The recent years' progress in deep learning (DL) technology has resulted in convolutional neural networks (CNNs) capable of producing fast and accurate results, with minimal data preprocessing. Currently, gait ana...
详细信息
DDGI, GIBS, and other similar dynamic global illumination algorithms solve the irradiance integral by shortening and reusing the light path, obtaining the multi-bounce diffuse reflection effect without recursion. Howe...
详细信息
Multi-label zero-shot learning (ML-ZSL), with the difficulty of both multi-label learning and zero-shot learning, aims to recognize various unseen objects that are not observed during training. Previous methods mainly...
详细信息
Deep neural networks have been widely and successfully applied to many critical tasks, such as imagepatternrecognition, natural language processing.and autonomous driving, and large amounts of training data and incr...
详细信息
In this paper, we address the classification of medical actions with only one single sample by developing a novel one-shot learning framework which contains both cross-attention and dynamic time warping (DTW) modules....
详细信息
As the birthplace of soybeans, China has become the world's largest importer and consumer of soybeans. The supply and demand imbalance of soybeans has become one of the significant food and oil security concerns i...
详细信息
With the continuous progress of mankind, the level of sports is particularly important in today's society. Mobile communication system is one of the key parts. This paper proposes a method of human biological sign...
详细信息
The use of eye movements for identifying intrinsic human psychological changes is a hot topic, and the identification of eye states in specific scenarios is the basis for analyzing the test taker's instantaneous p...
详细信息
images form the basis of human vision and are an important source of information for both human perception and machine patternrecognition. Since the development of the image quality evaluation field, a large number o...
详细信息
Sketch-based image retrieval (SBIR) has undergone an increasing interest in the community of computer vision bringing high impact in real applications. For instance, SBIR brings an increased benefit to eCommerce searc...
详细信息
ISBN:
(纸本)9781665448994
Sketch-based image retrieval (SBIR) has undergone an increasing interest in the community of computer vision bringing high impact in real applications. For instance, SBIR brings an increased benefit to eCommerce search engines because it allows users to formulate a query just by drawing what they need to buy. However, current methods showing high precision in retrieval work in a high dimensional space, which negatively affects aspects like memory consumption and time processing. Although some authors have also proposed compact representations, these drastically degrade the performance in a low dimension. Therefore in this work, we present different results of evaluating methods for producing compact embeddings in the context of sketch-based image retrieval. Our main interest is in strategies aiming to keep the local structure of the original space. The recent unsupervised local-topology preserving dimension reduction method UMAP fits our requirements and shows outstanding performance, improving even the precision achieved by SOTA methods. We evaluate six methods in two different datasets. We use Flickr15K and eCommerce datasets;the latter is another contribution of this work. We show that UMAP allows us to have feature vectors of 16 bytes improving precision by more than 35%.
暂无评论