8 papers
Enhancing Conversational Agents via Task-Oriented Adversarial Memory Adaptation
Yimin Deng, Yuqing Fu, Derong Xu +10
Conversational agents struggle to handle long conversations due to context window limitations. Therefore, memory systems are developed to leverage essential historical information.…
DeRA: Decoupled Representation Alignment for Video Tokenization
Pengbo Guo, Junke Wang, Zhen Xing +4
This paper presents DeRA, a novel 1D video tokenizer that decouples the spatial-temporal representation learning in video tokenization to achieve better training efficiency and per…
Exploring Spectral Characteristics for Single Image Reflection Removal
Pengbo Guo, Chengxu Liu, Guoshuai Zhao +3
Eliminating reflections caused by incident light interacting with reflective medium remains an ill-posed problem in the image restoration area. The primary challenge arises from th…
Learning Deblurring Texture Prior from Unpaired Data with Diffusion Model
Chengxu Liu, Lu Qi, Jinshan Pan +2
Since acquiring large amounts of realistic blurry-sharp image pairs is difficult and expensive, learning blind image deblurring from unpaired data is a more practical and promising…
Frequency Domain-Based Diffusion Model for Unpaired Image Dehazing
Chengxu Liu, Lu Qi, Jinshan Pan +2
Unpaired image dehazing has attracted increasing attention due to its flexible data requirements during model training. Dominant methods based on contrastive learning not only intr…
Learning Attribute-aware Representations for Few-shot Scene Text Segmentation
Yifan Tang, Chenming Li, Chengxu Liu +8
Supervised scene text segmentation has achieved notable progress in recent years. However, its development is largely constrained by the scarcity of high-quality datasets and the h…