F
Feng Wu
Researcher at University of Science and Technology of China
Publications - 669
Citations - 19574
Feng Wu is an academic researcher from University of Science and Technology of China. The author has contributed to research in topics: Motion compensation & Data compression. The author has an hindex of 60, co-authored 645 publications receiving 15886 citations. Previous affiliations of Feng Wu include Center for Excellence in Education & Microsoft.
Papers
More filters
Proceedings ArticleDOI
Compressive data gathering for large-scale wireless sensor networks
TL;DR: This paper presents the first complete design to apply compressive sampling theory to sensor data gathering for large-scale wireless sensor networks and shows the efficiency and robustness of the proposed scheme.
Journal ArticleDOI
Background Prior-Based Salient Object Detection via Deep Reconstruction Residual
TL;DR: A novel framework for saliency detection is proposed by first modeling the background and then separating salient objects from the background by developing stacked denoising autoencoders with deep learning architectures to model the background.
Journal ArticleDOI
Efficient Parallel Framework for HEVC Motion Estimation on Many-Core Processors
TL;DR: This paper analyzes the ME structure in HEVC and proposes a parallel framework to decouple ME for different partitions on many-core processors and achieves more than 30 and 40 times speedup for 1920 × 1080 and 2560 × 1600 video sequences, respectively.
Journal ArticleDOI
A framework for efficient progressive fine granularity scalable video coding
Feng Wu,Shipeng Li,Ya-Qin Zhang +2 more
TL;DR: Experimental results show that the PFGS framework can improve the coding efficiency up to more than 1 dB over the FGS scheme in terms of average PSNR, yet still keeps all the original properties, such as fine granularity, bandwidth adaptation, and error recovery.
Journal ArticleDOI
A Highly Parallel Framework for HEVC Coding Unit Partitioning Tree Decision on Many-core Processors
TL;DR: This paper proposes a parallel framework to decide coding unit trees through in-depth understanding of the dependency among different coding units, and achieves averagely more than 11 and 16 times speedup for 1920x1080 and 2560x1600 video sequences, respectively, without any coding efficiency degradation.