Xiangfei Sheng

Orcid: 0009-0004-8468-1970

According to our database1, Xiangfei Sheng authored at least 13 papers between 2023 and 2026.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

On csauthors.net:

Bibliography

2026
Fine-grained Image Aesthetic Assessment: Learning Discriminative Scores from Relative Ranks.
CoRR, March, 2026

AesPrompt: Zero-Shot Image Aesthetics Assessment With Multi-Granularity Aesthetic Prompt Learning.
IEEE Trans. Multim., 2026

LongT2IBench: A Benchmark for Evaluating Long Text-to-Image Generation with Graph-structured Annotations.
Proceedings of the Fortieth AAAI Conference on Artificial Intelligence, 2026

Fine-grained Image Quality Assessment for Perceptual Image Restoration.
Proceedings of the Fortieth AAAI Conference on Artificial Intelligence, 2026

TuningIQA: Fine-Grained Blind Image Quality Assessment for Livestreaming Camera Tuning.
Proceedings of the Fortieth AAAI Conference on Artificial Intelligence, 2026

2025
Towards Explainable Image Aesthetics Assessment With Attribute-Oriented Critiques Generation.
IEEE Trans. Circuits Syst. Video Technol., February, 2025

InstructCrop: Teaching Multimodal Large Language Models to Crop Aesthetic Images.
Proceedings of the 33rd ACM International Conference on Multimedia, 2025

Text-to-Image Diffusion Models are AI-Generated Image Quality Scorers.
Proceedings of the IEEE International Conference on Multimedia and Expo, 2025

2024
AesBench: An Expert Benchmark for Multimodal Large Language Models on Image Aesthetics Perception.
CoRR, 2024

AesExpert: Towards Multi-modality Foundation Model for Image Aesthetics Perception.
Proceedings of the 32nd ACM International Conference on Multimedia, MM 2024, Melbourne, VIC, Australia, 28 October 2024, 2024


2023
Technical Quality-Assisted Image Aesthetics Quality Assessment.
Proceedings of the Pattern Recognition and Computer Vision - 6th Chinese Conference, 2023

AesCLIP: Multi-Attribute Contrastive Learning for Image Aesthetics Assessment.
Proceedings of the 31st ACM International Conference on Multimedia, 2023


  Loading...