Search Results for author: Shaojie Wang

Found 6 papers, 1 papers with code

PROVES: Establishing Image Provenance using Semantic Signatures

1 code implementation21 Oct 2021 Mingyang Xie, Manav Kulshrestha, Shaojie Wang, Jinghan Yang, Ayan Chakrabarti, Ning Zhang, Yevgeniy Vorobeychik

Modern AI tools, such as generative adversarial networks, have transformed our ability to create and modify visual data with photorealistic results.

Face Verification

Adversarial Robustness of Deep Sensor Fusion Models

no code implementations23 Jun 2020 Shaojie Wang, Tong Wu, Ayan Chakrabarti, Yevgeniy Vorobeychik

First, we find that the fusion model is usually both more accurate, and more robust against single-source attacks than single-sensor deep neural networks.

2D object detection Adversarial Robustness +4

Improve CAM with Auto-adapted Segmentation and Co-supervised Augmentation

no code implementations17 Nov 2019 Ziyi Kou, Guofeng Cui, Shaojie Wang, Wentian Zhao, Chenliang Xu

In this paper, we propose a confidence segmentation (ConfSeg) module that builds confidence score for each pixel in CAM without introducing additional hyper-parameters.

Weakly-Supervised Object Localization

Weakly Supervised Localization Using Background Images

no code implementations9 Sep 2019 Ziyi Kou, Wentian Zhao, Guofeng Cui, Shaojie Wang

Weakly Supervised Object Localization (WSOL) methodsusually rely on fully convolutional networks in order to ob-tain class activation maps(CAMs) of targeted labels.

Weakly-Supervised Object Localization

GAN-EM: GAN based EM learning framework

no code implementations2 Dec 2018 Wentian Zhao, Shaojie Wang, Zhihuai Xie, Jing Shi, Chenliang Xu

To overcome such limitation, we propose a GAN based EM learning framework that can maximize the likelihood of images and estimate the latent variables with only the constraint of L-Lipschitz continuity.

Dimensionality Reduction General Classification +1

How to Make a BLT Sandwich? Learning to Reason towards Understanding Web Instructional Videos

no code implementations2 Dec 2018 Shaojie Wang, Wentian Zhao, Ziyi Kou, Chenliang Xu

Furthermore, we study multiple modalities including description and transcripts for the purpose of boosting video understanding.

Logical Reasoning Question Answering +1

Cannot find the paper you are looking for? You can Submit a new open access paper.