Search results for: Xiaohui Shen

Items from 1 to 20 out of 71 results

article

Targeted single‐cell RNA sequencing analysis reveals metabolic reprogramming and the ferroptosis‐resistant state in hematologic malignancies

Xiaohui Shen, Peiyuan Dong, Jingjing Kong, Nannan Sun, more

Cell Biochemistry and Function > 41 > 8 > 1343 - 1356

Hematologic malignancies are the most common hematopoietic diseases and a major public health concern. However, the mechanisms underlying myeloid tumors remain unknown owing to the intricate interplay between mutations and diverse clonal evolution patterns, as evidenced by the analysis of bulk cell‐derived omics data. Several single‐cell omics techniques have been used to characterize the hierarchies...

article

Correlating the Solvating Power of Solvents with the Strength of Ion‐Dipole Interaction in Electrolytes of Lithium‐ion Batteries

Kean Chen, Xiaohui Shen, Laibing Luo, Hui Chen, more

Angewandte Chemie International Edition > 62 > 47 > n/a - n/a

The solvation structure of Li⁺ plays a significant role in determining the physicochemical properties of electrolytes. However, to date, there is still no clear definition of the solvating power of different electrolyte solvents, and even the solvents that preferentially participate in the solvation structure remain controversial. In this study, we comprehensively discuss the solvating power and solvation...

article

Correlating the Solvating Power of Solvents with the Strength of Ion‐Dipole Interaction in Electrolytes of Lithium‐ion Batteries

Kean Chen, Xiaohui Shen, Laibing Luo, Hui Chen, more

Angewandte Chemie > 135 > 47 > n/a - n/a

article

Iron accumulation and axonal damage of cerebellum in idiopathic cervical dystonia

Hongxia Li, Ming Zhang, Yunhao Wu, Yufei Li, more

European Journal of Neurology > 30 > 6 > 1619 - 1630

Background and purpose Postmortem brain study indicated that cerebellar Purkinje cell (PC) loss might be a pathological finding in patients with inherited and idiopathic cervical dystonia (ICD). The analysis of conventional magnetic resonance imaging brain scans failed to yield support for this finding. Previous studies have identified that iron overload can be the consequence of neuron death. The...

article

Achieving Desirable Initial Coulombic Efficiencies and Full Capacity Utilization of Li‐Ion Batteries by Chemical Prelithiation of Graphite Anode

Yifei Shen, Xiaohui Shen, Mei Yang, Jiangfeng Qian, more

Advanced Functional Materials > 31 > 24 > n/a - n/a

Chemical prelithiation is an effective approach to elevate the initial Coulombic efficiency (ICE) and energy utilization of Li‐ion battery electrodes. However, this approach fails to operate for the most commonly used graphite (Gr) anode, because all the prelithiation reagents reported so far have a much higher redox potential than Gr (≈0.2 V). Based on ionic solvation and coordination chemistry,...

article

Top-Down Neural Attention by Excitation Backprop

Jianming Zhang, Sarah Adel Bargal, Zhe Lin, Jonathan Brandt, more

International Journal of Computer Vision > 2018 > 126 > 10 > 1084-1102

We aim to model the top-down attention of a convolutional neural network (CNN) classifier for generating task-specific attention maps. Inspired by a top-down human visual attention model, we propose a new backpropagation scheme, called Excitation Backprop, to pass along top-down signals downwards in the network hierarchy via a probabilistic Winner-Take-All process. Furthermore, we introduce the concept...

article

STC: A Simple to Complex Framework for Weakly-Supervised Semantic Segmentation

Yunchao Wei, Xiaodan Liang, Yunpeng Chen, Xiaohui Shen, more

IEEE Transactions on Pattern Analysis and Machine Intelligence > 2017 > 39 > 11 > 2314 - 2320

Recently, significant improvement has been made on semantic object segmentation due to the development of deep convolutional neural networks (DCNNs). Training such a DCNN usually relies on a large number of images with pixel-level segmentation masks, and annotating these images is very costly in terms of both finance and human effort. In this paper, we propose a simple to complex (STC) framework in...

article

TCT-455 Angiographic derived Endothelial Shear Stress: a new predictor of atherosclerotic disease progression

Michalis Hadjiandreou, Lorenz Raber, Ryo Torii, Xiaohui Shen, more

Journal of the American College of Cardiology > 2017 > 70 > 18(S) > B187-B188

chapter

Personalized Image Aesthetics

Jian Ren, Xiaohui Shen, Zhe Lin, Radomir Mech, more

2017 IEEE International Conference on Computer Vision (ICCV) > 638 - 647

2017 IEEE International Conference on Computer Vision (ICCV)

Automatic image aesthetics rating has received a growing interest with the recent breakthrough in deep learning. Although many studies exist for learning a generic or universal aesthetics model, investigation of aesthetics models incorporating individual user’s preference is quite limited. We address this personalized aesthetics problem by showing that individual’s aesthetic preferences exhibit strong...

chapter

Video Scene Parsing with Predictive Feature Learning

Xiaojie Jin, Xin Li, Huaxin Xiao, Xiaohui Shen, more

2017 IEEE International Conference on Computer Vision (ICCV) > 5581 - 5589

2017 IEEE International Conference on Computer Vision (ICCV)

Video scene parsing is challenging due to the following two reasons: firstly, it is non-trivial to learn meaningful video representations for producing the temporally consistent labeling map; secondly, such a learning process becomes more difficult with insufficient labeled video training data. In this work, we propose a unified framework to address the above two problems, which is to our knowledge...

chapter

Recurrent Multimodal Interaction for Referring Image Segmentation

Chenxi Liu, Zhe Lin, Xiaohui Shen, Jimei Yang, more

2017 IEEE International Conference on Computer Vision (ICCV) > 1280 - 1289

2017 IEEE International Conference on Computer Vision (ICCV)

In this paper we are interested in the problem of image segmentation given natural language descriptions, i.e. referring expressions. Existing works tackle this problem by first modeling images and sentences independently and then segment images by combining these two types of representations. We argue that learning word-to-image interaction is more native in the sense of jointly modeling two modalities...

chapter

FoveaNet: Perspective-Aware Urban Scene Parsing

Xin Li, Zequn Jie, Wei Wang, Changsong Liu, more

2017 IEEE International Conference on Computer Vision (ICCV) > 784 - 792

2017 IEEE International Conference on Computer Vision (ICCV)

Parsing urban scene images benefits many applications, especially self-driving. Most of the current solutions employ generic image parsing models that treat all scales and locations in the images equally and do not consider the geometry property of car-captured urban scene images. Thus, they suffer from heterogeneous object scales caused by perspective projection of cameras on actual scenes and inevitably...

chapter

Scene Parsing with Global Context Embedding

Wei-Chih Hung, Yi-Hsuan Tsai, Xiaohui Shen, Zhe Lin, more

2017 IEEE International Conference on Computer Vision (ICCV) > 2650 - 2658

2017 IEEE International Conference on Computer Vision (ICCV)

We present a scene parsing method that utilizes global context information based on both the parametric and nonparametric models. Compared to previous methods that only exploit the local relationship between objects, we train a context network based on scene similarities to generate feature representations for global contexts. In addition, these learned features are utilized to generate global and...

article

BSDEs with monotone generator driven by time-changed Lévy noises

Xiaohui Shen, Long Jiang

Advances in Difference Equations > 2017 > 2017 > 1 > 1-11

In this paper, we establish an existence and uniqueness theorem for solutions to backward stochastic differential equations driven by time-changed Lévy noises, in which the generator is monotonic and general growth with respect to y. Our conclusion extends the corresponding result in Di Nunno and Sjursen (Stoch. Process. Appl. 124:1679-1709, 2014).

article

Learning to Segment Human by Watching YouTube

Xiaodan Liang, Yunchao Wei, Liang Lin, Yunpeng Chen, more

IEEE Transactions on Pattern Analysis and Machine Intelligence > 2017 > 39 > 7 > 1462 - 1468

An intuition on human segmentation is that when a human is moving in a video, the video-context (e.g., appearance and motion clues) may potentially infer reasonable mask information for the whole human body. Inspired by this, based on popular deep convolutional neural networks (CNN), we explore a very-weakly supervised learning framework for human segmentation task, where only an imperfect human detector...

chapter

Deep Image Harmonization

Yi-Hsuan Tsai, Xiaohui Shen, Zhe Lin, Kalyan Sunkavalli, more

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) > 2799 - 2807

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Compositing is one of the most common operations in photo editing. To generate realistic composites, the appearances of foreground and background need to be adjusted to make them compatible. Previous approaches to harmonize composites have focused on learning statistical relationships between hand-crafted appearance features of the foreground and background, which is unreliable especially when the...

chapter

Interpretable Structure-Evolving LSTM

Xiaodan Liang, Liang Lin, Xiaohui Shen, Jiashi Feng, more

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) > 2175 - 2184

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

This paper develops a general framework for learning interpretable data representation via Long Short-Term Memory (LSTM) recurrent neural networks over hierarchal graph structures. Instead of learning LSTM models over the pre-fixed structures, we propose to further learn the intermediate interpretable multi-level graph structures in a progressive and stochastic way from data during the LSTM network...

chapter

Skeleton Key: Image Captioning by Skeleton-Attribute Decomposition

Yufei Wang, Zhe Lin, Xiaohui Shen, Scott Cohen, more

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) > 7378 - 7387

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Recently, there has been a lot of interest in automatically generating descriptions for an image. Most existing language-model based approaches for this task learn to generate an image description word by word in its original word order. However, for humans, it is more natural to locate the objects and their relationships first, and then elaborate on each object, describing notable attributes. We...

chapter

Look into Person: Self-Supervised Structure-Sensitive Learning and a New Benchmark for Human Parsing

Ke Gong, Xiaodan Liang, Dongyu Zhang, Xiaohui Shen, more

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) > 6757 - 6765

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Human parsing has recently attracted a lot of research interests due to its huge application potentials. However existing datasets have limited number of images and annotations, and lack the variety of human appearances and the coverage of challenging cases in unconstrained environment. In this paper, we introduce a new benchmark Look into Person (LIP) that makes a significant advance in terms of...

article

Salient Object Subitizing

Jianming Zhang, Shugao Ma, Mehrnoosh Sameki, Stan Sclaroff, more

International Journal of Computer Vision > 2017 > 124 > 2 > 169-186

We study the problem of salient object subitizing, i.e. predicting the existence and the number of salient objects in an image using holistic cues. This task is inspired by the ability of people to quickly and accurately identify the number of items within the subitizing range (1–4). To this end, we present a salient object subitizing image dataset of about 14 K everyday images which are annotated...

Publication date

Last year (3)
Last 3 years (4)

Close

Date range setting

Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.

From:

To:
Set your own date range

Content availability

Available (70)
None (1)

Publication type

article (37)
book (34)

Keywords

SEMANTICS (11)
TRAINING (11)
IMAGE SEGMENTATION (10)
FEATURE EXTRACTION (8)
VISUALIZATION (7)
PROTON CONDUCTIVITY (5)
ADAPTATION MODELS (4)
CONVOLUTIONAL NEURAL NETWORK (4)
ESTIMATION (4)
IMAGE COLOR ANALYSIS (4)
BENCHMARK TESTING (3)
CONTEXT MODELING (3)
HUMAN PARSING (3)
LABELING (3)
MEASUREMENT (3)
NEURAL NETWORKS (3)
NOISE (3)
OBJECT DETECTION (3)
OPTICAL IMAGING (3)
ROBUSTNESS (3)
SULFONATED POLY(ETHER ETHER KETONE) (3)
CORRELATION (2)
DFT CALCULATIONS (2)
DIRECT METHANOL FUEL CELL (2)
ELECTROLYTES (2)
ELECTRONIC MAIL (2)
FRACTIONAL DIFFERENTIAL EQUATION (2)
HYBRID MEMBRANE (2)
HYBRID MEMBRANES (2)
IMAGE CODING (2)
IMAGE MOTION ANALYSIS (2)
IMAGE SEQUENCES (2)
LITHIUM-ION BATTERIES (2)
MATHEMATICAL MODEL (2)
MAXIMUM STABLE EXTREMAL REGIONS (2)
METHANOL PERMEABILITY (2)
MOTION SEGMENTATION (2)
NOISE MEASUREMENT (2)
OPTICAL FLOW (2)
OPTICAL SENSORS (2)
OPTICAL VARIABLES MEASUREMENT (2)
OPTIMIZATION (2)
P-LAPLACIAN OPERATOR (2)
PREDICTIVE MODELS (2)
SALIENCY DETECTION (2)
SEARCH PROBLEMS (2)
SOLVATING POWER (2)
SOLVATION STRUCTURE (2)
SPARSE MATRICES (2)
TARGET TRACKING (2)
TITANIA SUBMICROSPHERES (2)
VISUAL TRACKING (2)
VOCABULARY (2)
WEAKLY-SUPERVISED LEARNING (2)
ACCESS PATTERN (1)
ACTIVE SHAPE NETWORK (1)
ACTIVE TEMPLATE NETWORK (1)
ACTIVE TEMPLATE REGRESSION (1)
ACUTE MYELOID LEUKEMIA (1)
ADAPTIVE OPTICS (1)
AMINO ACIDS (1)
APPEARANCE MODEL (1)
APPEARANCE MODELING (1)
ARTICULATED HAND MOTION TRACKING (1)
ATMOSPHERIC MEASUREMENTS (1)
AUTOMATIC (1)
AUTOMATIC OBJECT DETECTION (1)
AUTOMOBILES (1)
BACKWARD STOCHASTIC DIFFERENTIAL EQUATION (1)
BAG-OF-WORDS (1)
BINARY TITANIA–SILICA (1)
BIRDS (1)
BOUNDARY VALUE PROBLEM (1)
BOUNDARY VALUE PROBLEMS (1)
CALLUS (1)
CAMERAS (1)
CEREBELLUM (1)
CERVICAL DYSTONIA (1)
CHEMICAL PRELITHIATION (1)
CNN (1)
COINCIDENCE DEGREE THEORY (1)
COLOR (1)
COMPLEX FLOW FIELD (1)
COMPOSITE MEMBRANE (1)
COMPOUND ADDITIVE (1)
COMPRESSIVE SENSING (1)
CONTEXT (1)
CONVOLUTION (1)
COULOMBIC EFFICIENCY (1)
CUCKOO SEARCH (1)
DATA INTENSIVE APPLICATIONS (1)
DATA INTENSIVE COMPUTING (1)
DATA MODELS (1)
DATABASE GESTURES (1)
DATABASES (1)
DECODING (1)
DECONTAMINATION OF AMMONIA (1)
DEEP LEARNING (1)
DENSE FLOW FIELD (1)
DENSE OPTICAL FLOW (1)
more

Data set

ieee (45)
Elsevier (12)
Springer (8)
Wiley (6)

INFONA - science communication portal

Search results for: Xiaohui Shen

Targeted single‐cell RNA sequencing analysis reveals metabolic reprogramming and the ferroptosis‐resistant state in hematologic malignancies

Correlating the Solvating Power of Solvents with the Strength of Ion‐Dipole Interaction in Electrolytes of Lithium‐ion Batteries

Correlating the Solvating Power of Solvents with the Strength of Ion‐Dipole Interaction in Electrolytes of Lithium‐ion Batteries

Iron accumulation and axonal damage of cerebellum in idiopathic cervical dystonia

Achieving Desirable Initial Coulombic Efficiencies and Full Capacity Utilization of Li‐Ion Batteries by Chemical Prelithiation of Graphite Anode

Top-Down Neural Attention by Excitation Backprop

STC: A Simple to Complex Framework for Weakly-Supervised Semantic Segmentation

TCT-455 Angiographic derived Endothelial Shear Stress: a new predictor of atherosclerotic disease progression

Personalized Image Aesthetics

Video Scene Parsing with Predictive Feature Learning

Recurrent Multimodal Interaction for Referring Image Segmentation

FoveaNet: Perspective-Aware Urban Scene Parsing

Scene Parsing with Global Context Embedding

BSDEs with monotone generator driven by time-changed Lévy noises

Learning to Segment Human by Watching YouTube

Deep Image Harmonization

Interpretable Structure-Evolving LSTM

Skeleton Key: Image Captioning by Skeleton-Attribute Decomposition

Look into Person: Self-Supervised Structure-Sensitive Learning and a New Benchmark for Human Parsing

Salient Object Subitizing

Filter options

Publication date

Content availability

Publication type

Keywords

Data set

Journal

INFONA - science communication portal

Search results for: Xiaohui Shen

Add recipient

Sending message cancelled

Are you sure you want to cancel sending this message?

Send message

Filter options

Publication date

Date range setting

Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.

Content availability

Publication type

Keywords

Data set

Journal

Reporting an error / abuse

Sending the report failed

Accessibility options