Search Results - "Ji, Xiaozhong"
-
1
Real-World Super-Resolution via Kernel Estimation and Noise Injection
Published in 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (01-06-2020)“…Recent state-of-the-art super-resolution methods have achieved impressive performance on ideal datasets regardless of blur and noise. However, these methods…”
Get full text
Conference Proceeding -
2
NTIRE 2020 Challenge on Real-World Image Super-Resolution: Methods and Results
Published in 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (01-06-2020)“…This paper reviews the NTIRE 2020 challenge on real world super-resolution. It focuses on the participating methods and final results. The challenge addresses…”
Get full text
Conference Proceeding -
3
The Catalytic Nanodiode: Gas Phase Catalytic Reaction Generated Electron Flow Using Nanoscale Platinum Titanium Oxide Schottky Diodes
Published in Nano letters (01-04-2005)“…Forty microampere current was generated on a platinum−titanium dioxide Schottky diode during the platinum catalyzed steady-state oxidation of carbon monoxide…”
Get full text
Journal Article -
4
CASR: a context-aware residual network for single-image super-resolution
Published in Neural computing & applications (01-09-2020)“…With the significant power of deep learning architectures, researchers have made much progress on super-resolution in the past few years. However, due to low…”
Get full text
Journal Article -
5
Electron Flow Generated by Gas Phase Exothermic Catalytic Reactions Using a Platinum−Gallium Nitride Nanodiode
Published in Journal of the American Chemical Society (27-04-2005)“…We report steady-state conversion of chemical reaction energy into hot electrons by ballistic injection into a platinum−gallium nitride (Pt/GaN) nanodiode…”
Get full text
Journal Article -
6
Blind Face Restoration via Integrating Face Shape and Generative Priors
Published in 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (01-06-2022)“…Blind face restoration, which aims to reconstruct high-quality images from low-quality inputs, can benefit many applications. Although existing…”
Get full text
Conference Proceeding -
7
Efficient Reinforcement Learning for StarCraft by Abstract Forward Models and Transfer Learning
Published in IEEE transactions on games (01-06-2022)“…Injecting human knowledge is an effective way to accelerate reinforcement learning (RL). However, these methods are underexplored. This paper presents our…”
Get full text
Journal Article -
8
NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results
Published in 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (01-06-2022)“…This paper reviews the NTIRE 2022 challenge on efficient single image super-resolution with focus on the proposed solutions and results. The task of the…”
Get full text
Conference Proceeding -
9
MIMAFace: Face Animation via Motion-Identity Modulated Appearance Feature Learning
Published 23-09-2024“…Current diffusion-based face animation methods generally adopt a ReferenceNet (a copy of U-Net) and a large amount of curated self-acquired data to learn…”
Get full text
Journal Article -
10
SVP: Style-Enhanced Vivid Portrait Talking Head Diffusion Model
Published 05-09-2024“…Talking Head Generation (THG), typically driven by audio, is an important and challenging task with broad application prospects in various fields such as…”
Get full text
Journal Article -
11
RealTalk: Real-time and Realistic Audio-driven Face Generation with 3D Facial Prior-guided Identity Alignment Network
Published 26-06-2024“…Person-generic audio-driven face generation is a challenging task in computer vision. Previous methods have achieved remarkable progress in audio-visual…”
Get full text
Journal Article -
12
DiffuMatting: Synthesizing Arbitrary Objects with Matting-level Annotation
Published 10-03-2024“…Due to the difficulty and labor-consuming nature of getting highly accurate or matting annotations, there only exists a limited amount of highly accurate…”
Get full text
Journal Article -
13
UniM-OV3D: Uni-Modality Open-Vocabulary 3D Scene Understanding with Fine-Grained Feature Representation
Published 20-01-2024“…3D open-vocabulary scene understanding aims to recognize arbitrary novel categories beyond the base label space. However, existing works not only fail to fully…”
Get full text
Journal Article -
14
NTIRE 2021 Challenge on Video Super-Resolution
Published in 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (01-06-2021)“…Super-Resolution (SR) is a fundamental computer vision task that aims to obtain a high-resolution clean image from the given low-resolution counterpart. This…”
Get full text
Conference Proceeding -
15
A Novel Two-Factor Attention Encoder-Decoder Network through Combining Temporal and Prior Knowledge for Weather Forecasting
Published in 2019 International Joint Conference on Neural Networks (IJCNN) (01-07-2019)“…This paper proposes a novel two-factor attention based encoder-decoder model (TwoFactorEncoderDecoder) for multivariate weather prediction. The proposed model…”
Get full text
Conference Proceeding -
16
Frequency Consistent Adaptation for Real World Super Resolution
Published 18-12-2020“…Recent deep-learning based Super-Resolution (SR) methods have achieved remarkable performance on images with known degradation. However, these methods always…”
Get full text
Journal Article -
17
Spectrum-to-Kernel Translation for Accurate Blind Image Super-Resolution
Published 23-10-2021“…Deep-learning based Super-Resolution (SR) methods have exhibited promising performance under non-blind setting where blur kernel is known. However, blur…”
Get full text
Journal Article -
18
AE TextSpotter: Learning Visual and Linguistic Representation for Ambiguous Text Spotting
Published 03-08-2020“…Scene text spotting aims to detect and recognize the entire word or sentence with multiple characters in natural images. It is still challenging because…”
Get full text
Journal Article -
19
Efficient Reinforcement Learning for StarCraft by Abstract Forward Models and Transfer Learning
Published 02-03-2019“…Injecting human knowledge is an effective way to accelerate reinforcement learning (RL). However, these methods are underexplored. This paper presents our…”
Get full text
Journal Article -
20
NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results
Published 11-05-2022“…This paper reviews the NTIRE 2022 challenge on efficient single image super-resolution with focus on the proposed solutions and results. The task of the…”
Get full text
Journal Article