H
Huizhu Jia
Researcher at Peking University
Publications - 104
Citations - 1882
Huizhu Jia is an academic researcher from Peking University. The author has contributed to research in topics: Encoder & Motion estimation. The author has an hindex of 13, co-authored 97 publications receiving 880 citations. Previous affiliations of Huizhu Jia include Beihang University.
Papers
More filters
Proceedings ArticleDOI
A highly efficient pipeline architecture of RDO-based mode decision design for AVS HD video encoder
TL;DR: An MD algorithm based on RDO is given, which makes more mode candidates enter into RDO mode decision with little hardware resource increment, and a block-level 5-stage hardware pipeline is implemented that can support the real time RDOmode decision processing of 1080P@30fps.
Journal ArticleDOI
Three-level pipelined multi-resolution integer motion estimation engine with optimized reference data sharing search for AVS
TL;DR: A three-level pipelined VLSI architecture design is proposed, where efficiently integrates the reference data sharing search (RDSS) into multi-resolution motion estimation algorithm (MMEA) and guarantees the gradual refinement of MMEA and the hardware utilization.
Proceedings ArticleDOI
Fusion Target Attention Mask Generation Network For Video Segmentation
TL;DR: A novel attention-driven hybrid encoder-decoder network that generates object segmentation by fully leveraging spatial and temporal information is proposed, which demonstrates its superior robustness and effectiveness as compared with the state of the arts.
Proceedings ArticleDOI
AnalogCast: Full linear coding and pseudo analog transmission for satellite remote-sensing images
TL;DR: The proposed AnalogCast is a pseudo analog coding system for transmitting satellite remote-sensing images to large number of receivers that follows the idea originally developed for SoftCast but with two special techniques, scale factor estimate based on L-shaped chunk division and scale factor fix curve-fitting model.
Journal ArticleDOI
Computation-constrained dynamic search range control for real-time video encoder
TL;DR: An effective predicted motion vector (PMV) deviation metric is model to predict the relationship between SR and motion vector difference (MVD), according to the prediction differences of both temporal and spatial motions of neighboring blocks.