Filters








1,171 Hits in 6.1 sec

Table of Contents

2019 IEEE transactions on multimedia  
Hancock 300 Unsupervised Learning of Human Pose Distance Metric via Sparsity Locality Preserving Projections . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .  ...  Pu 351 (Contents Continued on Back Cover) (Contents Continued from Front Cover) Multimodal Human-Machine Interfaces and Interaction Attention-Deep Learning for Multimedia Processing Gradient Prior-Aided  ... 
doi:10.1109/tmm.2019.2892660 fatcat:35egnbnnofbkpnmrujdvtpjj7m

Author Index

2010 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition  
for Unsupervised Human Behavior Analysis What's going on?  ...  via Nonlocal-Means Regularization with Application to Depth from Defocus Fears, Scott Metric-Induced Optimal Embedding for Intrinsic 3D Shape Analysis Fei-Fei, Li Efficient Extraction of Human  ... 
doi:10.1109/cvpr.2010.5539913 fatcat:y6m5knstrzfyfin6jzusc42p54

Graph Autoencoder-Based Unsupervised Feature Selection with Broad and Local Data Structure Preservation [article]

Siwei Feng, Marco F.Duarte
2018 arXiv   pre-print
Additionally, we include spectral graph analysis on the projected data into the learning process to achieve local data geometry preservation from the original data space to the low-dimensional feature  ...  These works first map data onto a low-dimensional subspace and then select features by posing a sparsity constraint on the transformation matrix.  ...  To the best of our knowledge, we are the first to combine unsupervised feature selection with an autoencoder design and the preservation of local data structure.  ... 
arXiv:1801.02251v2 fatcat:tgtkgizpnzf3xdvgibg3ep54xe

2021 Index IEEE Transactions on Multimedia Vol. 23

2021 IEEE transactions on multimedia  
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.  ...  ., +, TMM 2021 176-188 Pose-Normalized and Appearance-Preserved Street-to-Shop Clothing Image Generation and Feature Learning.  ...  Blind Image Clustering for Camera Source Identification via Row-Sparsity Optimization.  ... 
doi:10.1109/tmm.2022.3141947 fatcat:lil2nf3vd5ehbfgtslulu7y3lq

Normalized Diversification [article]

Shaohui Liu, Xiao Zhang, Jianqiao Wangni, Jianbo Shi
2021 arXiv   pre-print
We introduce the concept of normalized diversity which force the model to preserve the normalized pairwise distance between the sparse samples from a latent parametric distribution and their corresponding  ...  Experimental results show that our method achieves consistent improvement on unsupervised image generation, conditional image generation and hand pose estimation over strong baselines.  ...  For hand pose estimation, we choose to combine the l 2 distance on the visible joints and the joint adversarial discriminator of (x i ,ŷ i ) (image-pose GAN), whereŷ i denotes the 2D projection of the  ... 
arXiv:1904.03608v3 fatcat:kw4vywt6azbbthd57asivdeude

Learning patch-dependent kernel forest for person re-identification

Wei Wang, Ali Taalimi, Kun Duan, Rui Guo, Hairong Qi
2016 2016 IEEE Winter Conference on Applications of Computer Vision (WACV)  
by a combination of many simple local transforms, which guides us to learn a set of more specific local metrics other than a fixed metric working on the feature vector of a whole image.  ...  The pairwise distance between a query image and a gallery image is summarized based on all the pairwise distance of local patches measured by different local metric kernels.  ...  Figure 3 .Figure 4 . 34 Illustration of the greedy local patches matching via pairwise distance.  ... 
doi:10.1109/wacv.2016.7477578 dblp:conf/wacv/WangTDGQ16 fatcat:sed4qqw4jve5xdjqgy4jjznfw4

Landmarks Augmentation with Manifold-Barycentric Oversampling [article]

Iaroslav Bespalov, Nazar Buzun, Oleg Kachan, Dmitry V. Dylov
2021 arXiv   pre-print
The training of Generative Adversarial Networks (GANs) requires a large amount of data, stimulating the development of new augmentation methods to alleviate the challenge.  ...  Our approach reduces the overfitting and improves the quality metrics beyond the original data outcome and beyond the result obtained with popular modern augmentation methods.  ...  The learning rates are: 2 · 10−4 (image key-points (ordered), depicting the human pose in the images.  ... 
arXiv:2104.00925v2 fatcat:ucwztbpbnjhglpdszccw6gnxvm

Interpretable machine learning: Fundamental principles and 10 grand challenges

Cynthia Rudin, Chaofan Chen, Zhi Chen, Haiyang Huang, Lesia Semenova, Chudi Zhong
2022 Statistics Survey  
unsupervised disentanglement of neural networks; (7) Dimensionality reduction for data visualization; (8) Machine learning models that can incorporate physics and other generative or causal constraints  ...  ; (9) Characterization of the "Rashomon set" of good models; and (10) Interpretable reinforcement learning.  ...  Global methods aim mainly to preserve distances between any pair of points (rather than neighborhoods), while the local methods emphasize preservation of local neighborhoods (that is, which points are  ... 
doi:10.1214/21-ss133 fatcat:ahzfoilhmfa2rd4hcauvsn3eyy

2020 Index IEEE Transactions on Image Processing Vol. 29

2020 IEEE Transactions on Image Processing  
Nazir, A., +, TIP 2020 7192-7202 Distance measurement Deep Adversarial Metric Learning.  ...  Ma, R., +, TIP 2020 3927-3940 Efficient Evaluation of Image Quality via Deep-Learning Approximation of Perceptual Metrics.  ... 
doi:10.1109/tip.2020.3046056 fatcat:24m6k2elprf2nfmucbjzhvzk3m

Spectral Regression: A Unified Approach for Sparse Subspace Learning

Deng Cai, Xiaofei He, Jiawei Han
2007 Seventh IEEE International Conference on Data Mining (ICDM 2007)  
Some popular methods include Principal Component Analysis (PCA), Linear Discriminant Analysis (LDA) and Locality Preserving Projection (LPP).  ...  USSL casts the problem of learning the projective functions into a regression framework, which facilitates the use of different kinds of regularizers.  ...  Face clustering is an unsupervised task and we compare our algorithm with PCA, SparsePCA and Locality Preserving Projection (LPP) [18] [19] .  ... 
doi:10.1109/icdm.2007.89 dblp:conf/icdm/CaiHH07 fatcat:j34dzernwnfhhjf36hd4ssgo5u

Adversarial Inverse Graphics Networks: Learning 2D-to-3D Lifting and Image-to-Image Translation from Unpaired Supervision [article]

Hsiao-Yu Fish Tung, Adam W. Harley, William Seto, Katerina Fragkiadaki
2017 arXiv   pre-print
We apply AIGNs to 3D human pose estimation and 3D structure and egomotion estimation, and outperform models supervised by only paired annotations.  ...  Researchers have developed excellent feed-forward models that learn to map images to desired outputs, such as to the images' latent factors, or to other images, using supervised learning.  ...  of 3D poses, and minimizes the reprojection error via Expectation-Maximization.  ... 
arXiv:1705.11166v3 fatcat:xe4mr3ajqbd35c23xyiyxac3ym

Transfer Adaptation Learning: A Decade Survey [article]

Lei Zhang, Xinbo Gao
2020 arXiv   pre-print
and adversarial adaptation, which are beyond the early semi-supervised and unsupervised split.  ...  TAL aims to build models that can perform tasks of target domain by learning knowledge from a semantic related but distribution different source domain.  ...  ACKNOWLEDGMENT The author would like to thank the pioneer researchers in transfer learning, domain adaptation and other related fields. The author would also like to thank Dr. Mingsheng Long and Dr.  ... 
arXiv:1903.04687v2 fatcat:wurprqieffalnnp6isfkhh5y5i

6DoF object pose measurement by a monocular manifold-based pattern recognition technique

Rigas Kouskouridas, Konstantinos Charalampous, Antonios Gasteratos
2012 Measurement science and technology  
We employ a manifold modeling architecture that is grounded on a part-based representation of an object, which in turn, is accomplished via an unsupervised clustering of the extracted visual cues.  ...  In this paper, a novel solution to the compound problem of object recognition and 3D pose estimation is presented.  ...  Unlike the PCA, which aims to preserve the global structure of the data, LPP targets to preserve the local structure.  ... 
doi:10.1088/0957-0233/23/11/114005 fatcat:ji7i2oam5raxvg44zhnsltaauy

GLASS: Geometric Latent Augmentation for Shape Spaces [article]

Sanjeev Muralikrishnan, Siddhartha Chaudhuri, Noam Aigerman, Vladimir Kim, Matthew Fisher, Niloy Mitra
2022 arXiv   pre-print
We analyze the Hessian of the as-rigid-as-possible (ARAP) energy to sample from and project to the underlying (local) shape space, and use the augmented dataset to train a variational autoencoder (VAE)  ...  We investigate the problem of training generative models on a very sparse collection of 3D models.  ...  ., preserve local details) and do not distort the model too much (i.e., local lengths of elements are relatively preserved).  ... 
arXiv:2108.03225v3 fatcat:zk5hfto2g5hf7blh6gt3nhok6a

Autonomous Driving with Deep Learning: A Survey of State-of-Art Technologies [article]

Yu Huang, Yue Chen
2020 arXiv   pre-print
Almost at the same time, deep learning has made breakthrough by several pioneers, three of them (also called fathers of deep learning), Hinton, Bengio and LeCun, won ACM Turin Award in 2019.  ...  This is a survey of autonomous driving technologies with deep learning methods.  ...  Human Pose Estimation Human pose estimation with deep learning falls into bottom-up and top-down categories,where the bottom-up methods are split into single stage or multi-stage.  ... 
arXiv:2006.06091v3 fatcat:nhdgivmtrzcarp463xzqvnxlwq
« Previous Showing results 1 — 15 out of 1,171 results