Fashion apparel detection: The role of deep convolutional neural network and pose-dependent priors

Abstract

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 or carrying. The types of fashion items we consider in this work include hat, glasses, bag, pants, shoes and so on. The detection of fashion items can be an important first step of various e-commerce applications for fashion industry. Our method is based on state-of-the-art object detection method pipeline which combines object proposal methods with a Deep Convolutional Neural Network. Since the locations of fashion items are in strong correlation with the locations of body joints positions, we incorporate contextual information from body poses in order to improve the detection performance. Through the experiments, we demonstrate the effectiveness of the proposed method.

Towards better exploiting convolutional neural networks for remote sensing scene classification

“…Specifically, features (usually, called deep features) can be extracted from any layer of a pre-trained network and then used in a given task. Deep features trained on ImageNet (a dataset of everyday objects) have already shown remarkable results in applications like flower categorization [42], human attribute detection [43], bird sub-categorization [44], scene retrieval [45], and many others [37,36], including remote sensing [14,38]. Furthermore, Razavian et al [46] suggest that features obtained from deep learning should be the primary candidate in most visual recognition tasks.…”

Urban Area Detection in Very High Resolution Remote Sensing Images Using Deep Convolutional Neural Networks

“…Deep features can be transferred from natural images to remote sensing images, which has been verified in many works [ 26 ]. With the support of the abundant training data of ImageNet (1.2 million images and 1000 distinct classes), pretrained DCNNs have acquired a sufficient ability of image deep feature extraction and have shown remarkable results in many applications, such as human attribute detection [ 40 ], scene retrieval [ 41 ], robotics [ 42 ] and remote sensing [ 43 , 44 , 45 , 46 , 47 ]. Furthermore, it is very simple to adopt the pre-trained DCNNs as feature extractors since there is no training or tuning needed.…”

Augmenting organizational decision-making with deep learning algorithms: Principles, promises, and challenges

“…Such applications are particularly useful for understanding and segmenting customer feedback using product reviews inside platforms like Amazon and eBay to augment advertising targeting decisions (Kannan & Li, 2017;Xu, Wang, Li, & Haghighi, 2017). Application of DL on image data in fashion firms include apparel segmentation (Zhilan Hu, Yan, & Lin, 2008), apparel recognition (Bossard et al, 2011), apparel classification and retrieval (Hara, Jagadeesh, & Piramuthu, 2016), and apparel classification for tagging (Eshwar et al, 2016). By using various DL outcomes, the fashion firms aim to support their strategic and marketing decisions, through more efficiently identifying personalized products meeting customer needs, monitoring future fashion trends toward informing product-design decisions, market segmentation, and target marketing campaigns.…”