17 Result(s)
-
Article
Triplet penalty matters: penalty metric space triplet loss for person re-identification
This paper provided a unified perspective to improve triplet loss function and proposed a substantial triplet loss named Penalty Metric Space Triplet Loss (Tri-PMS) based on this perspective for person re-iden...
-
Article
Combination of validity aggregation and multi-scale feature for person re-identification
Person re-identification (re-ID) gradually has attracted attention of the industry and academe. It has a great application future in computer vision with the development of deep learning. The main challenges i...
-
Chapter and Conference Paper
Automated Malaria Cells Detection from Blood Smears Under Severe Class Imbalance via Importance-Aware Balanced Group Softmax
Malaria is one of the main threats to global health. Manual examination of thick and thin blood smears is the current gold standard for diagnosing malaria. However, it is of extremely low throughput and suscep...
-
Chapter and Conference Paper
Memory-Efficient Automatic Kidney and Tumor Segmentation Based on Non-local Context Guided 3D U-Net
Automatic kidney and tumor segmentation from CT volumes is essential for clinical diagnosis and surgery planning. However, it is still a very challenging problem as kidney and tumor usually exhibit various sca...
-
Chapter and Conference Paper
RVSeg-Net: An Efficient Feature Pyramid Cascade Network for Retinal Vessel Segmentation
Accurate retinal vessel segmentation plays a critical role in the diagnosis of many relevant diseases. However, it remains a challenging task due to (1) the great scale variation of retinal vessels, (2) the ex...
-
Chapter and Conference Paper
PolypSeg: An Efficient Context-Aware Network for Polyp Segmentation from Colonoscopy Videos
Polyp segmentation from colonoscopy videos is of great importance for improving the quantitative analysis of colon cancer. However, it remains a challenging task due to (1) the large size and shape variation o...
-
Article
Online transfer learning with multiple decision trees
Online learning techniques have been widely used in many fields where instances come one by one. However, in early stage of a data stream, online learning models cannot exhibit good classification accuracy for...
-
Article
Open AccessK-Connected Cores Computation in Large Dual Networks
Computing \(k\text {-}core\) k ...
-
Chapter and Conference Paper
An Artificial Neural Network for Solving Quadratic Zero-One Programming Problems
This paper proposes a neurodynamic approach for solving the quadratic zero-one programming problem with linear constraints. Based on the basic idea of the Scholtes’ relaxation scheme, the original quadratic ze...
-
Article
Sensitivity and stability analysis of the additive model in uncertain data envelopment analysis
DEA is a non-parametric productive efficiency measurement method for operations with multiple inputs and multiple outputs. An issue which has received widespread attention in rapidly growing field of DEA is th...
-
Chapter and Conference Paper
Welding Robot with Laser Tracking System Used in High-Mobility Off-road Vehicle Rack Girder
By using a laser tracking system on an arc welding robot workstation, irregular welding, misalignment, and undercut etc. problems could be solved due to contour size deviation of the truck rack girder on the h...
-
Article
The \(\alpha \) -cost minimization model for capacitated facility location-allocation problem with uncertain demands
Facility location-allocation problem aims at determining the locations of some facilities to serve a set of spatially distributed customers and the allocation of each customer to the facilities such that the t...
-
Chapter and Conference Paper
Multiscale Geometric Active Contour Model and Boundary Extraction in Kidney MR Images
Active contour methods (ACM) are model-based approaches for image segmentation and were developed in the late 1980s. ACM can be divided into two classes: parametric active contour model and geometric active co...
-
Article
Related-Key Impossible Differential Attack on Reduced-Round LBlock
LBlock is a 32-round lightweight block cipher with 64-bit block size and 80-bit key. This paper identifies 16-round related-key impossible differentials of LBlock, which are better than the 15-round related-ke...
-
Article
Sensitivity and stability analysis in fuzzy data envelopment analysis
As a useful management and decision tool, data envelopment analysis (DEA) has become a pop area of research. One of the topics of interests in DEA is sensitivity and stability analysis of decision making units...
-
Article
Technology for simulating crowd evacuation behaviors
This paper presents a model for simulating crowd evacuation and investigates three widely recognized problems. For the space continuity problem, this paper presents two computation algorithms: one uses grid sp...
-
Chapter and Conference Paper
A Probabilistic Feature Based Maximum Entropy Model for Chinese Named Entity Recognition
This paper proposes a probabilistic feature based Maximum Entropy (ME) model for Chinese named entity recognition. Where, probabilistic feature functions are used instead of binary feature functions, it is one...
