Z
Zhibo Chen
Researcher at University of Science and Technology of China
Publications - 374
Citations - 6048
Zhibo Chen is an academic researcher from University of Science and Technology of China. The author has contributed to research in topics: Computer science & Image quality. The author has an hindex of 27, co-authored 344 publications receiving 3385 citations. Previous affiliations of Zhibo Chen include Sony Broadcast & Professional Research Laboratories & Microsoft.
Papers
More filters
Posted Content
Beyond Triplet Loss: Meta Prototypical N-tuple Loss for Person Re-identification
TL;DR: Wang et al. as mentioned in this paper proposed a multi-class classification loss, i.e., N-tuple loss, to jointly consider multiple (N) instances for per-query optimization.
Patent
Method and apparatus for video quality assessment based on content complexity
TL;DR: In this article, the energy of prediction residuals and alignment scaling factors are calculated to estimate the content complexity of a video, and an overall content unpredictability parameter can be estimated to compute a compression distortion factor for the video.
Posted Content
Quality Assessment of Stereoscopic 360-degree Images from Multi-viewports
TL;DR: In this article, a multi-viewport based full-reference stereo 360 IQA model was proposed to evaluate the quality of experience (QoE) of 3D omnidirectional panoramic images.
Posted Content
Task-driven Semantic Coding via Reinforcement Learning.
Xin Li,Jun Shi,Zhibo Chen +2 more
TL;DR: Zhang et al. as mentioned in this paper implemented task-driven semantic coding by implementing semantic bit allocation based on reinforcement learning (RL) for video/image classification, detection and segmentation.
Proceedings ArticleDOI
Light Field Compression Based on Implicit Neural Representation
Henan Wang,Hanxi Zhu,Zhibo Chen +2 more
TL;DR: Zhang et al. as discussed by the authors proposed a novel light field compression scheme based on implicit neural representation to reduce redundancy between views, which achieves comparable rate-distortion performance as well as superior perceptual quality over traditional methods.