activity
20182020
most citedDeVLBert: Learning Deconfounded Visio-Linguistic Representations

64 citations · 160 across the 12 of their papers we have counts for

collaborators

14 papers

cs.CV2020

MGD-GAN: Text-to-Pedestrian generation through Multi-Grained Discrimination

Shengyu Zhang, Donghui Wang, Zhou Zhao +3

In this paper, we investigate the problem of text-to-pedestrian synthesis, which has many potential applications in art, design, and video surveillance. Existing methods for text-t…

cs.CV202064 cited

DeVLBert: Learning Deconfounded Visio-Linguistic Representations

Shengyu Zhang, Tan Jiang, Tan Wang +6

In this paper, we propose to investigate the problem of out-of-domain visio-linguistic pretraining, where the pretraining data distribution differs from that of downstream data on…

cs.CL20205 cited

Improving Robustness and Generality of NLP Models Using Disentangled Representations

Jiawei Wu, Xiaoya Li, Xiang Ao +3

Supervised neural networks, which first map an input to a single representation , and then map to the output label , have achieved remarkable success in a wide range…

cs.CV20203 cited

Learning a Domain Classifier Bank for Unsupervised Adaptive Object Detection

Sanli Tang, Zhanzhan Cheng, Shiliang Pu +3

In real applications, object detectors based on deep networks still face challenges of the large domain gap between the labeled training data and unlabeled testing data. To reduce…

cs.CV202022 cited

Rethinking Localization Map: Towards Accurate Object Perception with Self-Enhancement Maps

Xiaolin Zhang, Yunchao Wei, Yi Yang +1

Recently, remarkable progress has been made in weakly supervised object localization (WSOL) to promote object localization maps. The common practice of evaluating these maps applie…

cs.SI202034 cited

Analyzing COVID-19 on Online Social Media: Trends, Sentiments and Emotions

Xiaoya Li, Mingxin Zhou, Jiawei Wu +3

At the time of writing, the ongoing pandemic of coronavirus disease (COVID-19) has caused severe impacts on society, economy and people's daily lives. People constantly express the…