Picture for Zhiwei Xiong

Zhiwei Xiong

Multi-Granularity Semantic Revision for Large Language Model Distillation

Add code
Jul 14, 2024
Viaarxiv icon

LeRF: Learning Resampling Function for Adaptive and Efficient Image Interpolation

Add code
Jul 13, 2024
Viaarxiv icon

CEIA: CLIP-Based Event-Image Alignment for Open-World Event-Based Understanding

Add code
Jul 09, 2024
Viaarxiv icon

Mamba-based Light Field Super-Resolution with Efficient Subspace Scanning

Add code
Jun 23, 2024
Viaarxiv icon

Diffusion-Promoted HDR Video Reconstruction

Add code
Jun 12, 2024
Viaarxiv icon

UniCompress: Enhancing Multi-Data Medical Image Compression with Knowledge Distillation

Add code
May 27, 2024
Figure 1 for UniCompress: Enhancing Multi-Data Medical Image Compression with Knowledge Distillation
Figure 2 for UniCompress: Enhancing Multi-Data Medical Image Compression with Knowledge Distillation
Figure 3 for UniCompress: Enhancing Multi-Data Medical Image Compression with Knowledge Distillation
Figure 4 for UniCompress: Enhancing Multi-Data Medical Image Compression with Knowledge Distillation
Viaarxiv icon

TokenUnify: Scalable Autoregressive Visual Pre-training with Mixture Token Prediction

Add code
May 27, 2024
Figure 1 for TokenUnify: Scalable Autoregressive Visual Pre-training with Mixture Token Prediction
Figure 2 for TokenUnify: Scalable Autoregressive Visual Pre-training with Mixture Token Prediction
Figure 3 for TokenUnify: Scalable Autoregressive Visual Pre-training with Mixture Token Prediction
Figure 4 for TokenUnify: Scalable Autoregressive Visual Pre-training with Mixture Token Prediction
Viaarxiv icon

Incorporating Degradation Estimation in Light Field Spatial Super-Resolution

Add code
May 11, 2024
Viaarxiv icon

Multi-modal Learnable Queries for Image Aesthetics Assessment

Add code
May 02, 2024
Figure 1 for Multi-modal Learnable Queries for Image Aesthetics Assessment
Figure 2 for Multi-modal Learnable Queries for Image Aesthetics Assessment
Figure 3 for Multi-modal Learnable Queries for Image Aesthetics Assessment
Figure 4 for Multi-modal Learnable Queries for Image Aesthetics Assessment
Viaarxiv icon

Event-assisted Low-Light Video Object Segmentation

Add code
Apr 02, 2024
Figure 1 for Event-assisted Low-Light Video Object Segmentation
Figure 2 for Event-assisted Low-Light Video Object Segmentation
Figure 3 for Event-assisted Low-Light Video Object Segmentation
Figure 4 for Event-assisted Low-Light Video Object Segmentation
Viaarxiv icon