Picture for Xin Feng

Xin Feng

Start from Video-Music Retrieval: An Inter-Intra Modal Loss for Cross Modal Retrieval

Add code
Jul 28, 2024
Viaarxiv icon

Metamorpheus: Interactive, Affective, and Creative Dream Narration Through Metaphorical Visual Storytelling

Add code
Mar 01, 2024
Viaarxiv icon

Unsupervised Learning Method for the Wave Equation Based on Finite Difference Residual Constraints Loss

Add code
Jan 23, 2024
Viaarxiv icon

Hierarchical Contrastive Learning for Pattern-Generalizable Image Corruption Detection

Add code
Aug 27, 2023
Viaarxiv icon

Efficient Visual Computing with Camera RAW Snapshots

Add code
Dec 15, 2022
Viaarxiv icon

Learning Generalizable Latent Representations for Novel Degradations in Super Resolution

Add code
Jul 25, 2022
Figure 1 for Learning Generalizable Latent Representations for Novel Degradations in Super Resolution
Figure 2 for Learning Generalizable Latent Representations for Novel Degradations in Super Resolution
Figure 3 for Learning Generalizable Latent Representations for Novel Degradations in Super Resolution
Figure 4 for Learning Generalizable Latent Representations for Novel Degradations in Super Resolution
Viaarxiv icon

Learning Sequence Representations by Non-local Recurrent Neural Memory

Add code
Jul 20, 2022
Figure 1 for Learning Sequence Representations by Non-local Recurrent Neural Memory
Figure 2 for Learning Sequence Representations by Non-local Recurrent Neural Memory
Figure 3 for Learning Sequence Representations by Non-local Recurrent Neural Memory
Figure 4 for Learning Sequence Representations by Non-local Recurrent Neural Memory
Viaarxiv icon

Global-Local Stepwise Generative Network for Ultra High-Resolution Image Restoration

Add code
Jul 16, 2022
Figure 1 for Global-Local Stepwise Generative Network for Ultra High-Resolution Image Restoration
Figure 2 for Global-Local Stepwise Generative Network for Ultra High-Resolution Image Restoration
Figure 3 for Global-Local Stepwise Generative Network for Ultra High-Resolution Image Restoration
Figure 4 for Global-Local Stepwise Generative Network for Ultra High-Resolution Image Restoration
Viaarxiv icon

ViT-P: Rethinking Data-efficient Vision Transformers from Locality

Add code
Mar 04, 2022
Figure 1 for ViT-P: Rethinking Data-efficient Vision Transformers from Locality
Figure 2 for ViT-P: Rethinking Data-efficient Vision Transformers from Locality
Figure 3 for ViT-P: Rethinking Data-efficient Vision Transformers from Locality
Figure 4 for ViT-P: Rethinking Data-efficient Vision Transformers from Locality
Viaarxiv icon

U2-Former: A Nested U-shaped Transformer for Image Restoration

Add code
Dec 08, 2021
Figure 1 for U2-Former: A Nested U-shaped Transformer for Image Restoration
Figure 2 for U2-Former: A Nested U-shaped Transformer for Image Restoration
Figure 3 for U2-Former: A Nested U-shaped Transformer for Image Restoration
Figure 4 for U2-Former: A Nested U-shaped Transformer for Image Restoration
Viaarxiv icon