1 code implementation • 8 Jan 2024 • Jiquan Yuan, Xinyan Cao, Jinming Che, Qinyuan Wang, Sen Liang, Wei Ren, Jinlong Lin, Xixin Cao
However, most existing AIGCIQA methods regress predicted scores directly from individual generated images, overlooking the information contained in the text prompts of these images.
1 code implementation • 10 Dec 2023 • Jiquan Yuan, Xinyan Cao, Linjing Cao, Jinlong Lin, Xixin Cao
To demonstrate the effectiveness of our proposed PSCR framework, we conduct extensive experiments on three mainstream AIGCIQA databases including AGIQA-1K, AGIQA-3K and AIGCIQA2023.
1 code implementation • 27 Nov 2023 • Jiquan Yuan, Xinyan Cao, Changjin Li, Fanyi Yang, Jinlong Lin, Xixin Cao
Although previous work has established several human perception-based AIGC image quality assessment (AIGCIQA) databases for text-generated images, the AI image generation technology includes scenarios like text-to-image and image-to-image, and assessing only the images generated by text-to-image models is insufficient.
no code implementations • 29 Nov 2019 • Yuxuan Zhao, Xinyan Cao, Jinlong Lin, Dunshan Yu, Xixin Cao
There has been an encouraging progress in the affective states recognition models based on the single-modality signals as electroencephalogram (EEG) signals or peripheral physiological signals in recent years.