203 citations · 267 across the 21 of their papers we have counts for
8 papers · 1 filter
Minimum Latency Deep Online Video Stabilization
Zhuofan Zhang, Zhen Liu, Ping Tan +2
We present a novel camera path optimization framework for the task of online video stabilization. Typically, a stabilization pipeline consists of three steps: motion estimating, pa…
BESS: Balanced Entity Sampling and Sharing for Large-Scale Knowledge Graph Completion
Alberto Cattaneo, Daniel Justus, Harry Mellor +7
We present the award-winning submission to the WikiKG90Mv2 track of OGB-LSC@NeurIPS 2022. The task is link-prediction on the large-scale knowledge graph WikiKG90Mv2, consisting of…
SML:Enhance the Network Smoothness with Skip Meta Logit for CTR Prediction
Wenlong Deng, Lang Lang, Zhen Liu +1
In light of the smoothness property brought by skip connections in ResNet, this paper proposed the Skip Logit to introduce the skip connection mechanism that fits arbitrary DNN dim…
Enhanced Current Density and Asymmetry of Metal-Insulator-Metal Diodes Based on the Self-Assembly of Pt Nanoparticles for Optical Rectennas
Zhen Liu, Shunsuke Abe, Makoto Shimizu +1
Optical rectennas consist of nano-antennas and nano-scale rectifying diodes, providing extensive prospects for thermal radiation energy harvesting applications. To achieve this, hi…
Ghost-free High Dynamic Range Imaging with Context-aware Transformer
Zhen Liu, Yinglong Wang, Bing Zeng +1
High dynamic range (HDR) deghosting algorithms aim to generate ghost-free HDR images with realistic details. Restricted by the locality of the receptive field, existing CNN-based m…
MUDGUARD: Taming Malicious Majorities in Federated Learning using Privacy-Preserving Byzantine-Robust Clustering
Rui Wang, Xingkai Wang, Huanhuan Chen +4
Byzantine-robust Federated Learning (FL) aims to counter malicious clients and train an accurate global model while maintaining an extremely low attack success rate. Most existing…