11 citations · 21 across the 11 of their papers we have counts for
7 papers · 1 filter
Visual and Textual Prompts in VLLMs for Enhancing Emotion Recognition
Zhifeng Wang, Qixuan Zhang, Peter Zhang +5
Vision Large Language Models (VLLMs) exhibit promising potential for multi-modal understanding, yet their application to video-based emotion recognition remains limited by insuffic…
Visual Prompting in LLMs for Enhancing Emotion Recognition
Qixuan Zhang, Zhifeng Wang, Dylan Zhang +5
Vision Large Language Models (VLLMs) are transforming the intersection of computer vision and natural language processing. Nonetheless, the potential of using visual prompts for em…
Authentic Emotion Mapping: Benchmarking Facial Expressions in Real News
Qixuan Zhang, Zhifeng Wang, Yang Liu +4
In this paper, we present a novel benchmark for Emotion Recognition using facial landmarks extracted from realistic news videos. Traditional methods relying on RGB images are resou…
AMF: Adaptable Weighting Fusion with Multiple Fine-tuning for Image Classification
Xuyang Shen, Jo Plested, Sabrina Caldwell +2
Fine-tuning is widely applied in image classification tasks as a transfer learning approach. It re-uses the knowledge from a source task to learn and obtain a high performance in t…
Exploring Biases and Prejudice of Facial Synthesis via Semantic Latent Space
Xuyang Shen, Jo Plested, Sabrina Caldwell +1
Deep learning (DL) models are widely used to provide a more convenient and smarter life. However, biased algorithms will negatively influence us. For instance, groups targeted by b…
Disentangling Noise from Images: A Flow-Based Image Denoising Neural Network
Yang Liu, Saeed Anwar, Zhenyue Qin +3
The prevalent convolutional neural network (CNN) based image denoising methods extract features of images to restore the clean ground truth, achieving high denoising accuracy. Howe…
Are Deep Neural Architectures Losing Information? Invertibility Is Indispensable
Yang Liu, Zhenyue Qin, Saeed Anwar +2
Ever since the advent of AlexNet, designing novel deep neural architectures for different tasks has consistently been a productive research direction. Despite the exceptional perfo…