Picture for Mingyu Zhang

Mingyu Zhang

Take A Step Back: Rethinking the Two Stages in Visual Reasoning

Add code
Jul 29, 2024
Viaarxiv icon

STAR-GNN: Spatial-Temporal Video Representation for Content-based Retrieval

Add code
Aug 15, 2022
Figure 1 for STAR-GNN: Spatial-Temporal Video Representation for Content-based Retrieval
Figure 2 for STAR-GNN: Spatial-Temporal Video Representation for Content-based Retrieval
Figure 3 for STAR-GNN: Spatial-Temporal Video Representation for Content-based Retrieval
Figure 4 for STAR-GNN: Spatial-Temporal Video Representation for Content-based Retrieval
Viaarxiv icon

InvisibiliTee: Angle-agnostic Cloaking from Person-Tracking Systems with a Tee

Add code
Aug 15, 2022
Figure 1 for InvisibiliTee: Angle-agnostic Cloaking from Person-Tracking Systems with a Tee
Figure 2 for InvisibiliTee: Angle-agnostic Cloaking from Person-Tracking Systems with a Tee
Figure 3 for InvisibiliTee: Angle-agnostic Cloaking from Person-Tracking Systems with a Tee
Figure 4 for InvisibiliTee: Angle-agnostic Cloaking from Person-Tracking Systems with a Tee
Viaarxiv icon

Modality-Balanced Embedding for Video Retrieval

Add code
Apr 18, 2022
Figure 1 for Modality-Balanced Embedding for Video Retrieval
Figure 2 for Modality-Balanced Embedding for Video Retrieval
Figure 3 for Modality-Balanced Embedding for Video Retrieval
Viaarxiv icon

Unsupervised Adversarial Attacks on Deep Feature-based Retrieval with GAN

Add code
Jul 12, 2019
Figure 1 for Unsupervised Adversarial Attacks on Deep Feature-based Retrieval with GAN
Figure 2 for Unsupervised Adversarial Attacks on Deep Feature-based Retrieval with GAN
Figure 3 for Unsupervised Adversarial Attacks on Deep Feature-based Retrieval with GAN
Figure 4 for Unsupervised Adversarial Attacks on Deep Feature-based Retrieval with GAN
Viaarxiv icon