no code implementations • 28 Feb 2024 • Andrei Cozma, Landon Harris, Hairong Qi, Ping Ji, Wenpeng Guo, Song Yuan
This paper introduces a robust approach for automated defect detection in tire X-ray images by harnessing traditional feature extraction methods such as Local Binary Pattern (LBP) and Gray Level Co-Occurrence Matrix (GLCM) features, as well as Fourier and Wavelet-based features, complemented by advanced machine learning techniques.
1 code implementation • 29 Jan 2024 • Maofeng Tang, Andrei Cozma, Konstantinos Georgiou, Hairong Qi
Remote sensing images present unique challenges to image analysis due to the extensive geographic coverage, hardware limitations, and misaligned multi-scale images.
no code implementations • 7 Jun 2023 • Xieting Chu, Hongjue Zhao, Enze Xu, Hairong Qi, Minghan Chen, Huajie Shao
Experimental results demonstrate that the proposed SRCV significantly outperforms state-of-the-art baselines in discovering mathematical expressions with multiple variables.
no code implementations • 11 Jul 2021 • Ramin Nabati, Landon Harris, Hairong Qi
Our proposed method uses a center-based radar-camera fusion algorithm for object detection and utilizes a greedy algorithm for object association.
no code implementations • 17 Feb 2021 • Jiangnan Li, Yingyuan Yang, Jinyuan Stella Sun, Kevin Tomsovic, Hairong Qi
False data injection attacks (FDIAs) pose a significant security threat to power system state estimation.
3 code implementations • 10 Nov 2020 • Ramin Nabati, Hairong Qi
In this paper, we focus on the problem of radar and camera sensor fusion and propose a middle-fusion approach to exploit both radar and camera data for 3D object detection.
Ranked #9 on 3D Object Detection on nuscenes Camera-Radar
no code implementations • 17 Sep 2020 • Ramin Nabati, Hairong Qi
Our radar object proposal network uses radar point clouds to generate 3D proposals from a set of 3D prior boxes.
no code implementations • 19 Aug 2020 • Ying Qu, Razieh Kaviani Baghbaderani, Wei Li, Lianru Gao, Hairong Qi
Transfer learning-based methods address this problem by pre-training in the source domain and fine-tuning on the target domain.
General Classification Hyperspectral Image Classification +1
1 code implementation • ECCV 2020 • Razieh Kaviani Baghbaderani, Ying Qu, Hairong Qi, Craig Stutts
Although inherently a classification problem, both representative and discriminative aspects of data need to be exploited in order to better distinguish unknown classes from known.
no code implementations • 16 Jun 2020 • Ying Qu, Razieh Kaviani Baghbaderani, Hairong Qi, Chiman Kwan
First, the self-attention mechanism is proposed where the spatial varying detail extraction and injection functions are estimated according to the attention representations indicating spectral characteristics of the MSI with sub-pixel accuracy.
no code implementations • 12 Mar 2020 • Jiangnan Li, Yingyuan Yang, Jinyuan Stella Sun, Kevin Tomsovic, Hairong Qi
We study the potential vulnerabilities of ML applied in CPSs by proposing Constrained Adversarial Machine Learning (ConAML), which generates adversarial examples that satisfy the intrinsic constraints of the physical systems.
no code implementations • 30 Aug 2019 • Alireza Rahimpour, Sujitha Martin, Ashish Tawari, Hairong Qi
In this paper, we propose a novel architecture for road-user importance estimation which takes advantage of the local and global context of the scene.
1 code implementation • ICCV 2019 • Zhibo Wang, Siyan Zheng, Mengkai Song, Qian Wang, Alireza Rahimpour, Hairong Qi
The results demonstrate that deep re-ID systems are vulnerable to our physical attacks.
1 code implementation • 24 Jul 2019 • Ying Qu, Zhenzhou Shao, Hairong Qi
Photorealistic stylization aims to transfer the style of a reference photo onto a content photo in a natural fashion, such that the stylized image looks like a real photo taken by a camera.
no code implementations • 16 May 2019 • Chengcheng Li, Zi Wang, Dali Wang, Xiangyang Wang, Hairong Qi
Most existing channel pruning methods formulate the pruning task from a perspective of inefficiency reduction which iteratively rank and remove the least important filters, or find the set of filters that minimizes some reconstruction errors after pruning.
1 code implementation • 1 May 2019 • Ramin Nabati, Hairong Qi
Region proposal algorithms play an important role in most state-of-the-art two-stage object detection networks by hypothesizing object locations in the image.
Ranked #1 on 3D Object Detection on nuScenes-F
1 code implementation • 27 Apr 2019 • Ying Qu, Hairong Qi, Chiman Kwan, Naoto Yokoya, Jocelyn Chanussot
With this design, the network allows to extract correlated spectral and spatial information from unregistered images that better preserves the spectral information.
2 code implementations • CVPR 2019 • Zhifei Zhang, Zhaowen Wang, Zhe Lin, Hairong Qi
Reference-based super-resolution (RefSR), on the other hand, has proven to be promising in recovering high-resolution (HR) details when a reference (Ref) image with similar content as that of the LR input is given.
Ranked #2 on Image Super-Resolution on CUFED5 - 4x upscaling
no code implementations • 18 Feb 2019 • Zi Wang, Chengcheng Li, Dali Wang, Xiangyang Wang, Hairong Qi
In specific, with the proposed method, 75% and 54% of the total computation time for the whole pruning procedure can be reduced for AlexNet on CIFAR-10, and for VGG-16 on ImageNet, respectively.
no code implementations • 18 Feb 2019 • Chengcheng Li, Zi Wang, Xiangyang Wang, Hairong Qi
In this work, we propose a novel single-shot channel pruning approach based on alternating direction methods of multipliers (ADMM), which can eliminate the need for complex iterative pruning and fine-tuning procedure and achieve a target compression ratio with only one run of pruning and fine-tuning.
1 code implementation • 3 Dec 2018 • Zhibo Wang, Mengkai Song, Zhifei Zhang, Yang song, Qian Wang, Hairong Qi
Although the state-of-the-art attacking techniques that incorporated the advance of Generative adversarial networks (GANs) could construct class representatives of the global data distribution among all clients, it is still challenging to distinguishably attack a specific client (i. e., user-level privacy leakage), which is a stronger privacy threat to precisely recover the private data from a specific client.
no code implementations • 24 Jun 2018 • Alireza Rahimpour, Hairong Qi
In this paper, we investigate the challenging task of person re-identification from a new perspective and propose an end-to-end attention-based architecture for few-shot re-identification through meta-learning.
no code implementations • 5 May 2018 • Chengcheng Li, Zi Wang, Hairong Qi
Building on top of the success of generative adversarial networks (GANs), conditional GANs attempt to better direct the data generation process by conditioning with certain additional information.
no code implementations • CVPR 2018 • Ying Qu, Hairong Qi, Chiman Kwan
We refer to the proposed architecture as unsupervised Sparse Dirichlet-Net, or uSDN.
1 code implementation • 13 Apr 2018 • Yang Song, Jingwen Zhu, Dawei Li, Xiaolong Wang, Hairong Qi
Given an arbitrary face image and an arbitrary speech clip, the proposed work attempts to generating the talking face video with accurate lip synchronization while maintaining smooth transition of both lip and facial movement over the entire video clip.
no code implementations • 10 Apr 2018 • Zhifei Zhang, Zhaowen Wang, Zhe Lin, Hairong Qi
We focus on transferring the high-resolution texture from reference images to the super-resolution process without the constraint of content similarity between reference and target images, which is a key difference from previous example-based methods.
no code implementations • 4 Apr 2018 • Liu Liu, Hairong Qi
Learning compact representation is vital and challenging for large scale multimedia data.
1 code implementation • 21 Jan 2018 • Zhifei Zhang, Yang song, Hairong Qi
Incorporating encoding-decoding nets with adversarial nets has been widely adopted in image generation tasks.
no code implementations • 23 Jul 2017 • Alireza Rahimpour, Liu Liu, Ali Taalimi, Yang song, Hairong Qi
Despite recent attempts for solving the person re-identification problem, it remains a challenging task since a person's appearance can vary significantly when large variations in view angle, human pose, and illumination are involved.
no code implementations • 2 Jun 2017 • Yang Song, Zhifei Zhang, Hairong Qi
A more generalized question is that if a large proportion (e. g., more than 50%) of the face/sketch is missing, can a realistic whole face sketch/image still be estimated.
no code implementations • 30 May 2017 • Ali Taalimi, Alireza Rahimpour, Liu Liu, Hairong Qi
Nowadays, distributed smart cameras are deployed for a wide set of tasks in several application scenarios, ranging from object recognition, image retrieval, and forensic applications.
no code implementations • 30 May 2017 • Ali Taalimi, Liu Liu, Hairong Qi
We use a network flow approach to link detections in low-level and tracklets in high-level.
no code implementations • 15 Mar 2017 • Liu Liu, Alireza Rahimpour, Ali Taalimi, Hairong Qi
Furthermore, in the effort of handling multilabel images, we design a joint cross entropy loss that includes both softmax cross entropy and weighted binary cross entropy in consideration of the correlation and independence of labels, respectively.
5 code implementations • CVPR 2017 • Zhifei Zhang, Yang song, Hairong Qi
In CAAE, the face is first mapped to a latent vector through a convolutional encoder, and then the vector is projected to the face manifold conditional on age through a deconvolutional generator.
no code implementations • 19 Dec 2016 • Alireza Rahimpour, Ali Taalimi, Hairong Qi
Distributed surveillance systems have become popular in recent years due to security concerns.
1 code implementation • 24 Sep 2016 • Zhifei Zhang, Yang song, Wei Wang, Hairong Qi
The staggering amount of streaming time series coming from the real world calls for more efficient and effective online modeling solution.
no code implementations • 2013 IEEE International Conference on Computer Vision 2014 • Jiajia Luo, Wei Wang, Hairong Qi
Human action recognition based on the depth information provided by commodity depth sensors is an important yet challenging task.
no code implementations • 12 Jul 2013 • Li He, Hairong Qi, Russell Zaretzki
In this paper, a color transfer framework to evoke different emotions for images based on color combinations is proposed.
no code implementations • CVPR 2013 • Li He, Hairong Qi, Russell Zaretzki
This is due to the unique property of the beta process model that the sparse representation can be decomposed to values and dictionary atom indicators.