143 Result(s)
-
Chapter and Conference Paper
Explaining Deepfake Detection by Analysing Image Matching
This paper aims to interpret how deepfake detection models learn artifact features of images when just supervised by binary labels. To this end, three hypotheses from the perspective of image matching are prop...
-
Chapter and Conference Paper
CLOSE: Curriculum Learning on the Sharing Extent Towards Better One-Shot NAS
One-shot Neural Architecture Search (NAS) has been widely used to discover architectures due to its efficiency. However, previous studies reveal that one-shot performance estimations of architectures might not...
-
Chapter and Conference Paper
AdaAfford: Learning to Adapt Manipulation Affordance for 3D Articulated Objects via Few-Shot Interactions
Perceiving and interacting with 3D articulated objects, such as cabinets, doors, and faucets, pose particular challenges for future home-assistant robots performing daily tasks in human environments.
-
Chapter and Conference Paper
FH-Net: A Fast Hierarchical Network for Scene Flow Estimation on Real-World Point Clouds
Estimating scene flow from real-world point clouds is a fundamental task for practical 3D vision. Previous methods often rely on deep models to first extract expensive per-point features at full resolution, an...
-
Chapter and Conference Paper
Lightweight Attentional Feature Fusion: A New Baseline for Text-to-Video Retrieval
In this paper we revisit feature fusion, an old-fashioned topic, in the new context of text-to-video retrieval. Different from previous research that considers feature fusion only at one end, let it be video or t...
-
Chapter and Conference Paper
Reciprocal Learning for Semi-supervised Segmentation
Semi-supervised learning has been recently employed to solve problems from medical image segmentation due to challenges in acquiring sufficient manual annotations, which is an important prerequisite for buildi...
-
Chapter and Conference Paper
Cascaded Coarse-to-Fine Neural Network for Brain Tumor Segmentation
A cascaded framework of coarse-to-fine networks is proposed to segment brain tumor from multi-modality MR images into three subregions: enhancing tumor, whole tumor and tumor core. The framework is designed to...
-
Chapter and Conference Paper
Triplet-Branch Network with Prior-Knowledge Embedding for Fatigue Fracture Grading
In recent years, there has been increasing awareness of the occurrence of fatigue fractures. Athletes and soldiers, who engaged in unaccustomed, repetitive or vigorous activities, are potential victims of such...
-
Chapter and Conference Paper
Statistical Dependency Guided Contrastive Learning for Multiple Labeling in Prenatal Ultrasound
Standard plane recognition plays an important role in prenatal ultrasound (US) screening. Automatically recognizing the standard plane along with the corresponding anatomical structures in US image can not onl...
-
Chapter and Conference Paper
Federated Whole Prostate Segmentation in MRI with Personalized Neural Architectures
Building robust deep learning-based models requires diverse training data, ideally from several sources. However, these datasets cannot be combined easily because of patient privacy concerns or regulatory hurd...
-
Chapter and Conference Paper
Hierarchical Attention Guided Framework for Multi-resolution Collaborative Whole Slide Image Segmentation
Segmentation of whole slide images (WSIs) is an important step for computer-aided cancer diagnosis. However, due to the gigapixel dimension, WSIs are usually cropped into patches for analysis. Processing high-...
-
Chapter and Conference Paper
Frequency Attention Network: Blind Noise Removal for Real Images
With outstanding feature extraction capabilities, deep convolutional neural networks (CNNs) have achieved extraordinary improvements in image denoising tasks. However, because of the difference of statistical ...
-
Chapter and Conference Paper
Improving Generalizability in Limited-Angle CT Reconstruction with Sinogram Extrapolation
Computed tomography (CT) reconstruction from X-ray projections acquired within a limited angle range is challenging, especially when the angle range is extremely small. Both analytical and iterative models nee...
-
Chapter and Conference Paper
Unsupervised Representation Learning Meets Pseudo-Label Supervised Self-Distillation: A New Approach to Rare Disease Classification
Rare diseases are characterized by low prevalence and are often chronically debilitating or life-threatening. Imaging-based classification of rare diseases is challenging due to the severe shortage in training...
-
Chapter and Conference Paper
VisDrone-SOT2020: The Vision Meets Drone Single Object Tracking Challenge Results
The Vision Meets Drone (VisDrone2020) Single Object Tracking is the third annual UAV tracking evaluation activity organized by the VisDrone team, in conjunction with European Conference on Computer Vision (ECC...
-
Chapter and Conference Paper
The Eighth Visual Object Tracking VOT2020 Challenge Results
The Visual Object Tracking challenge VOT2020 is the eighth annual tracker benchmarking activity organized by the VOT initiative. Results of 58 trackers are presented; many are state-of-the-art trackers publish...
-
Chapter and Conference Paper
VisDrone-DET2020: The Vision Meets Drone Object Detection in Image Challenge Results
The Vision Meets Drone Object Detection in Image Challenge (VisDrone-DET 2020) is the third annual object detector benchmarking activity. Compared with the previous VisDrone-DET 2018 and VisDrone-DET 2019 chal...
-
Chapter and Conference Paper
Cascaded Global Context Convolutional Neural Network for Brain Tumor Segmentation
A cascade of global context convolutional neural networks is proposed to segment multi-modality MR images with brain tumor into three subregions: enhancing tumor, whole tumor and tumor core. Each network is a ...
-
Chapter and Conference Paper
Computer-Aided Tumor Diagnosis in Automated Breast Ultrasound Using 3D Detection Network
Automated breast ultrasound (ABUS) is a new and promising imaging modality for breast cancer detection and diagnosis, which could provide intuitive 3D information and coronal plane information with great diagn...
-
Chapter and Conference Paper
FTR-NAS: Fault-Tolerant Recurrent Neural Architecture Search
With the popularity of the applications equipped with neural networks on edge devices, robustness has become the focus of researchers. However, when deploying the applications onto the hardware, environmental ...