  [4] is one of the most successful algorithms for face recognition. In their method, the original multi-class face recognition problem is first converted into a two-class problem.  ... 
doi:10.1007/978-3-642-12307-8_30 fatcat:wbo26vnzpnhora6lhzf5pvhylu

Active Learning of Ensemble Classifiers for Gesture Recognition [chapter]

J. Schumacher, D. Sakič, A. Grumpe, Gernot A. Fink, C. Wöhler
2012 Lecture Notes in Computer Science  
In addition to supervised learning, we make use of both labelled and unlabelled data in an active learning framework in order to reduce the effort required for manual labelling.  ...  The active learning scenario yields recognition rates in excess of 80% even when only a fraction of 20% of all training samples are used.  ...  samples associated with 11 persons used for active learning, and an independent test set consisting of samples associated with 2 persons.  ... 
doi:10.1007/978-3-642-32717-9_50 fatcat:4xynfrycoba2dmv4mn22potjym

Two-person interaction detection using body-pose features and multiple instance learning

Kiwon Yun, Jean Honorio, Debaleena Chattopadhyay, Tamara L. Berg, Dimitris Samaras
2012 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops  
Microsoft Kinect) provides adequate accuracy for real-time full-body human tracking for activity recognition applications.  ...  For whole sequence classification, we also explore techniques related to Multiple Instance Learning (MIL) in which the sequence is represented by a bag of body-pose features.  ...  Multiple Instance Learning: Multiple Instance Learning (MIL) is a variant of supervised learning.  ... 
doi:10.1109/cvprw.2012.6239234 dblp:conf/cvpr/YunHCBS12 fatcat:ly52lrf3l5a4zkxtexm3iwlup4

Multi-modal & Multi-view & Interactive Benchmark Dataset for Human Action Recognition

Ning Xu, Anan Liu, Weizhi Nie, Yongkang Wong, Fuwu Li, Yuting Su
2015 Proceedings of the 23rd ACM international conference on Multimedia - MM '15  
Human action recognition is one of the most active research areas in both computer vision and machine learning communities.  ...  This benchmark can provide solid basis for the evaluation of this task and will benefit advancing related computer vision and machine learning research topics.  ...  Adaptive multiple kernel learning proposed by Xu et al. [4] is a representative method.  ... 
doi:10.1145/2733373.2806315 dblp:conf/mm/XuLNWLS15 fatcat:wd6ifkmjfzbafbulmm5zoe76n4

A Study of Fall Detection in Assisted Living: Identifying and Improving the Optimal Machine Learning Method

Nirmalya Thakur, Chia Y. Han
2021 Journal of Sensor and Actuator Networks  
First, it presents and discusses a comprehensive comparative study, where 19 different machine learning methods were used to develop fall detection systems, to deduce the optimal machine learning method  ...  for the development of such systems.  ...  In order of decreasing class precision value for the detection of falls, these machine learning methods can be arranged as k-NN > gradient boosted trees > naïve bayes (kernel) > artificial neural network  ... 
doi:10.3390/jsan10030039 fatcat:ycdwrr55pffzrdk6vnd6flfepq

AdaBoost Gabor Fisher Classifier for Face Recognition [chapter]

Shiguang Shan, Peng Yang, Xilin Chen, Wen Gao
2005 Lecture Notes in Computer Science  
This paper proposes the AdaBoost Gabor Fisher Classifier (AGFC) for robust face recognition, in which a chain AdaBoost learning method based on Bootstrap re-sampling is proposed and applied to face recognition  ...  with impressive recognition performance.  ...  AdaBoost (Adaptive Boosting) is a typical instance of Boosting learning.  ... 
doi:10.1007/11564386_22 fatcat:ukvogi244nbiditqeink4pv6ry
« Previous Showing results 1 — 15 out of 8,707 results