7 citations · 17 across the 9 of their papers we have counts for
5 papers · 1 filter
Privacy Preserving Visual Question Answering
Cristian-Paul Bara, Qing Ping, Abhinav Mathur +3
We introduce a novel privacy-preserving methodology for performing Visual Question Answering on the edge. Our method constructs a symbolic representation of the visual scene, using…
A Thousand Words Are Worth More Than a Picture: Natural Language-Centric Outside-Knowledge Visual Question Answering
Feng Gao, Qing Ping, Govind Thattai +3
Outside-knowledge visual question answering (OK-VQA) requires the agent to comprehend the image, make use of relevant knowledge from the entire web, and digest all the information…
Learning Better Visual Dialog Agents with Pretrained Visual-Linguistic Representation
Tao Tu, Qing Ping, Govind Thattai +2
GuessWhat?! is a two-player visual dialog guessing game where player A asks a sequence of yes/no questions (Questioner) and makes a final guess (Guesser) about a target object in a…
Adversarial Code Learning for Image Generation
Jiangbo Yuan, Bing Wu, Wanying Ding +2
We introduce the "adversarial code learning" (ACL) module that improves overall image generation performance to several types of deep models. Instead of performing a posterior dist…
Fashion-AttGAN: Attribute-Aware Fashion Editing with Multi-Objective GAN
Qing Ping, Bing Wu, Wanying Ding +1
In this paper, we introduce attribute-aware fashion-editing, a novel task, to the fashion domain. We re-define the overall objectives in AttGAN and propose the Fashion-AttGAN model…