Search Results for author: Yujia Liu

Found 20 papers, 8 papers with code

Defense Against Adversarial Attacks on No-Reference Image Quality Models with Gradient Norm Regularization

1 code implementation18 Mar 2024 Yujia Liu, Chenxi Yang, Dingquan Li, Jianhao Ding, Tingting Jiang

To be specific, we present theoretical evidence showing that the magnitude of score changes is related to the $\ell_1$ norm of the model's gradient with respect to the input image.

Adversarial Robustness No-Reference Image Quality Assessment +1

Point2Building: Reconstructing Buildings from Airborne LiDAR Point Clouds

no code implementations4 Mar 2024 Yujia Liu, Anton Obukhov, Jan Dirk Wegner, Konrad Schindler

What makes 3D building reconstruction from airborne LiDAR hard is the large diversity of building designs and especially roof shapes, the low and varying point density across the scene, and the often incomplete coverage of building facades due to occlusions by vegetation or to the viewing angle of the sensor.

LM-HT SNN: Enhancing the Performance of SNN to ANN Counterpart through Learnable Multi-hierarchical Threshold Model

no code implementations1 Feb 2024 Zecheng Hao, Xinyu Shi, Zhiyu Pan, Yujia Liu, Zhaofei Yu, Tiejun Huang

Compared to traditional Artificial Neural Network (ANN), Spiking Neural Network (SNN) has garnered widespread academic interest for its intrinsic ability to transmit information in a more biological-inspired and energy-efficient manner.

Exploring Vulnerabilities of No-Reference Image Quality Assessment Models: A Query-Based Black-Box Method

no code implementations10 Jan 2024 Chenxi Yang, Yujia Liu, Dingquan Li, Tingting Jiang

Ensuring the robustness of NR-IQA methods is vital for reliable comparisons of different image processing techniques and consistent user experiences in recommendations.

No-Reference Image Quality Assessment NR-IQA

Point2CAD: Reverse Engineering CAD Models from 3D Point Clouds

no code implementations7 Dec 2023 Yujia Liu, Anton Obukhov, Jan Dirk Wegner, Konrad Schindler

Computer-Aided Design (CAD) model reconstruction from point clouds is an important problem at the intersection of computer vision, graphics, and machine learning; it saves the designer significant time when iterating on in-the-wild objects.

CAD Reconstruction Semantic Segmentation

MindShift: Leveraging Large Language Models for Mental-States-Based Problematic Smartphone Use Intervention

no code implementations28 Sep 2023 Ruolan Wu, Chun Yu, Xiaole Pan, Yujia Liu, Ningning Zhang, Yue Fu, YuHan Wang, Zhi Zheng, Li Chen, Qiaolei Jiang, Xuhai Xu, Yuanchun Shi

We first conducted a Wizard-of-Oz study (N=12) and an interview study (N=10) to summarize the mental states behind problematic smartphone use: boredom, stress, and inertia.

Persuasion Strategies

Learning Personalized Page Content Ranking Using Customer Representation

no code implementations9 May 2023 Xin Shen, Yan Zhao, Sujan Perera, Yujia Liu, Jinyun Yan, Mitchell Goodman

We propose a deep learning based bandit algorithm that incorporates historical shopping behavior, customer latent shopping goals, and the correlation between customers and content categories.

BigSmall: Efficient Multi-Task Learning for Disparate Spatial and Temporal Physiological Measurements

2 code implementations21 Mar 2023 Girish Narayanswamy, Yujia Liu, Yuzhe Yang, Chengqian Ma, Xin Liu, Daniel McDuff, Shwetak Patel

As an example, perception occurs at different scales both spatially and temporally, suggesting that the extraction of salient visual information may be made more effective by paying attention to specific features at varying scales.

Multi-Task Learning

PC2WF: 3D Wireframe Reconstruction from Raw Point Clouds

1 code implementation ICLR 2021 Yujia Liu, Stefano D'Aronco, Konrad Schindler, Jan Dirk Wegner

Next, the corners are linked with an exhaustive set of candidate edges, which is again pruned to obtain the final wireframe.

3D Wireframe Reconstruction

Reconfigurable Design for Omni-adaptive Grasp Learning

2 code implementations29 Feb 2020 Fang Wan, Haokun Wang, Jiyuan Wu, Yujia Liu, Sheng Ge, Chaoyang Song

Such reconfigurable design with these omni-adaptive fingers enables us to systematically investigate the optimal arrangement of the fingers towards robust grasping.

Rigid-Soft Interactive Learning for Robust Grasping

2 code implementations29 Feb 2020 Linhan Yang, Fang Wan, Haokun Wang, Xiaobo Liu, Yujia Liu, Jia Pan, Chaoyang Song

We use soft, stuffed toys for training, instead of everyday objects, to reduce the integration complexity and computational burden and exploit such rigid-soft interaction by changing the gripper fingers to the soft ones when dealing with rigid, daily-life items such as the Yale-CMU-Berkeley (YCB) objects.

Small Data Image Classification

Scalable Tactile Sensing for an Omni-adaptive Soft Robot Finger

2 code implementations29 Feb 2020 Zeyi Yang, Sheng Ge, Fang Wan, Yujia Liu, Chaoyang Song

Robotic fingers made of soft material and compliant structures usually lead to superior adaptation when interacting with the unstructured physical environment.

LabelFool: A Trick in the Label Space

no code implementations25 Sep 2019 Yujia Liu, Tingting Jiang, Ming Jiang

It is widely known that well-designed perturbations can cause state-of-the-art machine learning classifiers to mis-label an image, with sufficiently small perturbations that are imperceptible to the human eyes.

A geometry-inspired decision-based attack

1 code implementation ICCV 2019 Yujia Liu, Seyed-Mohsen Moosavi-Dezfooli, Pascal Frossard

The qFool method can drastically reduce the number of queries compared to previous decision-based attacks while reaching the same quality of adversarial examples.

General Classification Image Classification

Detection based Defense against Adversarial Examples from the Steganalysis Point of View

no code implementations CVPR 2019 Jiayang Liu, Weiming Zhang, Yiwei Zhang, Dongdong Hou, Yujia Liu, Hongyue Zha, Nenghai Yu

Moreover, secondary adversarial attacks cannot be directly performed to our method because our method is not based on a neural network but based on high-dimensional artificial features and FLD (Fisher Linear Discriminant) ensemble.

Steganalysis

Enhanced Attacks on Defensively Distilled Deep Neural Networks

no code implementations16 Nov 2017 Yujia Liu, Weiming Zhang, Shaohua Li, Nenghai Yu

In this paper, we first propose the epsilon-neighborhood attack, which can fool the defensively distilled networks with 100% success rate in the white-box setting, and it is fast to generate adversarial examples with good visual quality.

Face Recognition General Classification +2

Cannot find the paper you are looking for? You can Submit a new open access paper.