Picture for Dongyun Lin

Dongyun Lin

Bridging the Intent Gap: Knowledge-Enhanced Visual Generation

May 21, 2024
Viaarxiv icon

PEVA-Net: Prompt-Enhanced View Aggregation Network for Zero/Few-Shot Multi-View 3D Shape Recognition

Apr 30, 2024
Figure 1 for PEVA-Net: Prompt-Enhanced View Aggregation Network for Zero/Few-Shot Multi-View 3D Shape Recognition
Figure 2 for PEVA-Net: Prompt-Enhanced View Aggregation Network for Zero/Few-Shot Multi-View 3D Shape Recognition
Figure 3 for PEVA-Net: Prompt-Enhanced View Aggregation Network for Zero/Few-Shot Multi-View 3D Shape Recognition
Figure 4 for PEVA-Net: Prompt-Enhanced View Aggregation Network for Zero/Few-Shot Multi-View 3D Shape Recognition
Viaarxiv icon

Keyword-Aware Relative Spatio-Temporal Graph Networks for Video Question Answering

Jul 25, 2023
Figure 1 for Keyword-Aware Relative Spatio-Temporal Graph Networks for Video Question Answering
Figure 2 for Keyword-Aware Relative Spatio-Temporal Graph Networks for Video Question Answering
Figure 3 for Keyword-Aware Relative Spatio-Temporal Graph Networks for Video Question Answering
Figure 4 for Keyword-Aware Relative Spatio-Temporal Graph Networks for Video Question Answering
Viaarxiv icon

SCA-PVNet: Self-and-Cross Attention Based Aggregation of Point Cloud and Multi-View for 3D Object Retrieval

Jul 20, 2023
Viaarxiv icon

A Study on Differentiable Logic and LLMs for EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition 2023

Jul 13, 2023
Figure 1 for A Study on Differentiable Logic and LLMs for EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition 2023
Figure 2 for A Study on Differentiable Logic and LLMs for EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition 2023
Figure 3 for A Study on Differentiable Logic and LLMs for EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition 2023
Figure 4 for A Study on Differentiable Logic and LLMs for EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition 2023
Viaarxiv icon

Team VI-I2R Technical Report on EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition 2022

Jan 29, 2023
Figure 1 for Team VI-I2R Technical Report on EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition 2022
Figure 2 for Team VI-I2R Technical Report on EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition 2022
Figure 3 for Team VI-I2R Technical Report on EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition 2022
Figure 4 for Team VI-I2R Technical Report on EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition 2022
Viaarxiv icon

Few-Shot Defect Segmentation Leveraging Abundant Normal Training Samples Through Normal Background Regularization and Crop-and-Paste Operation

Jul 18, 2020
Figure 1 for Few-Shot Defect Segmentation Leveraging Abundant Normal Training Samples Through Normal Background Regularization and Crop-and-Paste Operation
Figure 2 for Few-Shot Defect Segmentation Leveraging Abundant Normal Training Samples Through Normal Background Regularization and Crop-and-Paste Operation
Figure 3 for Few-Shot Defect Segmentation Leveraging Abundant Normal Training Samples Through Normal Background Regularization and Crop-and-Paste Operation
Figure 4 for Few-Shot Defect Segmentation Leveraging Abundant Normal Training Samples Through Normal Background Regularization and Crop-and-Paste Operation
Viaarxiv icon

DDR-ID: Dual Deep Reconstruction Networks Based Image Decomposition for Anomaly Detection

Jul 18, 2020
Figure 1 for DDR-ID: Dual Deep Reconstruction Networks Based Image Decomposition for Anomaly Detection
Figure 2 for DDR-ID: Dual Deep Reconstruction Networks Based Image Decomposition for Anomaly Detection
Figure 3 for DDR-ID: Dual Deep Reconstruction Networks Based Image Decomposition for Anomaly Detection
Figure 4 for DDR-ID: Dual Deep Reconstruction Networks Based Image Decomposition for Anomaly Detection
Viaarxiv icon