-
Chapter and Conference Paper
TPNet: Enhancing Weakly Supervised Polyp Frame Detection with Temporal Encoder and Prototype-Based Memory Bank
Polyp detection plays a crucial role in the early prevention of colorectal cancer. The availability of large-scale polyp video datasets and video-level annotations has spurred research efforts to formulate pol...
-
Chapter and Conference Paper
A Multi-stage Network with Self-attention for Tooth Instance Segmentation
Automatic and accurate instance segmentation of teeth from 3D Cone-Beam Computer Tomography (CBCT) images is crucial for dental diagnose. Although Convolutional Neural Networks (CNNs) are widely used for tooth...
-
Article
Toward embedding-based multi-label feature selection with label and feature collaboration
Similar to single-label learning, multi-label learning employs feature selection technique to alleviate the curse of dimensionality. Many multi-label methods, which utilize label correlation or instance correl...
-
Chapter and Conference Paper
A Classifier-Based Two-Stage Training Model for Few-Shot Segmentation
Over the past few years, deep learning-based semantic segmentation methods reached state-of-the-art performance. The segmentation task is time-consuming and requires a lot of pixel-level annotated data, which ...
-
Chapter and Conference Paper
A Improved Prior Box Generation Method for Small Object Detection
As a task in object detection, small object detection mainly focuses on detecting objects of small size, which is more complex than general object detection. It is pivotal in various applications, e.g., small ...
-
Chapter and Conference Paper
Boundary Difference over Union Loss for Medical Image Segmentation
Medical image segmentation is crucial for clinical diagnosis. However, current losses for medical image segmentation mainly focus on overall segmentation results, with fewer losses proposed to guide boundary s...
-
Chapter and Conference Paper
Generalized Person Re-identification by Locating and Eliminating Domain-Sensitive Features
In this paper, we study the problem of domain generalization for person re-identification (re-ID), which adopts training data from multiple domains to learn a re-ID model that can be directly deployed to unsee...
-
Article
Improving embedding learning by virtual attribute decoupling for text-based person search
This paper considers the problem of text-based person search, which aims to find the target person based on a query textual description. Previous methods commonly focus on learning shared image-text embeddings...
-
Chapter and Conference Paper
Attention and Multi-granied Feature Learning for Baggage Re-identification
The current baggage re-identification methods only consider the global coarse-grained features while ignoring the fine-grained features. To deal with this issue, we proposed a simple and efficient multi-granul...
-
Chapter and Conference Paper
An Improved SSD-Based Gastric Cancer Detection Method
Gastric cancer is one of the malignant cancers with a very high fatal rate, and early detection plays an essential role in the treatment and improves the five-year 5-year survival rate. In this study, we an im...
-
Chapter and Conference Paper
A Semi-supervised Video Object Segmentation Method Based on Adaptive Memory Module
Video object segmentation has becoming a hot research topic in the computer vision society, with a wide range of applications, such as autonomous driving, video editing, and video surveillance. However, due to...
-
Article
SAFD: single shot anchor free face detector
The anchor-free based face detection methods can cover a large range of scales and perform better in the speed. However, their performance still bears a large gap compared with anchor-based methods, especially...
-
Chapter and Conference Paper
Learning Consistency- and Discrepancy-Context for 2D Organ Segmentation
Recently, CNN-based methods lead tremendous progress in segmenting abdominal organs (e.g., kidney, liver, and pancreas) and anomaly tumors in CT scans. Although 3D CNN-based methods can significantly improve accu...
-
Chapter and Conference Paper
MDA-Network: Mask and Dual Attention Network for Handwritten Mathematical Expression Recognition
Building a system for automatic handwritten mathematical expressions recognition (HMER) has received considerable attention for its extensive applications. However, HMER remains challenging due to its own many...
-
Chapter and Conference Paper
A Fast Feature Selection Method Based on Mutual Information in Multi-label Learning
Recently, multi-label learning is concerned and studied in lots of fields by many researchers. However, multi-label datasets often have noisy, irrelevant and redundant features with high dimensionality. Accomp...
-
Chapter and Conference Paper
A Simple and Convex Formulation for Multi-label Feature Selection
In recent years, multi-label study has received extensive attention and research in many fields. The feature dimensions of a multi-label data set are high but contain a large amount of noise as well as irrelev...
-
Chapter and Conference Paper
Generalizing a Person Retrieval Model Hetero- and Homogeneously
Person re-identification (re-ID) poses unique challenges for unsupervised domain adaptation (UDA) in that classes in the source and target sets (domains) are entirely different and that image variations are la...
-
Article
Detecting ground control points via convolutional neural network for stereo matching
In this paper, we present a novel approach to detect ground control points (GCPs) for stereo matching problem. First of all, we train a convolutional neural network (CNN) on a large stereo set, and compute the...
-
Article
Stratified pooling based deep convolutional neural networks for human action recognition
Video based human action recognition is an active and challenging topic in computer vision. Over the last few years, deep convolutional neural networks (CNN) has become the most popular method and achieved the...
-
Chapter and Conference Paper
SentiNet: Mining Visual Sentiment from Scratch
An image is worth a thousand of words for sentiment expression, but the semantic gap between low-level pixels and high-level sentiment make visual sentiment analysis difficult. Our work focuses on two aspects ...
