-
Chapter and Conference Paper
Zero-Shot Relation Triplet Extraction via Retrieval-Augmented Synthetic Data Generation
In response to the challenge of existing relation triplet extraction models struggling to adapt to new relation categories in zero-shot scenarios, we propose a method that combines generated synthetic training...
-
Chapter and Conference Paper
Style Recognition of Calligraphic Chinese Characters Based on Morphological Convolutional Neural Network
As an indispensable part of the excellent traditional Chinese culture, calligraphic Chinese characters have gradually evolved into different style types in the development process, which has raised the thresho...
-
Chapter and Conference Paper
CrowdFusion: Refined Cross-Modal Fusion Network for RGB-T Crowd Counting
Crowd counting is a crucial task in computer vision, offering numerous applications in smart security, remote sensing, agriculture and forestry. While pure image-based models have made significant advancements...
-
Chapter and Conference Paper
An Adaptive Weight Joint Loss Optimization for Dog Face Recognition
In recent years, the field of human face recognition has developed rapidly, and a large number of deep learning methods have proven their efficiency in human face recognition. However, these methods do not wor...
-
Chapter and Conference Paper
Lightweight Image Compression Based on Deep Learning
Deep learning based image compression (DLIC) algorithms have achieved higher compression gain than conventional algorithms. However, the large parameters and float-point operations (FLOPs) of DLIC severely lim...
-
Chapter and Conference Paper
You Already Have It: A Generator-Free Low-Precision DNN Training Framework Using Stochastic Rounding
Stochastic rounding is a critical technique used in low-precision deep neural networks (DNNs) training to ensure good model accuracy. However, it requires a large number of random numbers generated on the fly....
-
Chapter and Conference Paper
4Seasons: A Cross-Season Dataset for Multi-Weather SLAM in Autonomous Driving
We present a novel dataset covering seasonal and challenging perceptual conditions for autonomous driving. Among others, it enables research on visual odometry, global place recognition, and map-based re-local...
-
Chapter and Conference Paper
A Deep Reinforced Tree-Traversal Agent for Coronary Artery Centerline Extraction
Vessel centerline extraction is fundamental for plentiful medical applications. Majority of current methods require pre-segmentations, distance maps or similar sorts of scanning whole volume action and followe...
-
Chapter and Conference Paper
Lightweight Single-Image Super-Resolution Network with Attentive Auxiliary Feature Learning
Despite convolutional network-based methods have boosted the performance of single image super-resolution (SISR), the huge computation costs restrict their practical applicability. In this paper, we develop a ...
-
Chapter and Conference Paper
Segmentation to Label: Automatic Coronary Artery Labeling from Mask Parcellation
Automatic and accurate coronary artery labeling technique from CCTA can greatly reduce clinician’s manual efforts and benefit large-scale data analysis. Current line of research falls into two general categori...
-
Chapter and Conference Paper
Collaborative-Representation-Based Nearest Neighbor Classifier for Hyperspectral Image Classification Combined with Superpixel and Loopy Belief Propagation
The k nearest neighbor (KNN) is one of the most popular classifiers for hyperspectral images (HSI). However, in hyperspectral imagery classification, since the pixel spectral signatures are usually mixed due t...
-
Chapter and Conference Paper
Emotion Recognition Using Eye Gaze Based on Shallow CNN with Identity Map**
Machine recognition of human emotions has attracted more and more attention for its wide application in recent years. As a spontaneous signal of human behavior, eye gaze is utilized for emotion recognition. Co...
-
Chapter and Conference Paper
EEG-Based Emotion Estimate Using Shallow Fully Convolutional Neural Network with Boost Training Strategy
Emotion recognition using Electroencephalogram (EEG) has drawn the attention of many scholars. However, there are few studies looking into regressive approach. Actually, human affective states are continuous r...
-
Chapter and Conference Paper
Suppressing Mislabeled Data via Grou** and Self-attention
Deep networks achieve excellent results on large-scale clean data but degrade significantly when learning from noisy labels. To suppressing the impact of mislabeled data, this paper proposes a conceptually sim...
-
Chapter and Conference Paper
The Sixth Visual Object Tracking VOT2018 Challenge Results
The Visual Object Tracking challenge VOT2018 is the sixth annual tracker benchmarking activity organized by the VOT initiative. Results of over eighty trackers are presented; many are state-of-the-art trackers...
-
Chapter and Conference Paper
BERT Based Hierarchical Sequence Classification for Context-Aware Microblog Sentiment Analysis
In microblog sentiment analysis task, most of the existing algorithms treat each microblog isolatedly. However, in many cases, the sentiments of microblogs can be ambiguous and context-dependent, such as micro...
-
Chapter and Conference Paper
Dense Light Field Reconstruction from Sparse Sampling Using Residual Network
A light field records numerous light rays from a real-world scene. However, capturing a dense light field by existing devices is a time-consuming process. Besides, reconstructing a large amount of light rays e...
-
Chapter and Conference Paper
Face Recognition via Heuristic Deep Active Learning
Recent successes on face recognition tasks require a large number of annotated samples for training models. However, the sample-labeling process is slow and expensive. An effective approach to reduce the annot...
-
Chapter and Conference Paper
Predicting Multisite Protein Sub-cellular Locations Based on Correlation Coefficient
With the development of proteomics and cell biology, protein sub-cellular location has become a hot topic in bioinformatics. As the time goes on, more and more researchers make great efforts on studying protei...
-
Chapter and Conference Paper
Determination of Focal Length for Targets Positioning with Binocular Stereo Vision
Targets positioning with binocular stereo vision has the potential of usage for surveillance on airdrome surface. This paper analyses the impact of focal length of a camera on the accuracy of positioning targe...