143 Result(s)
-
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
Accelerated Lifetime Experiment of Maximum Current Ratio Based on Charge and Discharge Capacity Confinement
Lithium-ion batteries will undergo continuous aging during the process of charging and discharging. Charging and discharging cycle conditions for lithium-ion batteries are usually an important method to detect...
-
Chapter and Conference Paper
A Fine-Grained Domain Adaptation Method for Cross-Session Vigilance Estimation in SSVEP-Based BCI
Brain-computer interface (BCI), a direct communication system between the human brain and external environment, can provide assistance for people with disabilities. Vigilance is an important cognitive state an...
-
Chapter and Conference Paper
CSEC: A Chinese Semantic Error Correction Dataset for Written Correction
Existing research primarily focuses on spelling and grammatical errors in English, such as missing or wrongly adding characters. This kind of shallow error has been well-studied. Instead, there are many unsolv...
-
Chapter and Conference Paper
CACL:Commonsense-Aware Contrastive Learning for Knowledge Graph Completion
Most knowledge graphs (KGs) are incomplete in the real world, so knowledge graph completion (KGC) is widely investigated to predict the most credible missing facts from given knowledge. However, existing KGC m...
-
Chapter and Conference Paper
Graph Reinforcement Learning for Securing Critical Loads by E-Mobility
Inefficient scheduling of electric vehicles (EVs) is detrimental to not only the profitability of charging stations but also the experience of EV users and the stable operation of the grid. Regulating the char...
-
Chapter and Conference Paper
An Effective Morphological Analysis Framework of Intracranial Artery in 3D Digital Subtraction Angiography
Acquiring accurate anatomy information of intracranial artery from 3D digital subtraction angiography (3D-DSA) is crucial for intracranial artery intervention surgery. However, this task often comes with chall...
-
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
Visual Realism Assessment for Face-Swap Videos
Deep-learning-based face-swap videos, also known as deepfakes, are becoming more and more realistic and deceiving. The malicious usage of these face-swap videos has caused wide concerns. The research community...
-
Chapter and Conference Paper
Adaptive Rounding Compensation for Post-training Quantization
Network quantization can compress and accelerate deep neural networks by reducing the bit-width of network parameters so that the quantized networks can be deployed to resource-limited devices. Post-Training Q...
-
Chapter and Conference Paper
Rethinking Image Inpainting with Attention Feature Fusion
Recent image inpainting models have archived significant progress through learning from large-scale data. However, restoring images under complicated scenarios (e.g. large masks or complex textures) remains ch...
-
Chapter and Conference Paper
Efficient Visual Tracking via Hierarchical Cross-Attention Transformer
In recent years, target tracking has made great progress in accuracy. This development is mainly attributed to powerful networks (such as transformers) and additional modules (such as online update and refinem...
-
Chapter and Conference Paper
Towards Accurate Alignment and Sufficient Context in Scene Text Recognition
Encoder-decoder framework has recently become cutting-edge in scene text recognition (STR), where most decoder networks consist of two parts: an attention model to align visual features from the encoder for ea...
-
Chapter and Conference Paper
MMID: Combining Maximized the Mutual Information and Diffusion Model for Image Super-Resolution
The Denoising Diffusion Probabilistic Models (DDPM) [11] have shown promise in recovering realistic details for single image super-resolution (SISR). However, the diffusion model’s recovery results often suffer f...
-
Chapter and Conference Paper
Learning a Deep Fourier Attention Generative Adversarial Network for Light Field Image Super-Resolution
Human eyes can see the three-dimensional (3D) world because they receive the light emitted by objects, and the light field (LF) is a complete representation of the set of light in the 3D world. Light field ima...
-
Chapter and Conference Paper
MIPI 2022 Challenge on RGB+ToF Depth Completion: Dataset and Report
Develo** and integrating advanced image sensors with novel algorithms in camera systems is prevalent with the increasing demand for computational photography and imaging on mobile platforms. However, the lac...
-
Chapter and Conference Paper
Multi-view Adaptive Bone Activation from Chest X-Ray with Conditional Adversarial Nets
Activating bone from a chest X-ray (CXR) is significant for disease diagnosis and health equity for under-developed areas, while the complex overlap of anatomical structures in CXR constantly challenges bone a...
-
Chapter and Conference Paper
Detection and Classification of Coronary Artery Plaques in Coronary Computed Tomography Angiography Using 3D CNN
Measuring the existence of coronary artery plaques and stenoses is a standard way of evaluating the risk of cardiovascular diseases. Coronary Computed Tomography Angiography (CCTA) is one of the most common as...
-
Chapter and Conference Paper
Non-Uniform Attention Network for Multi-modal Sentiment Analysis
Remarkable success has been achieved in the multi-modal sentiment analysis community thanks to the existence of annotated multi-modal data sets. However, coming from three different modalities, text, sound, an...
-
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....