8 papers · 1 filter
Zero-Shot Video Restoration and Enhancement with Text-to-Image Latent Diffusion Models and Multi-Modal References
Cong Cao, Huanjing Yue, Xin Liu +1
Zero-shot image restoration methods with text-to-image latent diffusion models have achieved great success in universal image restoration tasks without training. However, applying…
Zero-Shot Video Restoration and Enhancement with Assistance of Video Diffusion Models
Cong Cao, Huanjing Yue, Shangbin Xie +2
Although diffusion-based zero-shot image restoration and enhancement methods have achieved great success, applying them to video restoration or enhancement will lead to severe temp…
Distribution-Specific Learning for Joint Salient and Camouflaged Object Detection
Chao Hao, Zitong Yu, Xin Liu +5
Salient object detection (SOD) and camouflaged object detection (COD) are two closely related but distinct computer vision tasks. Although both are class-agnostic segmentation task…
FEALLM: Advancing Facial Emotion Analysis in Multimodal Large Language Models with Emotional Synergy and Reasoning
Zhuozhao Hu, Kaishen Yuan, Xin Liu +5
Facial Emotion Analysis (FEA) plays a crucial role in visual affective computing, aiming to infer a person's emotional state based on facial data. Scientifically, facial expression…
EMO-LLaMA: Enhancing Facial Emotion Understanding with Instruction Tuning
Bohao Xing, Zitong Yu, Xin Liu +6
Facial expression recognition (FER) is an important research topic in emotional artificial intelligence. In recent decades, researchers have made remarkable progress. However, curr…
From Recognition to Prediction: Leveraging Sequence Reasoning for Action Anticipation
Xin Liu, Chao Hao, Zitong Yu +2
The action anticipation task refers to predicting what action will happen based on observed videos, which requires the model to have a strong ability to summarize the present and t…