Picture for Dehui Kong

Dehui Kong

SYENet: A Simple Yet Effective Network for Multiple Low-Level Vision Tasks with Real-time Performance on Mobile Device

Add code
Aug 16, 2023
Figure 1 for SYENet: A Simple Yet Effective Network for Multiple Low-Level Vision Tasks with Real-time Performance on Mobile Device
Figure 2 for SYENet: A Simple Yet Effective Network for Multiple Low-Level Vision Tasks with Real-time Performance on Mobile Device
Figure 3 for SYENet: A Simple Yet Effective Network for Multiple Low-Level Vision Tasks with Real-time Performance on Mobile Device
Figure 4 for SYENet: A Simple Yet Effective Network for Multiple Low-Level Vision Tasks with Real-time Performance on Mobile Device
Viaarxiv icon

Learned Smartphone ISP on Mobile GPUs with Deep Learning, Mobile AI & AIM 2022 Challenge: Report

Nov 07, 2022
Figure 1 for Learned Smartphone ISP on Mobile GPUs with Deep Learning, Mobile AI & AIM 2022 Challenge: Report
Figure 2 for Learned Smartphone ISP on Mobile GPUs with Deep Learning, Mobile AI & AIM 2022 Challenge: Report
Figure 3 for Learned Smartphone ISP on Mobile GPUs with Deep Learning, Mobile AI & AIM 2022 Challenge: Report
Figure 4 for Learned Smartphone ISP on Mobile GPUs with Deep Learning, Mobile AI & AIM 2022 Challenge: Report
Viaarxiv icon

Grassmannian Graph-attentional Landmark Selection for Domain Adaptation

Sep 07, 2021
Figure 1 for Grassmannian Graph-attentional Landmark Selection for Domain Adaptation
Figure 2 for Grassmannian Graph-attentional Landmark Selection for Domain Adaptation
Figure 3 for Grassmannian Graph-attentional Landmark Selection for Domain Adaptation
Figure 4 for Grassmannian Graph-attentional Landmark Selection for Domain Adaptation
Viaarxiv icon

GAN for Vision, KG for Relation: a Two-stage Deep Network for Zero-shot Action Recognition

May 25, 2021
Figure 1 for GAN for Vision, KG for Relation: a Two-stage Deep Network for Zero-shot Action Recognition
Figure 2 for GAN for Vision, KG for Relation: a Two-stage Deep Network for Zero-shot Action Recognition
Figure 3 for GAN for Vision, KG for Relation: a Two-stage Deep Network for Zero-shot Action Recognition
Figure 4 for GAN for Vision, KG for Relation: a Two-stage Deep Network for Zero-shot Action Recognition
Viaarxiv icon

Real-time Human Action Recognition Using Locally Aggregated Kinematic-Guided Skeletonlet and Supervised Hashing-by-Analysis Model

May 24, 2021
Figure 1 for Real-time Human Action Recognition Using Locally Aggregated Kinematic-Guided Skeletonlet and Supervised Hashing-by-Analysis Model
Figure 2 for Real-time Human Action Recognition Using Locally Aggregated Kinematic-Guided Skeletonlet and Supervised Hashing-by-Analysis Model
Figure 3 for Real-time Human Action Recognition Using Locally Aggregated Kinematic-Guided Skeletonlet and Supervised Hashing-by-Analysis Model
Figure 4 for Real-time Human Action Recognition Using Locally Aggregated Kinematic-Guided Skeletonlet and Supervised Hashing-by-Analysis Model
Viaarxiv icon