activity
20192022
most citedPairwise Interactive Graph Attention Network for Context-Aware Recommendation

5 citations · 14 across the 9 of their papers we have counts for

collaborators

11 papers

cs.CV2022

AdvMask: A Sparse Adversarial Attack Based Data Augmentation Method for Image Classification

Suorong Yang, Jinqiao Li, Jian Zhao +1

Data augmentation is a widely used technique for enhancing the generalization ability of convolutional neural networks (CNNs) in image classification tasks. Occlusion is a critical…

cs.CV2022

AugRmixAT: A Data Processing and Training Method for Improving Multiple Robustness and Generalization Performance

Xiaoliang Liu, Furao Shen, Jian Zhao +1

Deep neural networks are powerful, but they also have shortcomings such as their sensitivity to adversarial examples, noise, blur, occlusion, etc. Moreover, ensuring the reliabilit…

cs.CV2022★ 1 cited

Review Neural Networks about Image Transformation Based on IGC Learning Framework with Annotated Information

Yuanjie Yan, Suorong Yang, Yan Wang +2

Image transformation, a class of vision and graphics problems whose goal is to learn the mapping between an input image and an output image, develops rapidly in the context of deep…

cs.CL2021

SASICM A Multi-Task Benchmark For Subtext Recognition

Hua Yan, Feng Han, Junyi An +3

Subtext is a kind of deep semantics which can be acquired after one or more rounds of expression transformation. As a popular way of expressing one's intentions, it is well worth s…

cs.CV2021

Faster and Simpler Siamese Network for Single Object Tracking

Shaokui Jiang, Baile Xu, Jian Zhao +1

Single object tracking (SOT) is currently one of the most important tasks in computer vision. With the development of the deep network and the release for a series of large scale d…

cs.CV2021★ 1 cited

IC Networks: Remodeling the Basic Unit for Convolutional Neural Networks

Junyi An, Fengshan Liu, Jian Zhao +1

Convolutional neural network (CNN) is a class of artificial neural networks widely used in computer vision tasks. Most CNNs achieve excellent performance by stacking certain types…