tsingqguo Goto Github PK
Name: Qing Guo
Type: User
Company: A*STAR
Bio: Senior Scientist, PI, with CFAR, A*STAR. Research interests are AI security, computer vision, image processing, and deep learning.
Location: Singapore
Name: Qing Guo
Type: User
Company: A*STAR
Bio: Senior Scientist, PI, with CFAR, A*STAR. Research interests are AI security, computer vision, image processing, and deep learning.
Location: Singapore
SSD: Single Shot MultiBox Detector | a PyTorch Tutorial to Object Detection
We propose the adversarial blur attack (ABA) against visual object tracking.
AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty
We propose a novel data augmentation by enriching the backgrounds for change detection in a weakly-superivsed way.
abc
init
We propose a cross- temporal context aggregation (CTCA) model for continuous sign language recognition
Learning Dynamic Siamese Network for Visual Object Tracking
we propose EfficientDerain for high-efficiency single-image deraining
We further extend the efficientderain in https://github.com/tsingqguo/efficientderain via a novel predictive filtering framework.
We propose a statistical consistency attack (StatAttack) against diverse DeepFake detectors.
We propose a new method for effective shadow removal by regarding it as an exposure fusion problem.
This repository contains the demos of frequency-tuned ACM.
We propose the shadow-guided inpainting task to take advantage of the shadow removal and image inpainting.
We introduce a novel approach to counter adversarial attacks, namely, image resampling. The underlying rationale behind our idea is that image resampling can alleviate the influence of adversarial perturbations while preserving essential semantic information, thereby conferring an inherent advantage in defending against adversarial attacks.
Official implementation of "Can You Spot the Chameleon? Adversarially Camouflaging Images from Co-Salient Object Detection" in CVPR 2022.
We proposed a novel framework for image inpainting. https://arxiv.org/abs/2107.04281
Try to build a new tracking framework with Siamese network
an implementation of Video Frame Interpolation via Adaptive Separable Convolution using PyTorch(Backward Implemented)
Tips for releasing research code in Machine Learning (with official NeurIPS 2020 recommendations)
We have identified a novel adversarial defense solution, i.e., image resampling, which can break the adversarial textures while maintaining the main semantic information in the input image. This work has been accepted to ICLR 2024.
We build a benchmark to involve existing adversairal tracking attacks and defense methods and evaluates their performance, which could trick a series of novel works and push the progress to build a robust tracking system.
We propose the semantic-aware implicit representation by learning semantic-aware implicit representation (SAIR), that is, we make the implicit representation of each pixel rely on both its appearance and semantic information (e.g., which object does the pixel belong to). This work is publised in ECCV 2024.
We propose a shadow-removal benchmark dataset (i.e., SHAREL) to explore the mutual influence of shadow removal and facial landmark detection tasks.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.