162 Hits in 6.1 sec

Fashion Meets Computer Vision: A Survey [article]

Wen-Huang Cheng, Sijie Song, Chieh-Yun Chen, Shintami Chusnul Hidayati, Jiaying Liu
2021 arXiv   pre-print
Fashion, mainly conveyed by vision, has thus attracted much attention from computer vision researchers in recent years.  ...  Given the rapid development, this paper provides a comprehensive survey of more than 200 major fashion-related works covering four main aspects for enabling intelligent fashion: (1) Fashion detection includes  ...  A similar idea was also employed in [160] , where the proposed generator, referred to as metric-regularized cGAN, was regularized by a projected compatibility distance function.  ... 
arXiv:2003.13988v2 fatcat:ajzvyn4ck5gqxk5ht5u3mrdmba

Visually-Aware Fashion Recommendation and Design with Generative Image Models [article]

Wang-Cheng Kang, Chen Fang, Zhaowen Wang, Julian McAuley
2017 arXiv   pre-print
Furthermore, we show that our model can be used generatively, i.e., given a user and a product category, we can generate new images (i.e., clothing items) that are most consistent with their personal taste  ...  Recent work has shown that approaches to 'visual' recommendation (e.g. clothing, art, etc.) can be made more accurate by incorporating visual signals directly into the recommendation objective, using '  ...  A GAN consists of a generator G and a discriminator D, which are usually implemented as multi-layer convolutional or deconvolutional neural networks.  ... 
arXiv:1711.02231v1 fatcat:xytgylq6bvbthhcebq3hccunfe

C-Flow: Conditional Generative Flow Models for Images and 3D Point Clouds [article]

Albert Pumarola, Stefan Popov, Francesc Moreno-Noguer, Vittorio Ferrari
2020 arXiv   pre-print
In this paper, we introduce C-Flow, a novel conditioning scheme that brings normalizing flows to an entirely new scenario with great possibilities for multi-modal data modeling.  ...  much attention as alternative generative models.  ...  It is also partially supported by the EU project TER-RINET: The European robotics research infrastructure network H2020-INFRAIA-2017-1-730994.  ... 
arXiv:1912.07009v2 fatcat:duekym2fwvd37it6k6uxzh3vda

A Decade Survey of Content Based Image Retrieval using Deep Learning [article]

Shiv Ram Dubey
2020 arXiv   pre-print
Generally, the similarity between the representative features of the query image and dataset images is used to rank the images for retrieval.  ...  The content based image retrieval aims to find the similar images from a large scale dataset against a query image.  ...  At the same time, a regularized GAN is used to introduce the BinGAN model [171] to learn the compact binary patterns.  ... 
arXiv:2012.00641v1 fatcat:2zcho2szpzcc3cs6uou3jpcley

Learning to Dress 3D People in Generative Clothing [article]

Qianli Ma, Jinlong Yang, Anurag Ranjan, Sergi Pujades, Gerard Pons-Moll, Siyu Tang, Michael J. Black
2020 arXiv   pre-print
To address this, we learn a generative 3D mesh model of clothed people from 3D scans with varying pose and clothing.  ...  Specifically, we train a conditional Mesh-VAE-GAN to learn the clothing deformation from the SMPL body model, making clothing an additional term in SMPL.  ...  While MJB is a part-time employee of Amazon, his research was performed solely at, and funded solely by, MPI.  ... 
arXiv:1907.13615v3 fatcat:qu4bywdhxrerbcjzzayxugbggu

Deep Learning for Sensor-based Human Activity Recognition: Overview, Challenges and Opportunities [article]

Kaixuan Chen, Dalin Zhang, Lina Yao, Bin Guo, Zhiwen Yu, Yunhao Liu
2021 arXiv   pre-print
We then propose a new taxonomy to structure the deep methods by challenges.  ...  We first introduce the multi-modality of the sensory data and provide information for public datasets that can be used for evaluation in different challenge tasks.  ...  The most popular approach of SFF is to organize the raw sensing sequences into a 2D matrix by stacking along the modality dimension, and then to apply a 2D-CNN to the 2D matrix with 1D filters [42, 162  ... 
arXiv:2001.07416v2 fatcat:km2b3xn4sngtxgkdck6ymlmu3m

Big Data driven Product Design: A Survey [article]

Huafeng Quan, Shaobo Li, Changchang Zeng, Hongjing Wei, Jianjun Hu
2021 arXiv   pre-print
This paper aims to conduct a comprehensive survey on big data driven product design.  ...  reviews reflect customer evaluations and requirements; product images contain information of shape,color, and texture which can inspire designers to get initial design schemes more quickly or even directly generate  ...  [255] proposed a flow-navigated warping GAN (FW-GAN) to generate a try-on video conditioned on a person image, the desired clothes image, and a series of target poses.  ... 
arXiv:2109.11424v1 fatcat:ntw77c3grbbbllerzrwna32aem

Recovering 3D Human Mesh from Monocular Images: A Survey [article]

Yating Tian, Hongwen Zhang, Yebin Liu, Limin Wang
2022 arXiv   pre-print
We start with the introduction of body models and then elaborate recovery frameworks and training objectives by providing in-depth analyses of their strengths and weaknesses.  ...  Since the release of statistical body models, 3D human mesh recovery has been drawing broader attention.  ...  Generative Adversarial Network (GAN). Researchers first resort to GAN [205] to obtain adversarial priors.  ... 
arXiv:2203.01923v2 fatcat:vb6xa5wdsrhdxd2ebvg54qq2m4

A Survey on Generative Adversarial Networks: Variants, Applications, and Training [article]

Abdul Jabbar, Xi Li, Bourahla Omar
2020 arXiv   pre-print
The Generative Models have gained considerable attention in the field of unsupervised learning via a new and practical framework called Generative Adversarial Networks (GAN) due to its outstanding data  ...  Herein, we survey several training solutions proposed by different researchers to stabilize GAN training.  ...  [231] , Mode Regularized GAN (MRGAN) [232] , Multi-Agent Diverse GAN (MAD-GAN) [234] try to strengthen the generator network to expand its capacity by restricting it from optimizing for a single rigid  ... 
arXiv:2006.05132v1 fatcat:gyjezuh5sfdilkp43ydsea5cwa

Towards Fine-grained Human Pose Transfer with Detail Replenishing Network [article]

Lingbo Yang, Pan Wang, Chang Liu, Zhanning Gao, Peiran Ren, Xinfeng Zhang, Shanshe Wang, Siwei Ma, Xiansheng Hua, Wen Gao
2020 arXiv   pre-print
Thereafter, we substantiate the proposed methodology with a Detail Replenishing Network (DRN) and a corresponding coarse-to-fine model training scheme.  ...  However, existing HPT methods often suffer from three fundamental issues: detail deficiency, content ambiguity and style inconsistency, which severely degrade the visual quality and realism of generated  ...  L GAN (7) where L sty is the Gram-matrix based style loss [16] : L sty = 1 CHW l G(φ l (I t )) − G(φ l (Ĩ t )) 2 F (8) where G is the Gram matrix: G(F ) ij = 1 CHW H h=1 W w=1 F ihw F jhw The adversarial  ... 
arXiv:2005.12494v1 fatcat:uof52iucwzbuzlakzkrt72cwqi

Recent Advances in Zero-shot Recognition [article]

Yanwei Fu, Tao Xiang, Yu-Gang Jiang, Xiangyang Xue, Leonid Sigal, and Shaogang Gong
2017 arXiv   pre-print
This article provides a comprehensive review of existing zero-shot recognition techniques covering various aspects ranging from representations of models, and from datasets and evaluation settings.  ...  One approach to scaling up the recognition is to develop models capable of recognizing unseen categories without any training instances, or zero-shot recognition/ learning.  ...  Yanwei Fu is supported by The Program for Professor of Special Appointment (Eastern Scholar) at Shanghai Institutions of Higher Learning.  ... 
arXiv:1710.04837v1 fatcat:u3mp6dgj2rgqrarjm4dcywegmy

Effective and Privacy preserving Tabular Data Synthesizing [article]

Aditya Kunar
2021 arXiv   pre-print
In this thesis, we develop CTAB-GAN, a novel conditional table GAN architecture that can effectively model diverse data types with complex distributions.  ...  , by up to 17%.  ...  Figure 4 . 5 : 45 Challenges of modeling industrial dataset using existing GAN-based table generator: (a) Mixed data type, (b) long tail distribution, and (c) Skewed multi-modal data To such ends, the  ... 
arXiv:2108.10064v1 fatcat:dtsz6dqzfrhgbdcwgwz4ipsf5u

High-order Differentiable Autoencoder for Nonlinear Model Reduction [article]

Siyuan Shen, Yang Yin, Tianjia Shao, He Wang, Chenfanfu Jiang, Lei Lan, Kun Zhou
2021 arXiv   pre-print
Along this pipeline, we also design a sampling network and a weighting network to enable weight-varying Cubature integration in order to incorporate nonlinearity in the model reduction.  ...  We attack those difficulties by exploiting complex-step finite difference, coupled with reverse automatic differentiation.  ...  Training Poses Generation We generate training poses by running a scripted simulation.  ... 
arXiv:2102.11026v1 fatcat:biekm6nrvngrjdcligsgg7lsxi

Table of contents

2021 ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)  
......... 3745 EMBEDDING Shenfei Pei, Feiping Nie, Rong Wang, Xuelong Li, Northwestern Polytechnical University, China MLSP-5.2: TOWARDS EFFICIENT AGE ESTIMATION BY EMBEDDING POTENTIAL ................  ...  GAUSSIAN PROCESS LATENT VARIABLE MODEL Kyohei Kamikawa, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama, Hokkaido University, Japan MMSP-1.3: A MULTI-LAYER MULTI-CHANNEL ATTENTIVE NETWORK FOR ...........  ... 
doi:10.1109/icassp39728.2021.9414617 fatcat:m5ugnnuk7nacbd6jr6gv2lsfby

Compatible and Diverse Fashion Image Inpainting [article]

Xintong Han, Zuxuan Wu, Weilin Huang, Matthew R. Scott, Larry S. Davis
2019 arXiv   pre-print
In this paper, we propose to explicitly model visual compatibility through fashion image inpainting.  ...  More importantly, for each generation network, we introduce two encoders interacting with one another to learn latent code in a shared compatibility space.  ...  Davis and Zuxuan Wu are partially supported by the Office of Naval Research under Grant N000141612713.  ... 
arXiv:1902.01096v2 fatcat:ephb5bsn2vgurecvsunubyvc7e
« Previous Showing results 1 — 15 out of 162 results