-
Article
Open AccessDeep learning-driven automated quality assessment of ultra-widefield optical coherence tomography angiography images for diabetic retinopathy
Image quality assessment (IQA) of fundus images constitutes a foundational step in automated disease analysis. This process is pivotal in supporting the automation of screening, diagnosis, follow-up, and relat...
-
Article
Open AccessNeural 3D reconstruction from sparse views using geometric priors
Sparse view 3D reconstruction has attracted increasing attention with the development of neural implicit 3D representation. Existing methods usually only make use of 2D views, requiring a dense set of input vi...
-
Article
Open AccessAn anisotropic Chebyshev descriptor and its optimization for deformable shape correspondence
Shape descriptors have recently gained popularity in shape matching, statistical shape modeling, etc. Their discriminative ability and efficiency play a decisive role in these tasks. In this paper, we first pr...
-
Article
Open AccessGlobal video object segmentation with spatial constraint module
We present a lightweight and efficient semi-supervised video object segmentation network based on the space-time memory framework. To some extent, our method solves the two difficulties encountered in traditio...
-
Chapter and Conference Paper
Deep Residual Attention Network for Spectral Image Super-Resolution
Spectral imaging sensors often suffer from low spatial resolution, as there exists an essential tradeoff between the spectral and spatial resolutions that can be simultaneously achieved, especially when the te...
-
Chapter and Conference Paper
Non-local NetVLAD Encoding for Video Classification
This paper describes our solution for the 2 \(^\text {nd}\) YouTube-8M video understanding challenge organiz...
-
Chapter and Conference Paper
Can 3D Pose Be Learned from 2D Projections Alone?
3D pose estimation from a single image is a challenging task in computer vision. We present a weakly supervised approach to estimate 3D pose points, given only 2D pose landmarks. Our method does not require co...
-
Chapter and Conference Paper
PIRM2018 Challenge on Spectral Image Super-Resolution: Methods and Results
In this paper, we describe the Perceptual Image Restoration and Manipulation (PIRM) workshop challenge on spectral image super-resolution, motivate its structure and conclude on results obtained by the partici...
-
Chapter and Conference Paper
“Factual” or “Emotional”: Stylized Image Captioning with Adaptive Learning and Attention
Generating stylized captions for an image is an emerging topic in image captioning. Given an image as input, it requires the system to generate a caption that has a specific style (e.g., humorous, romantic, po...
-
Chapter and Conference Paper
Using LIP to Gloss Over Faces in Single-Stage Face Detection Networks
This work shows that it is possible to fool/attack recent state-of-the-art face detectors which are based on the single-stage networks. Successfully attacking face detectors could be a serious malware vulnerab...
-
Article
Open AccessView suggestion for interactive segmentation of indoor scenes
Point cloud segmentation is a fundamental problem. Due to the complexity of real-world scenes and the limitations of 3D scanners, interactive segmentation is currently the only way to cope with all kinds of po...
-
Chapter and Conference Paper
Preprocessing and Segmentation Algorithm for Multiple Overlapped Fiber Image
In the fiber image recognition system, pinpoint segmentation is critical for fiber feature extraction and further identification. In the case of fiber image taken by the optical microscope, the overlapped type...
-
Chapter and Conference Paper
An Altitude Based Landslide and Debris Flow Detection Method for a Single Mountain Remote Sensing Image
The altitude information of single remote sensing image may aid in detecting the natural disaster, such as landslide or debris flow. Accordingly, in this paper, an approach based on altitude is proposed to det...
-
Article
Open Access3D indoor scene modeling from RGB-D data: a survey
3D scene modeling has long been a fundamental problem in computer graphics and computer vision. With the popularity of consumer-level RGB-D cameras, there is a growing interest in digitizing real-world indoor ...
-
Chapter and Conference Paper
Motion-Corrected, Super-Resolution Reconstruction for High-Resolution 3D Cardiac Cine MRI
Cardiac cine MRI with 3D isotropic resolution is challenging as it requires efficient data acquisition and motion management. It is proposed to use a 2D balanced SSFP (steady-state free precession) sequence ra...
-
Chapter and Conference Paper
A Stroke Width Based Parameter-Free Document Binarization Method
This paper presents a parameter-free document binarization method based on text characteristics. For a given stroke width, the text and background regions in binarized object regions are estimated with morphol...
-
Chapter and Conference Paper
Identification of Cerebral Small Vessel Disease Using Multiple Instance Learning
Cerebral small vessel disease (SVD) is a common cause of ageing-associated physical and cognitive impairment. Identifying SVD is important for both clinical and research purposes but is usually dependent on ra...
-
Chapter and Conference Paper
Multi-modality Gesture Detection and Recognition with Un-supervision, Randomization and Discrimination
We describe in this paper our gesture detection and recognition system for the 2014 ChaLearn Looking at People (Track 3: Gesture Recognition) organized by ChaLearn in conjunction with the ECCV 2014 conference....
-
Chapter and Conference Paper
Spatiotemporal Background Subtraction Using Minimum Spanning Tree and Optical Flow
Background modeling and subtraction is a fundamental research topic in computer vision. Pixel-level background model uses a Gaussian mixture model (GMM) or kernel density estimation to represent the distributi...
-
Chapter and Conference Paper
Towards Unified Object Detection and Semantic Segmentation
Object detection and semantic segmentation are two strongly correlated tasks, yet typically solved separately or sequentially with substantially different techniques. Motivated by the complementary effect obse...