activity
20172023
most citedWaterGAN: Unsupervised Generative Network to Enable Real-time Color Correction of Monocular Underwater Images

397 citations · 695 across the 41 of their papers we have counts for

collaborators
Showing 2020Show all

12 papers · 1 filter

cs.CV2020

Skeleton-based Approaches based on Machine Vision: A Survey

Jie Li, Binglin Li, Min Gao

Recently, skeleton-based approaches have achieved rapid progress on the basis of great success in skeleton representation. Plenty of researches focus on solving specific problems a…

cs.NI2020★ 4 cited

Anatomy of Multipath BGP Deployment in a Large ISP Network

Jie Li, Vasileios Giotsas, Shi Zhou

Multipath routing is useful for networks to achieve load sharing among multiple routing paths. Multipath BGP (MBGP) is a technique to realize inter-domain multipath routing by enab…

cs.CV2020

Probabilistic 3D Multi-Modal, Multi-Object Tracking for Autonomous Driving

Hsu-kuang Chiu, Jie Li, Rares Ambrus +1

Multi-object tracking is an important ability for an autonomous vehicle to safely navigate a traffic scene. Current state-of-the-art follows the tracking-by-detection paradigm wher…

cs.CV2020

Association: Remind Your GAN not to Forget

Yi Gu, Jie Li, Yuting Gao +5

Neural networks are susceptible to catastrophic forgetting. They fail to preserve previously acquired knowledge when adapting to new tasks. Inspired by human associative memory sys…

cs.LG2020★ 1 cited

A Framework of Randomized Selection Based Certified Defenses Against Data Poisoning Attacks

Ruoxin Chen, Jie Li, Chentao Wu +2

Neural network classifiers are vulnerable to data poisoning attacks, as attackers can degrade or even manipulate their predictions thorough poisoning only a few training samples. H…

cs.CV2020★ 67 cited

Interpretable Detail-Fidelity Attention Network for Single Image Super-Resolution

Yuanfei Huang, Jie Li, Xinbo Gao +2

Benefiting from the strong capabilities of deep CNNs for feature representation and nonlinear mapping, deep-learning-based methods have achieved excellent performance in single ima…

cs.CV2020★ 2 cited

A Density-Aware PointRCNN for 3D Object Detection in Point Clouds

Jie Li, Yu Hu

We present an improved version of PointRCNN for 3D object detection, in which a multi-branch backbone network is adopted to handle the non-uniform density of point clouds. An uncer…

cs.CV2020

PillarFlow: End-to-end Birds-eye-view Flow Estimation for Autonomous Driving

Kuan-Hui Lee, Matthew Kliemann, Adrien Gaidon +4

In autonomous driving, accurately estimating the state of surrounding obstacles is critical for safe and robust path planning. However, this perception task is difficult, particula…

eess.SY2020

Reinforcement Solver for H-infinity Filter with Bounded Noise

Jie Li, Shengbo Eben Li, Kaiming Tang +2

H-infinity filter has been widely applied in engineering field, but copping with bounded noise is still an open problem and difficult to solve. This paper considers the H-infinity…

cs.CV2020★ 15 cited

Align Deep Features for Oriented Object Detection

Jiaming Han, Jian Ding, Jie Li +1

The past decade has witnessed significant progress on detecting objects in aerial images that are often distributed with large scale variations and arbitrary orientations. However…

eess.SY2020★ 1 cited

Ternary Policy Iteration Algorithm for Nonlinear Robust Control

Jie Li, Shengbo Eben Li, Yang Guan +3

The uncertainties in plant dynamics remain a challenge for nonlinear control problems. This paper develops a ternary policy iteration (TPI) algorithm for solving nonlinear robust c…

cs.CV2020★ 3 cited

Weakly Supervised Temporal Action Localization with Segment-Level Labels

Xinpeng Ding, Nannan Wang, Xinbo Gao +3

Temporal action localization presents a trade-off between test performance and annotation-time cost. Fully supervised methods achieve good performance with time-consuming boundary…