Multimodal deep autoencoder for human pose recovery
Video-based human pose recovery is usually conducted by retrieving relevant poses using
image features. In the retrieving process, the mapping between 2D images and 3D poses is …
image features. In the retrieving process, the mapping between 2D images and 3D poses is …
A region-based image caption generator with refined descriptions
Describing the content of an image is a challenging task. To enable detailed description, it
requires the detection and recognition of objects, people, relationships and associated …
requires the detection and recognition of objects, people, relationships and associated …
Deep view-sensitive pedestrian attribute inference in an end-to-end model
MS Sarfraz, A Schumann, Y Wang… - arXiv preprint arXiv …, 2017 - arxiv.org
Pedestrian attribute inference is a demanding problem in visual surveillance that can
facilitate person retrieval, search and indexing. To exploit semantic relations between …
facilitate person retrieval, search and indexing. To exploit semantic relations between …
Online feature selection with group structure analysis
Online selection of dynamic features has attracted intensive interest in recent years.
However, existing online feature selection methods evaluate features individually and …
However, existing online feature selection methods evaluate features individually and …
Fashion apparel detection: the role of deep convolutional neural network and pose-dependent priors
K Hara, V Jagadeesh… - 2016 IEEE Winter …, 2016 - ieeexplore.ieee.org
In this work, we propose and address a new computer vision task, which we call fashion item
detection, where the aim is to detect various fashion items a person in the image is wearing …
detection, where the aim is to detect various fashion items a person in the image is wearing …
Hypergraph regularized autoencoder for image-based 3D human pose recovery
C Hong, X Chen, X Wang, C Tang - Signal processing, 2016 - Elsevier
Image-based human pose recovery is usually conducted by retrieving relevant poses with
image features. However, semantic gap exists for current feature extractors, which limits …
image features. However, semantic gap exists for current feature extractors, which limits …
Dense-captionnet: a sentence generation architecture for fine-grained description of image semantics
Automatic image captioning, a highly challenging research problem, aims to understand and
describe the contents of the complex scene in human understandable natural language. The …
describe the contents of the complex scene in human understandable natural language. The …
Watch fashion shows to tell clothing attributes
In this paper, we propose a novel semi-supervised method to predict clothing attributes with
the assistance of unlabeled data like fashion shows. To this end, a two-stage framework is …
the assistance of unlabeled data like fashion shows. To this end, a two-stage framework is …
Multinomial latent logistic regression for image understanding
In this paper, we present multinomial latent logistic regression (MLLR), a new learning
paradigm that introduces latent variables to logistic regression. By inheriting the advantages …
paradigm that introduces latent variables to logistic regression. By inheriting the advantages …
基于改进的DenseNet-BC 对少数民族服饰的识别.
杨冰， 徐丹， 张豪远， 罗海妮 - Journal of Zhejiang University …, 2021 - search.ebscohost.com
随着信息技术的发展, 数字技术越来越多地应用于民族文化数字化保护, 民族服饰的数字化及
分类问题也日益受关注. 相比一般服饰, 少数民族服饰具有更多的细节特征信息 …
分类问题也日益受关注. 相比一般服饰, 少数民族服饰具有更多的细节特征信息 …