VenueNet: Fine-Grained Venue Discovery by Deep Correlation Learning

2017 ◽  
Author(s):  
Yi Yu ◽  
Suhua Tang ◽  
Kiyoharu Aizawa ◽  
Akiko Aizawa
Keyword(s):  
Fine Grained ◽  
Correlation Learning

Deep cascaded cross-modal correlation learning for fine-grained sketch-based image retrieval

2020 ◽  
Vol 100 ◽  
pp. 107148 ◽  
Author(s):  
Yanfei Wang ◽  
Fei Huang ◽  
Yuejie Zhang ◽  
Rui Feng ◽  
Tao Zhang ◽  
...  
Keyword(s):  
Image Retrieval ◽  
Fine Grained ◽  
Correlation Learning

scholarly journals Graph-Propagation Based Correlation Learning for Weakly Supervised Fine-Grained Image Classification

2020 ◽  
Vol 34 (07) ◽  
pp. 12289-12296 ◽  
Author(s):  
Zhuhui Wang ◽  
Shijie Wang ◽  
Haojie Li ◽  
Zhi Dou ◽  
Jianjun Li
Keyword(s):  
Image Classification ◽  
Feature Representation ◽  
Spatial Context ◽  
Discriminative Power ◽  
Fine Grained ◽  
Semantic Correlation ◽  
Discriminative Feature ◽  
Correlation Learning ◽  
Weakly Supervised ◽  
Graph Propagation

The key of Weakly Supervised Fine-grained Image Classification (WFGIC) is how to pick out the discriminative regions and learn the discriminative features from them. However, most recent WFGIC methods pick out the discriminative regions independently and utilize their features directly, while neglecting the facts that regions' features are mutually semantic correlated and region groups can be more discriminative. To address these issues, we propose an end-to-end Graph-propagation based Correlation Learning (GCL) model to fully mine and exploit the discriminative potentials of region correlations for WFGIC. Specifically, in discriminative region localization phase, a Criss-cross Graph Propagation (CGP) sub-network is proposed to learn region correlations, which establishes correlation between regions and then enhances each region by weighted aggregating other regions in a criss-cross way. By this means each region's representation encodes the global image-level context and local spatial context simultaneously, thus the network is guided to implicitly discover the more powerful discriminative region groups for WFGIC. In discriminative feature representation phase, the Correlation Feature Strengthening (CFS) sub-network is proposed to explore the internal semantic correlation among discriminative patches' feature vectors, to improve their discriminative power by iteratively enhancing informative elements while suppressing the useless ones. Extensive experiments demonstrate the effectiveness of proposed CGP and CFS sub-networks, and show that the GCL model achieves better performance both in accuracy and efficiency.

scholarly journals Cross-media Multi-level Alignment with Relation Attention Network

2018 ◽  
Author(s):  
Jinwei Qi ◽  
Yuxin Peng ◽  
Yuxin Yuan
Keyword(s):  
State Of The Art ◽  
Multimedia Data ◽  
Attention Network ◽  
Attention Model ◽  
Fine Grained ◽  
Cross Media ◽  
Textual Description ◽  
Correlation Learning ◽  
Media Types ◽  
Multi Level

With the rapid growth of multimedia data, such as image and text, it is a highly challenging problem to effectively correlate and retrieve the data of different media types. Naturally, when correlating an image with textual description, people focus on not only the alignment between discriminative image regions and key words, but also the relations lying in the visual and textual context. Relation understanding is essential for cross-media correlation learning, which is ignored by prior cross-media retrieval works. To address the above issue, we propose Cross-media Relation Attention Network (CRAN) with multi-level alignment. First, we propose visual-language relation attention model to explore both fine-grained patches and their relations of different media types. We aim to not only exploit cross-media fine-grained local information, but also capture the intrinsic relation information, which can provide complementary hints for correlation learning. Second, we propose cross-media multi-level alignment to explore global, local and relation alignments across different media types, which can mutually boost to learn more precise cross-media correlation. We conduct experiments on 2 cross-media datasets, and compare with 10 state-of-the-art methods to verify the effectiveness of proposed approach.

Application of an image management system in microscopy

1992 ◽  
Vol 50 (2) ◽  
pp. 1052-1053
Author(s):  
Richard S. Chemock
Keyword(s):  
Data Storage ◽  
Cost Savings ◽  
Image Data ◽  
Analytical Techniques ◽  
Operational Mode ◽  
Fine Grained ◽  
Image Recording ◽  
Primary Output ◽  
Capacity Data ◽  
Image Management System

One of the most common tasks in a typical analysis lab is the recording of images. Many analytical techniques (TEM, SEM, and metallography for example) produce images as their primary output. Until recently, the most common method of recording images was by using film. Current PS/2R systems offer very large capacity data storage devices and high resolution displays, making it practical to work with analytical images on PS/2s, thereby sidestepping the traditional film and darkroom steps. This change in operational mode offers many benefits: cost savings, throughput, archiving and searching capabilities as well as direct incorporation of the image data into reports.The conventional way to record images involves film, either sheet film (with its associated wet chemistry) for TEM or PolaroidR film for SEM and light microscopy. Although film is inconvenient, it does have the highest quality of all available image recording techniques. The fine grained film used for TEM has a resolution that would exceed a 4096x4096x16 bit digital image.

Use of fractals to describe microstructures of porous thick-film platinum electrodes

1992 ◽  
Vol 50 (1) ◽  
pp. 314-315
Author(s):  
Steven D. Toteda
Keyword(s):  
Fractal Dimension ◽  
Power Plants ◽  
Electrical Response ◽  
Cubic Phase ◽  
Platinum Electrodes ◽  
Fine Grained ◽  
Impedance Response ◽  
Platinum Particles ◽  
Energy Surfaces ◽  
Highly Porous

Zirconia oxygen sensors, in such applications as power plants and automobiles, generally utilize platinum electrodes for the catalytic reaction of dissociating O2 at the surface. The microstructure of the platinum electrode defines the resulting electrical response. The electrode must be porous enough to allow the oxygen to reach the zirconia surface while still remaining electrically continuous. At low sintering temperatures, the platinum is highly porous and fine grained. The platinum particles sinter together as the firing temperatures are increased. As the sintering temperatures are raised even further, the surface of the platinum begins to facet with lower energy surfaces. These microstructural changes can be seen in Figures 1 and 2, but the goal of the work is to characterize the microstructure by its fractal dimension and then relate the fractal dimension to the electrical response. The sensors were fabricated from zirconia powder stabilized in the cubic phase with 8 mol% percent yttria. Each substrate was sintered for 14 hours at 1200°C. The resulting zirconia pellets, 13mm in diameter and 2mm in thickness, were roughly 97 to 98 percent of theoretical density. The Engelhard #6082 platinum paste was applied to the zirconia disks after they were mechanically polished ( diamond). The electrodes were then sintered at temperatures ranging from 600°C to 1000°C. Each sensor was tested to determine the impedance response from 1Hz to 5,000Hz. These frequencies correspond to the electrode at the test temperature of 600°C.

Amorphous silica coating on α-alumina particles

1995 ◽  
Vol 53 ◽  
pp. 210-211
Author(s):  
J. W. Mellowes ◽  
C. M. Chun ◽  
I. A. Aksay
Keyword(s):  
Amorphous Silica ◽  
Heterogeneous Nucleation ◽  
Homogeneous Nucleation ◽  
Silica Coating ◽  
Full Density ◽  
Optimal Conditions ◽  
Fine Grained ◽  
Alumina Particles ◽  
Complete Mullitization ◽  
Powder Compacts

Mullite (3Al2O32SiO2) can be fabricated by transient viscous sintering using composite particles which consist of inner cores of a-alumina and outer coatings of amorphous silica. Powder compacts prepared with these particles are sintered to almost full density at relatively low temperatures (~1300°C) and converted to dense, fine-grained mullite at higher temperatures (>1500°C) by reaction between the alumina core and the silica coating. In order to achieve complete mullitization, optimal conditions for coating alumina particles with amorphous silica must be achieved. Formation of amorphous silica can occur in solution (homogeneous nucleation) or on the surface of alumina (heterogeneous nucleation) depending on the degree of supersaturation of the solvent in which the particles are immersed. Successful coating of silica on alumina occurs when heterogeneous nucleation is promoted and homogeneous nucleation is suppressed. Therefore, one key to successful coating is an understanding of the factors such as pH and concentration that control silica nucleation in aqueous solutions. In the current work, we use TEM to determine the optimal conditions of this processing.

Interfacial structures of dissimilar materials joined by capacitor-discharge welding

1994 ◽  
Vol 52 ◽  
pp. 534-535
Author(s):  
C. P. Doğan ◽  
R. D. Wilson ◽  
J. A. Hawk
Keyword(s):  
Rapid Solidification ◽  
Fusion Zone ◽  
Dissimilar Materials ◽  
Solidification Process ◽  
Weld Interface ◽  
Capacitor Discharge ◽  
Fine Grained ◽  
Iron Aluminum ◽  
Conductive Ceramics ◽  
Capacitor Discharge Welding

Capacitor Discharge Welding is a rapid solidification technique for joining conductive materials that results in a narrow fusion zone and almost no heat affected zone. As a result, the microstructures and properties of the bulk materials are essentially continuous across the weld interface. During the joining process, one of the materials to be joined acts as the anode and the other acts as the cathode. The anode and cathode are brought together with a concomitant discharge of a capacitor bank, creating an arc which melts the materials at the joining surfaces and welds them together (Fig. 1). As the electrodes impact, the arc is extinguished, and the molten interface cools at rates that can exceed 106 K/s. This process results in reduced porosity in the fusion zone, a fine-grained weldment, and a reduced tendency for hot cracking.At the U.S. Bureau of Mines, we are currently examining the possibilities of using capacitor discharge welding to join dissimilar metals, metals to intermetallics, and metals to conductive ceramics. In this particular study, we will examine the microstructural characteristics of iron-aluminum welds in detail, focussing our attention primarily on interfaces produced during the rapid solidification process.

Sign in / Sign up

Export Citation Format

Share Document