Search Results for author:
Found 24 papers, 9 papers with code
HW-TSC’s Participation at WMT 2021 Quality Estimation Shared Task
This paper presents our work in WMT 2021 Quality Estimation (QE) Shared Task.
Robust Stable Spiking Neural Networks
We present that membrane potential perturbation dynamics can reliably convey the intensity of perturbation.
Enhancing Adversarial Robustness in SNNs with Sparse Gradients
In this paper, we propose a novel approach to enhance the robustness of SNNs through gradient sparsity regularization.
Beyond Score Changes: Adversarial Attack on No-Reference Image Quality Assessment from Two Perspectives
Meanwhile, it is important to note that the correlation, like ranking correlation, plays a significant role in NR-IQA tasks.
Defense Against Adversarial Attacks on No-Reference Image Quality Models with Gradient Norm Regularization
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.
Point2Building: Reconstructing Buildings from Airborne LiDAR Point Clouds
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.
Demographic Bias of Expert-Level Vision-Language Foundation Models in Medical Imaging
Such demographic biases present over a wide range of pathologies and demographic attributes.
LM-HT SNN: Enhancing the Performance of SNN to ANN Counterpart through Learnable Multi-hierarchical Threshold Model
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
Ensuring the robustness of NR-IQA methods is vital for reliable comparisons of different image processing techniques and consistent user experiences in recommendations.
Towards HDR and HFR Video from Rolling-Mixed-Bit Spikings
However reconstructing HDR videos in high-speed conditions using single-bit spikings presents challenges due to the limited bit depth.
Point2CAD: Reverse Engineering CAD Models from 3D Point Clouds
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.
MindShift: Leveraging Large Language Models for Mental-States-Based Problematic Smartphone Use Intervention
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.
Learning Personalized Page Content Ranking Using Customer Representation
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
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.
The HW-TSC's Offline Speech Translation Systems for IWSLT 2021 Evaluation
This paper describes our work in participation of the IWSLT-2021 offline speech translation task.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+5
PC2WF: 3D Wireframe Reconstruction from Raw Point Clouds
Next, the corners are linked with an exhaustive set of candidate edges, which is again pruned to obtain the final wireframe.
Rigid-Soft Interactive Learning for Robust Grasping
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.
Reconfigurable Design for Omni-adaptive Grasp Learning
Such reconfigurable design with these omni-adaptive fingers enables us to systematically investigate the optimal arrangement of the fingers towards robust grasping.
Scalable Tactile Sensing for an Omni-adaptive Soft Robot Finger
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
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
The qFool method can drastically reduce the number of queries compared to previous decision-based attacks while reaching the same quality of adversarial examples.
Detection based Defense against Adversarial Examples from the Steganalysis Point of View
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.
Enhanced Attacks on Defensively Distilled Deep Neural Networks
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.
Clustering via Content-Augmented Stochastic Blockmodels
Much of the data being created on the web contains interactions between users and items.
