12 citations · 19 across the 31 of their papers we have counts for
12 papers · 1 filter
Simpler and Stronger Baselines for All-in-One Image Restoration
Hongyu Du, Wenlong Jiao, Heyang Lee +7
Current methods for all-in-one image restoration increasingly rely on complex mechanisms, such as Mixture-of-Experts or prompt learning, to handle diverse degradations.In this work…
BasicAVSR: Arbitrary-Scale Video Super-Resolution via Image Priors and Enhanced Motion Compensation
Wei Shang, Wanying Zhang, Shuhang Gu +3
Arbitrary-scale video super-resolution (AVSR) aims to enhance the resolution of video frames, potentially at various scaling factors, which presents several challenges regarding sp…
Decoupled Multi-Predictor Optimization for Inference-Efficient Model Tuning
Liwei Luo, Shuaitengyuan Li, Dongwei Ren +3
Recently, remarkable progress has been made in large-scale pre-trained model tuning, and inference efficiency is becoming more crucial for practical deployment. Early exiting in co…
Multimodal Negative Learning
Baoquan Gong, Xiyuan Gao, Pengfei Zhu +2
Multimodal learning systems often encounter challenges related to modality imbalance, where a dominant modality may overshadow others, thereby hindering the learning of weak modali…
Motion-Aware Adaptive Pixel Pruning for Efficient Local Motion Deblurring
Wei Shang, Dongwei Ren, Wanying Zhang +3
Local motion blur in digital images originates from the relative motion between dynamic objects and static imaging systems during exposure. Existing deblurring methods face signifi…
Hyperbolic Cycle Alignment for Infrared-Visible Image Fusion
Timing Li, Bing Cao, Jiahe Feng +3
Image fusion synthesizes complementary information from multiple sources, mitigating the inherent limitations of unimodal imaging systems. Accurate image registration is essential…
High-Frequency Prior-Driven Adaptive Masking for Accelerating Image Super-Resolution
Wei Shang, Dongwei Ren, Wanying Zhang +3
The primary challenge in accelerating image super-resolution lies in reducing computation while maintaining performance and adaptability. Motivated by the observation that high-fre…
Bi-directional Self-Registration for Misaligned Infrared-Visible Image Fusion
Timing Li, Bing Cao, Pengfei Zhu +2
Acquiring accurately aligned multi-modal image pairs is fundamental for achieving high-quality multi-modal image fusion. To address the lack of ground truth in current multi-modal…
VTD-CLIP: Video-to-Text Discretization via Prompting CLIP
Wencheng Zhu, Yuexin Wang, Hongxuan Li +2
Vision-language models bridge visual and linguistic understanding and have proven to be powerful for video recognition tasks. Existing approaches primarily rely on parameter-effici…
BackMix: Regularizing Open Set Recognition by Removing Underlying Fore-Background Priors
Yu Wang, Junxian Mu, Hongzhi Huang +3
Open set recognition (OSR) requires models to classify known samples while detecting unknown samples for real-world applications. Existing studies show impressive progress using un…
Dream-IF: Dynamic Relative EnhAnceMent for Image Fusion
Xingxin Xu, Bing Cao, Dongdong Li +2
Image fusion aims to integrate comprehensive information from images acquired through multiple sources. However, images captured by diverse sensors often encounter various degradat…
Asymmetric Reinforcing against Multi-modal Representation Bias
Xiyuan Gao, Bing Cao, Pengfei Zhu +2
The strength of multimodal learning lies in its ability to integrate information from various sources, providing rich and comprehensive insights. However, in real-world scenarios,…