AIS 2024 challenge on video quality assessment of user-generated content: Methods and results

MV Conde, S Zadtootaghaj, N Barman… - Proceedings of the …, 2024 - openaccess.thecvf.com
This paper reviews the AIS 2024 Video Quality Assessment (VQA) Challenge focused on
User-Generated Content (UGC). The aim of this challenge is to gather deep learning-based …

Aigc-vqa: A holistic perception metric for aigc video quality assessment

Y Lu, X Li, B Li, Z Yu, F Guan, X Wang… - Proceedings of the …, 2024 - openaccess.thecvf.com
With the development of generative models such as the diffusion model and auto-regressive
model AI-generated content (AIGC) is experiencing an explosive growth. Moreover existing …

Spire: Semantic prompt-driven image restoration

C Qi, Z Tu, K Ye, M Delbracio, P Milanfar… - … on Computer Vision, 2024 - Springer
Text-driven diffusion models have become increasingly popular for various image editing
tasks, including inpainting, stylization, and object replacement. However, it still remains an …

Prdp: Proximal reward difference prediction for large-scale reward finetuning of diffusion models

F Deng, Q Wang, W Wei, T Hou… - Proceedings of the …, 2024 - openaccess.thecvf.com
Reward finetuning has emerged as a promising approach to aligning foundation models
with downstream objectives. Remarkable success has been achieved in the language …

Q-ground: Image quality grounding with large multi-modality models

C Chen, S Yang, H Wu, L Liao, Z Zhang… - Proceedings of the …, 2024 - dl.acm.org
Recent advances of large multi-modality models (LMM) have greatly improved the ability of
image quality assessment (IQA) method to evaluate and explain the quality of visual content …

Atlantis: Aesthetic-oriented multiple granularities fusion network for joint multimodal aspect-based sentiment analysis

L **ao, X Wu, J Xu, W Li, C **, L He - Information Fusion, 2024 - Elsevier
Abstract Joint Multi-modal Aspect-based Sentiment Analysis (JMASA) is a challenging task
that seeks to identify all aspect-sentiment pairs from multimodal data. Current JMASA …