171 citations · 397 across the 13 of their papers we have counts for
14 papers
Understanding NVIDIA Grace-Blackwell Unified Memory Through Placement-Controlled Microbenchmarks
Nathan Graddon, Aaron Jarmusch, Sunita Chandrasekaran
NVIDIA Grace--Blackwell systems make CPU--GPU memory increasingly unified at the programming level, but unified addressability does not make the memory system uniform. A CUDA manag…
CausalChapter: Improving Long-Video Chaptering with Interventional Dependency Modeling
Xinran Duan, Guozhang Li, Yaoyao Zhong +3
Long-form instructional videos require automatic chaptering to support browsing, navigation, and knowledge access. Recent long-context language models can perform chaptering from t…
SketchJudge: A Diagnostic Benchmark for Grading Hand-drawn Diagrams with Multimodal Large Language Models
Yuhang Su, Mei Wang, Yaoyao Zhong +4
While Multimodal Large Language Models (MLLMs) have achieved remarkable progress in visual understanding, they often struggle when faced with the unstructured and ambiguous nature…
SMART: Self-Generating and Self-Validating Multi-Dimensional Assessment for LLMs' Mathematical Problem Solving
Yujie Hou, Mei Wang, Yaoyao Zhong +3
Large Language Models (LLMs) have achieved remarkable performance across a wide range of mathematical benchmarks. However, concerns remain as to whether these successes reflect gen…
Enhancing Generalization of Invisible Facial Privacy Cloak via Gradient Accumulation
Xuannan Liu, Yaoyao Zhong, Weihong Deng +4
The blooming of social media and face recognition (FR) systems has increased people's concern about privacy and security. A new type of adversarial privacy cloak (class-universal)…
AdvCloak: Customized Adversarial Cloak for Privacy Protection
Xuannan Liu, Yaoyao Zhong, Xing Cui +3
With extensive face images being shared on social media, there has been a notable escalation in privacy concerns. In this paper, we propose AdvCloak, an innovative framework for pr…
Enhancing Generalization of Universal Adversarial Perturbation through Gradient Aggregation
Xuannan Liu, Yaoyao Zhong, Yuhang Zhang +2
Deep neural networks are vulnerable to universal adversarial perturbation (UAP), an instance-agnostic perturbation capable of fooling the target model for most samples. Compared to…
SFace: Sigmoid-Constrained Hypersphere Loss for Robust Face Recognition
Yaoyao Zhong, Weihong Deng, Jiani Hu +3
Deep face recognition has achieved great success due to large-scale training databases and rapidly developing loss functions. The existing algorithms devote to realizing an ideal i…
OPOM: Customized Invisible Cloak towards Face Privacy Protection
Yaoyao Zhong, Weihong Deng
While convenient in daily life, face recognition technologies also raise privacy concerns for regular users on the social media since they could be used to analyze face images and…
Video Question Answering: Datasets, Algorithms and Challenges
Yaoyao Zhong, Junbin Xiao, Wei Ji +3
Video Question Answering (VideoQA) aims to answer natural language questions according to the given videos. It has earned increasing attention with recent research trends in joint…
MLFW: A Database for Face Recognition on Masked Faces
Chengrui Wang, Han Fang, Yaoyao Zhong +1
As more and more people begin to wear masks due to current COVID-19 pandemic, existing face recognition systems may encounter severe performance degradation when recognizing masked…
Face Transformer for Recognition
Yaoyao Zhong, Weihong Deng
Recently there has been a growing interest in Transformer not only in NLP but also in computer vision. We wonder if transformer can be used in face recognition and whether it is be…
Towards Transferable Adversarial Attack against Deep Face Recognition
Yaoyao Zhong, Weihong Deng
Face recognition has achieved great success in the last five years due to the development of deep learning methods. However, deep convolutional neural networks (DCNNs) have been fo…
Adversarial Learning with Margin-based Triplet Embedding Regularization
Yaoyao Zhong, Weihong Deng
The Deep neural networks (DNNs) have achieved great success on a variety of computer vision tasks, however, they are highly vulnerable to adversarial attacks. To address this probl…