activity
20172022
most citedMixup-Transformer: Dynamic Data Augmentation for NLP Tasks

23 citations · 52 across the 8 of their papers we have counts for

collaborators

9 papers

cs.LG20223 cited

Spectral Adversarial Training for Robust Graph Neural Network

Jintang Li, Jiaying Peng, Liang Chen +3

Recent studies demonstrate that Graph Neural Networks (GNNs) are vulnerable to slight but adversarially designed perturbations, known as adversarial examples. To address this issue…

cs.CL20223 cited

Multifaceted Improvements for Conversational Open-Domain Question Answering

Tingting Liang, Yixuan Jiang, Congying Xia +3

Open-domain question answering (OpenQA) is an important branch of textual QA which discovers answers for the given questions based on a large number of unstructured documents. Effe…

cs.CV20215 cited

OPANAS: One-Shot Path Aggregation Network Architecture Search for Object Detection

Tingting Liang, Yongtao Wang, Zhi Tang +2

Recently, neural architecture search (NAS) has been exploited to design feature pyramid networks (FPNs) and achieved promising results for visual object detection. Encouraged by th…

cs.CL202023 cited

Mixup-Transformer: Dynamic Data Augmentation for NLP Tasks

Lichao Sun, Congying Xia, Wenpeng Yin +3

Mixup is the latest data augmentation technique that linearly interpolates input examples and the corresponding labels. It has shown strong effectiveness in image classification by…

cs.IR20202 cited

Joint Training Capsule Network for Cold Start Recommendation

Tingting Liang, Congying Xia, Yuyu Yin +1

This paper proposes a novel neural network, joint training capsule network (JTCN), for the cold start recommendation task. We propose to mimic the high-level user preference other…

cs.CV20201 cited

MixTConv: Mixed Temporal Convolutional Kernels for Efficient Action Recogntion

Kaiyu Shan, Yongtao Wang, Zhuoying Wang +4

To efficiently extract spatiotemporal features of video for action recognition, most state-of-the-art methods integrate 1D temporal convolution into a conventional 2D CNN backbone.…