2 citations · 4 across the 3 of their papers we have counts for
7 papers
Removing Rain in Videos: A Large-scale Database and A Two-stream ConvLSTM Approach
Tie Liu, Mai Xu, Zulin Wang
Rain removal has recently attracted increasing research attention, as it is able to enhance the visibility of rain videos. However, the existing learning based rain removal approac…
Saliency Prediction on Omnidirectional Images with Generative Adversarial Imitation Learning
Mai Xu, Li Yang, Xiaoming Tao +2
When watching omnidirectional images (ODIs), subjects can access different viewports by moving their heads. Therefore, it is necessary to predict subjects' head fixations on ODIs.…
A DenseNet Based Approach for Multi-Frame In-Loop Filter in HEVC
Tianyi Li, Mai Xu, Ren Yang +1
High efficiency video coding (HEVC) has brought outperforming efficiency for video compression. To reduce the compression artifacts of HEVC, we propose a DenseNet based approach as…
What Makes Natural Scene Memorable?
Jiaxin Lu, Mai Xu, Ren Yang +1
Recent studies on image memorability have shed light on the visual features that make generic images, object images or face photographs memorable. However, a clear understanding an…
Bridge the Gap Between VQA and Human Behavior on Omnidirectional Video: A Large-Scale Dataset and a Deep Learning Model
Chen Li, Mai Xu, Xinzhe Du +1
Omnidirectional video enables spherical stimuli with the viewing range. Meanwhile, only the viewport region of omnidirectional video can be seen by the obse…
Multi-Frame Quality Enhancement for Compressed Video
Ren Yang, Mai Xu, Zulin Wang +1
The past few years have witnessed great success in applying deep learning to enhance the quality of compressed image/video. The existing approaches mainly focus on enhancing the qu…