activity
20202024
most citedEkya: Continuous Learning of Video Analytics Models on Edge Compute Servers

21 citations · 38 across the 4 of their papers we have counts for

collaborators

5 papers

cs.NI2024

Loss-tolerant neural video codec aware congestion control for real time video communication

Zhengxu Xia, Hanchen Li, Junchen Jiang

Because of reinforcement learning's (RL) ability to automatically create more adaptive controlling logics beyond the hand-crafted heuristics, numerous effort has been made to apply…

cs.NI2022★ 6 cited

AccMPEG: Optimizing Video Encoding for Video Analytics

Kuntai Du, Qizheng Zhang, Anton Arapin +3

With more videos being recorded by edge sensors (cameras) and analyzed by computer-vision deep neural nets (DNNs), a new breed of video streaming systems has emerged, with the goal…

cs.PF2021★ 11 cited

Towards Performance Clarity of Edge Video Analytics

Zhujun Xiao, Zhengxu Xia, Haitao Zheng +2

Edge video analytics is becoming the solution to many safety and management tasks. Its wide deployment, however, must first address the tension between inference accuracy and resou…

cs.DC2020★ 21 cited

Ekya: Continuous Learning of Video Analytics Models on Edge Compute Servers

Romil Bhardwaj, Zhengxu Xia, Ganesh Ananthanarayanan +6

Video analytics applications use edge compute servers for the analytics of the videos (for bandwidth and privacy). Compressed models that are deployed on the edge servers for infer…

cs.CV2020

Learning Model-Blind Temporal Denoisers without Ground Truths

Yanghao Li, Bichuan Guo, Jiangtao Wen +3

Denoisers trained with synthetic data often fail to cope with the diversity of unknown noises, giving way to methods that can adapt to existing noise without knowing its ground tru…