no code implementations • 23 Aug 2023 • Kangmin Xu, Liang Liao, Jing Xiao, Chaofeng Chen, HaoNing Wu, Qiong Yan, Weisi Lin
Further, we propose a local distortion extractor to obtain local distortion features from the pretrained CNN and a local distortion injector to inject the local distortion features into ViT.
1 code implementation • 8 Jul 2022 • Liang Liao, Kangmin Xu, HaoNing Wu, Chaofeng Chen, Wenxiu Sun, Qiong Yan, Weisi Lin
Experiments show that the perceptual representation in the HVS is an effective way of predicting subjective temporal quality, and thus TPQI can, for the first time, achieve comparable performance to the spatial quality metric and be even more effective in assessing videos with large temporal variations.
1 code implementation • 9 Jun 2021 • Jingyuan Chen, Guanchen Ding, Yuchen Yang, Wenwei Han, Kangmin Xu, Tianyi Gao, Zhe Zhang, Wanping Ouyang, Hao Cai, Zhenzhong Chen
For the vehicle detection and tracking module, we adopted YOLOv5 and multi-scale tracking to localize the anomalies.