Search Results for author:
Found 25 papers, 8 papers with code
Occlusion-Aware Siamese Network for Human Pose Estimation
To overcome the defects caused by the erasing operation, we perform feature reconstruction to recover the information destroyed by occlusion and details lost in cleaning procedure.
Blended Grammar Network for Human Parsing
Although human parsing has made great progress, it still faces a challenge, i. e., how to extract the whole foreground from similar or cluttered scenes effectively.
FiLo: Zero-Shot Anomaly Detection by Fine-Grained Description and High-Quality Localization
Zero-shot anomaly detection (ZSAD) methods entail detecting anomalies directly without access to any known normal or abnormal samples within the target item categories.
Optimization of Prompt Learning via Multi-Knowledge Representation for Vision-Language Models
This limitation restricts the capabilities of pretrained VLMs and can result in incorrect predictions in downstream tasks.
DisDet: Exploring Detectability of Backdoor Attack on Diffusion Models
In this paper, for the first time, we systematically explore the detectability of the poisoned noise input for the backdoored diffusion models, an important performance metric yet little explored in the existing works.
Adaptive Quantization for Key Generation in Low-Power Wide-Area Networks
Physical layer key generation based on reciprocal and random wireless channels has been an attractive solution for securing resource-constrained low-power wide-area networks (LPWANs).
AnomalyGPT: Detecting Industrial Anomalies Using Large Vision-Language Models
Large Vision-Language Models (LVLMs) such as MiniGPT-4 and LLaVA have demonstrated the capability of understanding images and achieved remarkable performance in various visual tasks.
Benchmarking and Analyzing Robust Point Cloud Recognition: Bag of Tricks for Defending Adversarial Examples
In this paper, we first establish a comprehensive, and rigorous point cloud adversarial robustness benchmark to evaluate adversarial robustness, which can provide a detailed understanding of the effects of the defense and attack methods.
Privacy-Utility Balanced Voice De-Identification Using Adversarial Examples
In this paper, we propose a voice de-identification system, which uses adversarial examples to balance the privacy and utility of voice services.
View-Disentangled Transformer for Brain Lesion Detection
Deep neural networks (DNNs) have been widely adopted in brain lesion detection and segmentation.
RIBAC: Towards Robust and Imperceptible Backdoor Attack against Compact DNN
Recently backdoor attack has become an emerging threat to the security of deep neural network (DNN) models.
UniVIP: A Unified Framework for Self-Supervised Visual Pre-training
Furthermore, our method can also exploit single-centric-object dataset such as ImageNet and outperforms BYOL by 2. 5% with the same pre-training epochs in linear probing, and surpass current self-supervised object detection methods on COCO dataset, demonstrating its universality and potential.
FewSense, Towards a Scalable and Cross-Domain Wi-Fi Sensing System Using Few-Shot Learning
When the system was applied in the target domain, few samples were used to fine-tune the feature extractor for domain adaptation.
C2AM Loss: Chasing a Better Decision Boundary for Long-Tail Object Detection
The decision boundary between any two categories is the angular bisector of their weight vectors.
Simultaneous Monitoring of Multiple People's Vital Sign Leveraging a Single Phased-MIMO Radar
Based on the designed TDM phased-MIMO radar, we develop a system to automatically localize multiple human subjects and estimate their vital signs.
Improving Multiple Object Tracking With Single Object Tracking
Despite considerable similarities between multiple object tracking (MOT) and single object tracking (SOT) tasks, modern MOT methods have not benefited from the development of SOT ones to achieve satisfactory performance.
Enabling Fast and Universal Audio Adversarial Attack Using Generative Model
These idealized assumptions, however, makes the existing audio adversarial attacks mostly impossible to be launched in a timely fashion in practice (e. g., playing unnoticeable adversarial perturbations along with user's streaming input).
Real-time, Universal, and Robust Adversarial Attacks Against Speaker Recognition Systems
As the popularity of voice user interface (VUI) exploded in recent years, speaker recognition system has emerged as an important medium of identifying a speaker in many security-required applications and services.
Spearphone: A Speech Privacy Exploit via Accelerometer-Sensed Reverberations from Smartphone Loudspeakers
In this paper, we build a speech privacy attack that exploits speech reverberations generated from a smartphone's inbuilt loudspeaker captured via a zero-permission motion sensor (accelerometer).
Cryptography and Security
Learning Feature Embeddings for Discriminant Model based Tracking
After observing that the features used in most online discriminatively trained trackers are not optimal, in this paper, we propose a novel and effective architecture to learn optimal feature embeddings for online discriminative tracking.
Recurrent Calibration Network for Irregular Text Recognition
In this paper, we propose a novel Recurrent Calibration Network (RCN) for irregular scene text recognition.
BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning
Datasets drive vision progress, yet existing driving datasets are impoverished in terms of visual content and supported tasks to study multitask learning for autonomous driving.
Ranked #5 on
Multiple Object Tracking
on BDD100K test
Reading Scene Text with Attention Convolutional Sequence Modeling
Reading text in the wild is a challenging task in the field of computer vision.
Fast Deep Matting for Portrait Animation on Mobile Phone
Finally, an automatic portrait animation system based on fast deep matting is built on mobile devices, which does not need any interaction and can realize real-time matting with 15 fps.
Joint Background Reconstruction and Foreground Segmentation via A Two-stage Convolutional Neural Network
In the first stage, a convolutional encoder-decoder sub-network is employed to reconstruct the background images and encode rich prior knowledge of background scenes.
