![Loading...](https://link.springer.com/static/c4a417b97a76cc2980e3c25e2271af3129e08bbe/images/pdf-preview/spacer.gif)
-
Article
MSSTN: a multi-scale spatio-temporal network for traffic flow prediction
Spatio-temporal feature extraction and fusion are crucial to traffic prediction accuracy. However, the complicated spatio-temporal correlations and dependencies between traffic nodes make the problem quite cha...
-
Chapter and Conference Paper
Transformer-Based Video Deinterlacing Method
Deinterlacing is a classical issue in video processing, aimed at generating progressive video from interlaced content. There are precious videos that are difficult to reshoot and still contain interlaced conte...
-
Chapter and Conference Paper
Comprehensive Analysis Scheme for Abnormal Behavior of Maritime Targets
Due to historical reasons, countries with coastlines have maritime disputes with many neighboring countries, and the countries concerned frequently violate national territorial rights and interests through isl...
-
Chapter and Conference Paper
A Domain Knowledge-Based Semi-supervised Pancreas Segmentation Approach
The five-year survival rate of pancreatic cancer is extremely low, and the survival time of patients can be extended by timely detection and treatment. Deep learning-based methods have been used to assist radi...
-
Chapter and Conference Paper
The Tenth Visual Object Tracking VOT2022 Challenge Results
The Visual Object Tracking challenge VOT2022 is the tenth annual tracker benchmarking activity organized by the VOT initiative. Results of 93 entries are presented; many are state-of-the-art trackers published...
-
Chapter and Conference Paper
U-TEN: An Unsupervised Two-Branch Enhancement Network for Object Detection Under Complex-Light Condition
The goal of low-light enhancement is to improve the visual quality of dark regions in an image. However, the existing low-light enhancement methods always failed in nighttime traffic surveillance. The reason c...
-
Chapter and Conference Paper
Portrait Matting Network with Essential Feature Mining and Fusion
We propose an end-to-end portrait matting algorithm that emphasizes the mining and fusion of critical features to achieve higher accuracy. Previous best-performing portrait matting algorithms still have diffic...
-
Chapter and Conference Paper
ET-HDR: An Efficient Two-Stage Network for Specular Highlight Detection and Removal
The detection and removal of specular highlights is a critical issue in computer vision and image processing tasks. In this paper, we propose an efficient end-to-end deep learning model named ET-HDR for automa...
-
Article
A Survey on Long-Tailed Visual Recognition
The heavy reliance on data is one of the major reasons that currently limit the development of deep learning. Data quality directly dominates the effect of deep learning models, and the long-tailed distributi...
-
Chapter and Conference Paper
Generative Meta-Adversarial Network for Unseen Object Navigation
Object navigation is a task to let the agent navigate to a target object. Prevailing works attempt to expand navigation ability in new environments and achieve reasonable performance on the seen object categor...
-
Chapter and Conference Paper
Stack Multiple Shallow Autoencoders into a Strong One: A New Reconstruction-Based Method to Detect Anomaly
Anomaly detection methods based on deep learning typically utilize reconstruction as a proxy task. These methods train a deep model to reconstruct the input from high-level features extracted from the samples....
-
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
Bi-direction Feature Pyramid Temporal Action Detection Network
Temporal action detection in long-untrimmed videos is still a challenging task in video content analysis. Many existing approaches contain two stages, which firstly generate action proposals and then classify ...
-
Chapter and Conference Paper
Cerebrovascular Segmentation in MRA via Reverse Edge Attention Network
Automated extraction of cerebrovascular is of great importance in understanding the mechanism, diagnosis, and treatment of many cerebrovascular pathologies. However, segmentation of cerebrovascular networks fr...
-
Chapter and Conference Paper
Constrain Latent Space for Schizophrenia Classification via Dual Space Map** Net
Mining potential biomarkers of schizophrenia (SCZ) while performing classification is essential for the research of SCZ. However, most related studies only perform a simple binary classification with high-dime...
-
Chapter and Conference Paper
Learning to See in the Dark with Events
Imaging in the dark environment is important for many real-world applications like video surveillance. Recently, the development of Event Cameras raises promising directions in solving this task thanks to its Hig...
-
Article
A novel EEG-complexity-based feature and its application on the epileptic seizure detection
The neurophysiology system is a complex network of nerves and cells, which carries messages to and from the brain and spinal cord to various parts of the body. Exploring complexity of the system can be contrib...
-
Article
Open AccessA feature selection framework for video semantic recognition via integrated cross-media analysis and embedded learning
Video data are usually represented by high dimensional features. The performance of video semantic recognition, however, may be deteriorated due to the irrelevant and redundant components included into the hig...
-
Article
Accelerated image factorization based on improved NMF algorithm
Non-negative matrix factorization (NMF) is widely used in feature extraction and dimension reduction fields. Essentially, it is an optimization problem to determine two non-negative low rank matrices ...
-
Chapter and Conference Paper
Focal Loss for Region Proposal Network
Currently, most state-of-the-art object detection models are based on a two-stage scheme pioneered by R-CNN and integrated with region proposal network (RPN), which is served as proposal generation. During the...