activity
20132024
most citedZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models

1.8k citations · 3.6k across the 86 of their papers we have counts for

collaborators
Showing cs.CVShow all

20 papers · 1 filter

cs.CV2023★ 1 cited

Structured Video-Language Modeling with Temporal Grouping and Spatial Grounding

Yuanhao Xiong, Long Zhao, Boqing Gong +5

Existing video-language pre-training methods primarily focus on instance-level alignment between video clips and captions via global contrastive learning but neglect rich fine-grai…

cs.CV2022★ 14 cited

Scaling Up Dataset Distillation to ImageNet-1K with Constant Memory

Justin Cui, Ruochen Wang, Si Si +1

Dataset Distillation is a newly emerging area that aims to distill large datasets into much smaller and highly informative synthetic ones to accelerate training and reduce storage.…

cs.CV2022★ 10 cited

Generalizing Few-Shot NAS with Gradient Matching

Shoukang Hu, Ruochen Wang, Lanqing Hong +3

Efficient performance estimation of architectures drawn from large search spaces is essential to Neural Architecture Search. One-Shot methods tackle this challenge by training one…

cs.CV2021

Temporal Shuffling for Defending Deep Action Recognition Models against Adversarial Attacks

Jaehui Hwang, Huan Zhang, Jun-Ho Choi +2

Recently, video-based action recognition methods using convolutional neural networks (CNNs) achieve remarkable recognition performance. However, there is still lack of understandin…

cs.CV2021★ 8 cited

Can Vision Transformers Perform Convolution?

Shanda Li, Xiangning Chen, Di He +1

Several recent studies have demonstrated that attention-based networks, such as Vision Transformer (ViT), can outperform Convolutional Neural Networks (CNNs) on several computer vi…

cs.CV2021

Adversarial Attack across Datasets

Yunxiao Qin, Yuanhao Xiong, Jinfeng Yi +2

Existing transfer attack methods commonly assume that the attacker knows the training set (e.g., the label set, the input size) of the black-box victim models, which is usually unr…