Search Results - "Lin, Guosheng"
-
1
Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fields
Published in IEEE transactions on pattern analysis and machine intelligence (01-10-2016)“…In this article, we tackle the problem of depth estimation from single monocular images. Compared with depth estimation using multiple images such as stereo…”
Get full text
Journal Article -
2
RefineNet: Multi-path Refinement Networks for High-Resolution Semantic Segmentation
Published in 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (01-07-2017)“…Recently, very deep convolutional neural networks (CNNs) have shown outstanding performance in object recognition and have also been the first choice for dense…”
Get full text
Conference Proceeding -
3
A Dilated Inception Network for Visual Saliency Prediction
Published in IEEE transactions on multimedia (01-08-2020)“…Recently, with the advent of deep convolutional neural networks (DCNN), the improvements in visual saliency prediction research are impressive. One possible…”
Get full text
Journal Article -
4
Deep convolutional neural fields for depth estimation from a single image
Published in 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (01-06-2015)“…We consider the problem of depth estimation from a single monocular image in this work. It is a challenging task as no reliable depth cues are available, e.g.,…”
Get full text
Conference Proceeding -
5
Exploring Context with Deep Structured Models for Semantic Segmentation
Published in IEEE transactions on pattern analysis and machine intelligence (01-06-2018)“…We propose an approach for exploiting contextual information in semantic image segmentation, and particularly investigate the use of patch-patch context and…”
Get full text
Journal Article -
6
Supervised Hashing Using Graph Cuts and Boosted Decision Trees
Published in IEEE transactions on pattern analysis and machine intelligence (01-11-2015)“…To build large-scale query-by-example image retrieval systems, embedding image features into a binary Hamming space provides great benefits. Supervised hashing…”
Get full text
Journal Article -
7
A General Two-Step Approach to Learning-Based Hashing
Published in 2013 IEEE International Conference on Computer Vision (01-12-2013)“…Most existing approaches to hashing apply a single form of hash function, and an optimization process which is typically deeply coupled to this specific form…”
Get full text
Conference Proceeding Journal Article -
8
Efficient Piecewise Training of Deep Structured Models for Semantic Segmentation
Published in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (01-06-2016)“…Recent advances in semantic image segmentation have mostly been achieved by training deep convolutional neural networks (CNNs). We show how to improve semantic…”
Get full text
Conference Proceeding -
9
Fast Supervised Hashing with Decision Trees for High-Dimensional Data
Published in 2014 IEEE Conference on Computer Vision and Pattern Recognition (01-06-2014)“…Supervised hashing aims to map the original features to compact binary codes that are able to preserve label based similarity in the Hamming space. Non-linear…”
Get full text
Conference Proceeding -
10
Fast Training of Triplet-Based Deep Binary Embedding Networks
Published in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (01-06-2016)“…In this paper, we aim to learn a mapping (or embedding) from images to a compact binary space in which Hamming distances correspond to a ranking measure for…”
Get full text
Conference Proceeding -
11
Bootstrapping the Performance of Webly Supervised Semantic Segmentation
Published in 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (01-06-2018)“…Fully supervised methods for semantic segmentation require pixel-level class masks to train, the creation of which is expensive in terms of manual labour and…”
Get full text
Conference Proceeding -
12
Multi-Path Region Mining for Weakly Supervised 3D Semantic Segmentation on Point Clouds
Published in 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (01-01-2020)“…Point clouds provide intrinsic geometric information and surface context for scene understanding. Existing methods for point cloud segmentation require a large…”
Get full text
Conference Proceeding -
13
Structured Learning of Tree Potentials in CRF for Image Segmentation
Published in IEEE transaction on neural networks and learning systems (01-06-2018)“…We propose a new approach to image segmentation, which exploits the advantages of both conditional random fields (CRFs) and decision trees. In the literature,…”
Get full text
Journal Article -
14
Discriminative Training of Deep Fully Connected Continuous CRFs With Task-Specific Loss
Published in IEEE transactions on image processing (01-05-2017)“…Recent works on deep conditional random fields (CRFs) have set new records on many vision tasks involving structured predictions. Here, we propose a fully…”
Get full text
Journal Article -
15
Protective effect of coptisine free base on indomethacin-induced gastric ulcers in rats: Characterization of potential molecular mechanisms
Published in Life sciences (1973) (15-01-2018)“…The aim of this study was to comparatively investigate the potential gastroprotective effect and underlying mechanisms of coptisine free base (CFB,…”
Get full text
Journal Article -
16
Obligate ligation-gated recombination (ObLiGaRe): custom-designed nuclease-mediated targeted integration through nonhomologous end joining
Published in Genome research (01-03-2013)“…Custom-designed nucleases (CDNs) greatly facilitate genetic engineering by generating a targeted DNA double-strand break (DSB) in the genome. Once a DSB is…”
Get full text
Journal Article -
17
StructBoost: Boosting Methods for Predicting Structured Output Variables
Published in IEEE transactions on pattern analysis and machine intelligence (01-10-2014)“…Boosting is a method for learning a single accurate predictor by linearly combining a set of less accurate weak learners. Recently, structured learning has…”
Get full text
Journal Article -
18
Character and laxative activity of polysaccharides isolated from Dendrobium officinale
Published in Journal of functional foods (01-07-2017)“…•D. officinale polysaccharides (DOP) were mainly composed of d-mannose and d-glucose.•DOP were the laxative ingredients of D. officinale.•DOP promoted…”
Get full text
Journal Article -
19
Therapeutic potential of Pien Tze Huang in colitis-associated colorectal cancer: mechanistic insights from a mouse model
Published in Cancer cell international (17-07-2024)“…Pien Tze Huang (PZH), a traditional Chinese medicine formulation, is recognized for its therapeutic effect on colitis and colorectal cancer. However, its…”
Get full text
Journal Article -
20
Multi-octave two-color soliton frequency comb in integrated chalcogenide microresonators
Published in Frontiers of Optoelectronics (Online) (11-11-2024)“…Mid-infrared (MIR) Kerr microcombs are of significant interest for portable dual-comb spectroscopy and precision molecular sensing due to strong molecular…”
Get full text
Journal Article