![Loading...](https://link.springer.com/static/c4a417b97a76cc2980e3c25e2271af3129e08bbe/images/pdf-preview/spacer.gif)
178 Result(s)
-
Article
Single-Temporal Supervised Learning for Universal Remote Sensing Change Detection
Bitemporal supervised learning paradigm always dominates remote sensing change detection using numerous labeled bitemporal image pairs, especially for high spatial resolution (HSR) remote sensing imagery. Howe...
-
Article
SSE-YOLOv5: a real-time fault line selection method based on lightweight modules and attention models
To address the problems of low precision and poor anti-noise performance of the standard route selection method for the small current grounding faults, a fault line selection approach based on YOLOv5 network t...
-
Article
FSODv2: A Deep Calibrated Few-Shot Object Detection Network
Traditional methods for object detection typically necessitate a substantial amount of training data, and creating high-quality training data is time-consuming. We propose a novel Few-Shot Object Detection net...
-
Chapter and Conference Paper
Visible and NIR Image Fusion Algorithm Based on Information Complementarity
Visible and near-infrared (NIR) band sensors provide images that capture complementary spectral radiations from a scene. And the fusion of the visible and NIR image aims at utilizing their spectrum properties ...
-
Chapter and Conference Paper
Dual-Domain Network for Restoring Images from Under-Display Cameras
With the increasing popularity of full-screen devices, phone manufacturers have started placing cameras behind screens to increase the percentage of the displays. However, this innovative approach, known as un...
-
Chapter and Conference Paper
“Car or Bus?" CLearSeg: CLIP-Enhanced Discrimination Among Resembling Classes for Few-Shot Semantic Segmentation
Few-shot semantic segmentation aims at learning to segment query images of unseen classes with the guidance of limited segmented support examples. However, existing models tend to confuse the resembling classes (
-
Article
Exploring Vision-Language Models for Imbalanced Learning
Vision-language models (VLMs) that use contrastive language-image pre-training have shown promising zero-shot classification performance. However, their performance on imbalanced dataset is relatively poor, wh...
-
Article
DCP–NAS: Discrepant Child–Parent Neural Architecture Search for 1-bit CNNs
Neural architecture search (NAS) proves to be among the effective approaches for many tasks by generating an application-adaptive neural architecture, which is still challenged by high computational cost and m...
-
Chapter and Conference Paper
UAU-Net: United Attention U-Shaped Network for the Segmentation of Pigment Deposits in Fundus Images of Retinitis Pigmentosa
Retinitis Pigmentosa (RP) is a retinal disease with high rate of blindness. Retinal pigment deposits are a typical symptom of RP, whose automatic segmentation is crucial to the early diagnosis of RP. In fundus...
-
Chapter and Conference Paper
An Improved Stimulus Reconstruction Method for EEG-Based Short-Time Auditory Attention Detection
Short-time auditory attention detection (AAD) based on electroencephalography (EEG) can be utilized to help hearing-impaired people improve their perception abilities in multi-speaker environments. However, th...
-
Chapter and Conference Paper
STAGE Challenge: Structural-Functional Transition in Glaucoma Assessment Challenge in MICCAI 2023
Glaucoma leads to irreversible vision impairment due to optic nerve damage, and there is currently no cure available. The visual field (VF) test is a reference standard examination to assess visual function an...
-
Chapter and Conference Paper
An End-to-End Chinese and Japanese Bilingual Speech Recognition Systems with Shared Character Decomposition
The rising number of tourists in most areas in East Asia has increased the requirement for East Asian speech recognition systems (e.g., Chinese and Japanese). However, the large existing character vocabulary l...
-
Chapter and Conference Paper
High Fidelity Virtual Try-On via Dual Branch Bottleneck Transformer
Image-based virtual try-on aims to fit an in-shop garment into a reference person image. To achieve this, a key step is garment war**, which aligns the target garment with the corresponding parts of the refe...
-
Chapter and Conference Paper
A Three-Stage Model Fusion Method for Out-of-Distribution Generalization
Training a model from scratch in a data-deficient environment is a challenging task. In this challenge, multiple differentiated backbones are used to train, and a number of tricks are used to assist in model t...
-
Chapter and Conference Paper
PAI3D: Painting Adaptive Instance-Prior for 3D Object Detection
3D object detection is a critical task in autonomous driving. Recently multi-modal fusion-based 3D object detection methods, which combine the complementary advantages of LiDAR and camera, have shown great per...
-
Chapter and Conference Paper
Textual Concept Expansion with Commonsense Knowledge to Improve Dual-Stream Image-Text Matching
We propose a Textual Concept Expansion (TCE) approach for creating joint textual-visual embeddings. TCE uses a multi-label classifier that takes a caption as input and produces as output a set of concepts that...
-
Chapter and Conference Paper
CounTr: An End-to-End Transformer Approach for Crowd Counting and Density Estimation
Modeling context information is critical for crowd counting and desntiy estimation. Current prevailing fully-convolutional network (FCN) based crowd counting methods cannot effectively capture long-range depen...
-
Chapter and Conference Paper
Towards Self-Supervised and Weight-preserving Neural Architecture Search
Neural architecture search (NAS) techniques can discover outstanding network architecture while saving tremendous labor from human experts. Recent advancements further reduce the computational overhead to an a...
-
Chapter and Conference Paper
Research on Emotional Classification and Literary Narrative Visualization Based on Graph Convolutional Neural Network
Watching a movie for three minutes has become a popular term in contemporary life, and people also hope to spend less time understanding the emotional direction and general plot of long novels. Currently, rese...
-
Chapter and Conference Paper
A Memetic Algorithm Based on Adaptive Simulated Annealing for Community Detection
The application of community detection (community discovery) has been widely used in various fields for several years. To improve the algorithm accuracy, we proposed a memetic algorithm based on an adaptive si...