![]() |
Minglang, Qiao |
I am a postdoctoral applicant from the Multimedia Computing Towards Communications Lab at Beihang University, China, where I collaborated with Prof. Mai Xu.
My research interests focus on low-level vision, including quality enhancement, quality assessment, human attention modeling, salient object detection and their applications in perceptual video coding.
I obtained my Ph.D. in Communications and Information Engineering at Beihang University in November 2024, supervised by Prof. Mai Xu.
Previously, I obtained my B.Sc. degree in 2018 at Beihang University, P.R. China.
![]() |
HyperSOR: context-aware graph hypernetwork for salient object ranking |
![]() |
Joint learning of audio–visual saliency prediction and sound source localization on multi-face videos |
![]() |
MT-VQA: A Multi-task Approach for Quality Assessment of Short-form Videos |
![]() |
NTIRE 2022 Challenge on Super-Resolution and Quality Enhancement of Compressed Video |
Viewport-Dependent Saliency Prediction in 360° Video |
|
![]() |
Learning to Predict Salient Faces: A Novel Visual-Audio Saliency Model |
![]() |
Saliency prediction of sports videos: A large-scale database and a self-adaptive approach |
![]() |
Predicting Head Movement in Panoramic Video: A Deep Reinforcement Learning Approach |
![]() |
Saliency prediction on mobile videos: A fixation mapping-based dataset and a transformer approach |