activity
20182022
most citedSharp Multiple Instance Learning for DeepFake Video Detection

154 citations · 338 across the 13 of their papers we have counts for

collaborators
Showing cs.CVShow all

18 papers · 1 filter

cs.CV202217 cited

IR-GAN: Image Manipulation with Linguistic Instruction by Increment Reasoning

Zhenhuan Liu, Jincan Deng, Liang Li +4

Conditional image generation is an active research topic including text2image and image translation. Recently image manipulation with linguistic instruction brings new challenges o…

cs.CV20215 cited

Greedy Gradient Ensemble for Robust Visual Question Answering

Xinzhe Han, Shuhui Wang, Chi Su +2

Language bias is a critical issue in Visual Question Answering (VQA), where models often exploit dataset biases for the final decision without considering the image information. As…

cs.CV202118 cited

Fast Batch Nuclear-norm Maximization and Minimization for Robust Domain Adaptation

Shuhao Cui, Shuhui Wang, Junbao Zhuo +3

Due to the domain discrepancy in visual domain adaptation, the performance of source model degrades when bumping into the high data density near decision boundary in target domain.…

cs.CV20213 cited

Learning Invariant Representation with Consistency and Diversity for Semi-supervised Source Hypothesis Transfer

Xiaodong Wang, Junbao Zhuo, Shuhao Cui +1

Semi-supervised domain adaptation (SSDA) aims to solve tasks in target domain by utilizing transferable information learned from the available source domain and a few labeled targe…

cs.CV20213 cited

QAIR: Practical Query-efficient Black-Box Attacks for Image Retrieval

Xiaodan Li, Jinfeng Li, Yuefeng Chen +5

We study the query-based attack against image retrieval to evaluate its robustness against adversarial examples under the black-box setting, where the adversary only has query acce…

cs.CV20209 cited

Heuristic Domain Adaptation

Shuhao Cui, Xuan Jin, Shuhui Wang +2

In visual domain adaptation (DA), separating the domain-specific characteristics from the domain-invariant representations is an ill-posed problem. Existing methods apply different…