1,534 Hits in 3.5 sec

Hard-sample Guided Hybrid Contrast Learning for Unsupervised Person Re-Identification [article]

Zheng Hu, Chuang Zhu, Gang He
2021 arXiv   pre-print
Recently, more attention has been paid to unsupervised Re-ID algorithms based on clustered pseudo-label.  ...  In this paper, we propose a Hard-sample Guided Hybrid Contrast Learning (HHCL) approach combining cluster-level loss with instance-level loss for unsupervised person Re-ID.  ...  Algorithm 1 : 1 Hard-sample Guided Hybrid Contrast Learning for Unsupervised Re-IdentificationData: An unlabeled training set X Input: ImageNet pre-trained model ϕ(·; θ), the iteration number N , the training  ... 
arXiv:2109.12333v1 fatcat:rgticvv3i5a55j6xy64uzvksiy

A survey on trajectory clustering analysis [article]

Jiang Bian, Dayong Tian, Yuanyan Tang, Dacheng Tao
2018 arXiv   pre-print
Existing trajectory clustering methods can be grouped into three categories: unsupervised, supervised and semi-supervised algorithms.  ...  This paper provides a holistic understanding and deep insight into trajectory clustering, and presents a comprehensive analysis of representative methods and promising future directions.  ...  Re-sampling Methods Re-sampling methods choose trajectory points by sampling rule to unify trajectory lengths.  ... 
arXiv:1802.06971v1 fatcat:z5d3nga4ivfmffwcf7moohrquq

A Survey on Content Based Image Retrieval Using Convolutional Neural Networks

2020 International Journal of Advanced Trends in Computer Science and Engineering  
It also focuses on content based image retrieval technique (CBIR), with an unsupervised learning method using convolutional Neural Networks (CNN).  ...  Traditional hashing techniques are most commonly used to provide high quality search results for labeled images.  ...  Hash code learning is framed from a unified unsupervised framework.  ... 
doi:10.30534/ijatcse/2020/70952020 fatcat:vjpq2j2pdza5di426baglhavai

Vocabulary hierarchy optimization for effective and transferable retrieval

Rongrong Ji, Xing Xie, Hongxun Yao, Wei-Ying Ma
2009 2009 IEEE Conference on Computer Vision and Pattern Recognition  
In this paper, we describe an unsupervised optimization strategy in generating the hierarchy structure of visual vocabulary, which produces a more effective and adaptive retrieval model for large-scale  ...  We deployed a large-scale image retrieval system using a vocabulary tree model to validate our advances.  ...  In a large-scale application scenario, our VT Shift algorithm can maintain good performance for database variance without model re-generation cost.  ... 
doi:10.1109/cvpr.2009.5206680 dblp:conf/cvpr/JiXYM09 fatcat:otadc56kobh2dhxsvm3efrimfi

2020 Index IEEE Transactions on Image Processing Vol. 29

2020 IEEE Transactions on Image Processing  
., +, TIP 2020 8213-8225 A Unified Deep Model for Joint Facial Expression Recognition, Face Synthesis, and Face Alignment.  ...  ., +, TIP 2020 2795-2807 A Multi-Scale Spatial-Temporal Attention Model for Person Re-Identifica- tion in Videos.  ... 
doi:10.1109/tip.2020.3046056 fatcat:24m6k2elprf2nfmucbjzhvzk3m

Robust Anchor Embedding for Unsupervised Video Person re-IDentification in the Wild [chapter]

Mang Ye, Xiangyuan Lan, Pong C. Yuen
2018 Lecture Notes in Computer Science  
To achieve it, we propose a novel Robust AnChor Embedding (RACE) framework via deep feature representation learning for large-scale unsupervised video re-ID.  ...  This paper addresses the scalability and robustness issues of estimating labels from imbalanced unlabeled data for unsupervised video-based person re-identification (re-ID).  ...  In this paper, we propose a scalable solution with deep neural networks for unsupervised video re-ID under wild settings.  ... 
doi:10.1007/978-3-030-01234-2_11 fatcat:dycgvmar55efdmx2dxzdib7yq4

Unsupervised Person Re-identification via Multi-label Classification [article]

Dongkai Wang, Shiliang Zhang
2020 arXiv   pre-print
Our method starts by assigning each person image with a single-class label, then evolves to multi-label classification by leveraging the updated ReID model for label prediction.  ...  The challenge of unsupervised person re-identification (ReID) lies in learning discriminative features without true labels.  ...  Unsupervised person re-ID performance comparison with state-of-the-art methods on Market-1501 and DukeMTMC-reID.  ... 
arXiv:2004.09228v1 fatcat:kky7hzj5svhchmvnbfpnvxg2g4

A summary of the 2012 JHU CLSP workshop on zero resource speech technologies and models of early language acquisition

Aren Jansen, Emmanuel Dupoux, Sharon Goldwater, Mark Johnson, Sanjeev Khudanpur, Kenneth Church, Naomi Feldman, Hynek Hermansky, Florian Metze, Richard Rose, Mike Seltzer, Pascal Clark (+15 others)
2013 2013 IEEE International Conference on Acoustics, Speech and Signal Processing  
We summarize the accomplishments of a multi-disciplinary workshop exploring the computational and scientific issues surrounding zero resource (unsupervised) speech technologies and related models of early  ...  Centered around the tasks of phonetic and lexical discovery, we consider unified evaluation metrics, present two new approaches for improving speaker independence in the absence of supervision, and evaluate  ...  for unsupervised learning.  ... 
doi:10.1109/icassp.2013.6639245 dblp:conf/icassp/JansenDGJKCFHMRSCMVBBCDFHLLNPRST13 fatcat:4lrcendhhjgz5nmr2fsovmzgae

Joint Active Learning with Feature Selection via CUR Matrix Decomposition

Changsheng Li, Xiangfeng Wang, Weishan Dong, Junchi Yan, Qingshan Liu, Hongyuan Zha
2018 IEEE Transactions on Pattern Analysis and Machine Intelligence  
This paper focuses on the problem of simultaneous sample and feature selection for machine learning in a fully unsupervised setting.  ...  We solve it efficiently by an iterative algorithm, and prove its global convergence.  ...  Therefore, it will benefit from devising principled model and algorithm for incorporating active learning and feature selection in a unified fashion. Recently, Raghavan et al.  ... 
doi:10.1109/tpami.2018.2840980 pmid:29993711 fatcat:q2hbthaxzjcdzazu6vmx5yrp5i

2019 Index IEEE Transactions on Knowledge and Data Engineering Vol. 31

2020 IEEE Transactions on Knowledge and Data Engineering  
Semertzidis , K., +, TKDE Jan. 2019 181-194 Iterative methods Accelerated and Inexact Soft-Impute for Large-Scale Matrix and Tensor Completion.  ...  ., +, TKDE May 2019 996-1009 Visualization ROMIR: Robust Multi-View Image Re-Ranking.  ... 
doi:10.1109/tkde.2019.2953412 fatcat:jkmpnsjcf5a3bhhf4ian66mj5y

On integrating re-ranking and rank list fusion techniques for image retrieval

K. S. Arun, V. K. Govindan, S. D. Madhu Kumar
2017 International Journal of Data Science and Analytics  
The re-ranking algorithm introduced in this work utilizes distance correlation coefficient to refine the search result generated by a given retrieval model.  ...  To this end, we present a novel image re-ranking scheme for reordering the initial search results returned by multiple retrieval models and an efficient rank list fusion scheme to combine these refined  ...  The proposed framework unifies a distance correlation coefficient-based image re-ranking algorithm and a PSO-based rank list fusion scheme.  ... 
doi:10.1007/s41060-017-0056-z dblp:journals/ijdsa/ArunGK17 fatcat:ibdnbknlmrc27feci2typq5fdu

Discovering human interactions in videos with limited data labeling

Mehran Khodabandeh, Arash Vahdat, Guang-Tong Zhou, Hossein Hajimirsadeghi, Mehrsan Javan Roshtkhari, Greg Mori, Stephen Se
2015 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)  
We present a novel approach for discovering human interactions in videos.  ...  This is achieved by formulating the whole process as a unified constrained latent max-margin clustering problem.  ...  This feedback is collected iteratively and the clusters are re-generated ( Fig. 3.1(c) ), resulting in pure clusters after a few iterations.  ... 
doi:10.1109/cvprw.2015.7301278 dblp:conf/cvpr/KhodabandehVZHR15 fatcat:lxul3g7tkfd4fgem5mmg7nye7y

Robust Discriminative Metric Learning for Image Representation

Zhengming Ding, Ming Shao, Wonjun Hwang, Sungjoov Suh, Jae-Joon Han, Changkyu Choi, Yun Fu
2019 IEEE transactions on circuits and systems for video technology (Print)  
In this paper, we propose a Robust Discriminative Metric Learning algorithm (RDML) via fast low-rank representation and denoising strategy.  ...  However, it is still a challenge to build a robust and discriminative metric, especially for corrupted data in the real-world application.  ...  CONCLUSIONS In this paper, we proposed a robust discriminative metric learning algorithm via seeking a fast low-rank representation and building a compact basis in a unified framework.  ... 
doi:10.1109/tcsvt.2018.2879626 fatcat:o7x6pyoqcbbjbfu35dmp5uvaay

Enforcing and Discovering Structure in Machine Learning [article]

Francesco Locatello
2021 arXiv   pre-print
Doing so may translate to faster, more accurate, and more flexible models, which may directly relate to real-world impact.  ...  It may be prudent to enforce corresponding structural properties to a learning algorithm's solution, such as incorporating prior beliefs, natural constraints, or causal structures.  ...  The algorithm will then fit the tails and, in the following iterations, re-learn a distribution close to q 0 .  ... 
arXiv:2111.13693v1 fatcat:2urmfjeh6nhvjeiv3qoiy5hrum

Robust Multi-view Representation: A Unified Perspective from Multi-view Learning to Domain Adaption

Zhengming Ding, Ming Shao, Yun Fu
2018 Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence  
First of all, we formulate a unified learning framework which is able to model most existing multi-view learning and domain adaptation in this line.  ...  Following this, we conduct a comprehensive discussion across these two problems by reviewing the algorithms along these two topics, including multi-view clustering, multi-view classification, zero-shot  ...  Thus, algorithm accelerating would benefit the deployment in the real-world applications, especially when dealing with large-scale data.  ... 
doi:10.24963/ijcai.2018/767 dblp:conf/ijcai/DingSF18 fatcat:s2cwblwxnbgavaeirobiyyfk6e
« Previous Showing results 1 — 15 out of 1,534 results