Bounding overwatch
View article: Unobservable Selection and Coefficient Stability: Theory and Evidence
Unobservable Selection and Coefficient Stability: Theory and Evidence Open
A common approach to evaluating robustness to omitted variable bias is to observe coefficient movements after inclusion of controls. This is informative only if selection on observables is informative about selection on unobservables. Alth…
View article
The Caltech-UCSD Birds-200-2011 Dataset Open
CUB-200-2011 is an extended version of CUB-200 [7], a challenging dataset of 200 bird species. The extended version roughly doubles the number of images per category and adds new part localization annotations. All images are annotated with…
View article
Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression Open
Bounding box regression is the crucial step in object detection. In existing methods, while ℓn-norm loss is widely adopted for bounding box regression, it is not tailored to the evaluation metric, i.e., Intersection over Union (IoU). Recen…
View article
You Only Look Once: Unified, Real-Time Object Detection Open
We present YOLO, a new approach to object detection. Prior work on object detection repurposes classifiers to perform detection. Instead, we frame object detection as a regression problem to spatially separated bounding boxes and associate…
View article
RU-AI: A Large Multimodal Dataset for Machine Generated Content Detection Open
This repository contains all the collected and aligned data for RU-AI dataset. It is constructed based on three large publicly available datasets: Flickr8K, COCO, and Places205, by adding their corresponding machine-generated pairs from fi…
View article
Mask R-CNN Open
We present a conceptually simple, flexible, and general framework for object instance segmentation. Our approach efficiently detects objects in an image while simultaneously generating a high-quality segmentation mask for each instance. Th…
View article
The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale Open
We present Open Images V4, a dataset of 9.2M images with unified annotations for image classification, object detection and visual relationship detection. The images have a Creative Commons Attribution license that allows to share and adap…
View article
Turbulence Modeling in the Age of Data Open
Data from experiments and direct simulations of turbulence have historically been used to calibrate simple engineering models such as those based on the Reynolds-averaged Navier–Stokes (RANS) equations. In the past few years, with the avai…
View article
DeepFruits: A Fruit Detection System Using Deep Neural Networks Open
This paper presents a novel approach to fruit detection using deep convolutional neural networks. The aim is to build an accurate, fast and reliable fruit detection system, which is a vital element of an autonomous agricultural robotic pla…
View article
Refugees, migrants, neither, both: categorical fetishism and the politics of bounding in Europe’s ‘migration crisis’ Open
The use of the categories ‘refugee’ and ‘migrant’ to differentiate between those on the move and the legitimacy, or otherwise, of their claims to international protection has featured strongly during Europe’s ‘migration crisis’ and has bee…
View article
R3Det: Refined Single-Stage Detector with Feature Refinement for Rotating Object Open
Rotation detection is a challenging task due to the difficulties of locating the multi-angle objects and separating them effectively from the background. Though considerable progress has been made, for practical settings, there still exist…
View article
Real-Time Seamless Single Shot 6D Object Pose Prediction Open
We propose a single-shot approach for simultaneously detecting an object in an RGB image and predicting its 6D pose without requiring multiple stages or having to examine multiple hypotheses. Unlike a recently proposed single-shot techniqu…
View article
Gliding Vertex on the Horizontal Bounding Box for Multi-Oriented Object Detection Open
Object detection has recently experienced substantial progress. Yet, the widely adopted horizontal bounding box representation is not appropriate for ubiquitous oriented objects such as objects in aerial images and scene texts. In this pap…
View article
BB8: A Scalable, Accurate, Robust to Partial Occlusion Method for Predicting the 3D Poses of Challenging Objects without Using Depth Open
International audience
View article
Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression Open
Bounding box regression is the crucial step in object detection. In existing methods, while $\ell_n$-norm loss is widely adopted for bounding box regression, it is not tailored to the evaluation metric, i.e., Intersection over Union (IoU).…
View article
Real-Time Scene Text Detection with Differentiable Binarization Open
Recently, segmentation-based methods are quite popular in scene text detection, as the segmentation results can more accurately describe scene text of various shapes such as curve text. However, the post-processing of binarization is essen…
View article
Generalized Focal Loss: Learning Qualified and Distributed Bounding\n Boxes for Dense Object Detection Open
One-stage detector basically formulates object detection as dense\nclassification and localization. The classification is usually optimized by\nFocal Loss and the box location is commonly learned under Dirac delta\ndistribution. A recent t…
View article
BDD100K: A Diverse Driving Video Database with Scalable Annotation Tooling. Open
Datasets drive vision progress and autonomous driving is a critical vision application, yet existing driving datasets are impoverished in terms of visual content. Driving imagery is becoming plentiful, but annotation is slow and expensive,…
View article
Objects as Points Open
Detection identifies objects as axis-aligned boxes in an image. Most successful object detectors enumerate a nearly exhaustive list of potential object locations and classify each. This is wasteful, inefficient, and requires additional pos…
View article
PixelLink: Detecting Scene Text via Instance Segmentation Open
Most state-of-the-art scene text detection algorithms are deep learning based methods that depend on bounding box regression and perform at least two kinds of predictions: text/non-text classification and location regression. Regression pl…
View article
A Comparative Analysis of Object Detection Metrics with a Companion Open-Source Toolkit Open
Recent outstanding results of supervised object detection in competitions and challenges are often associated with specific metrics and datasets. The evaluation of such methods applied in different contexts have increased the demand for an…
View article
The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale Open
We present Open Images V4, a dataset of 9.2M images with unified annotations for image classification, object detection and visual relationship detection. The images have a Creative Commons Attribution license that allows to share and adap…
View article
Human Semantic Parsing for Person Re-identification Open
Person re-identification is a challenging task mainly due to factors such as background clutter, pose, illumination and camera point of view variations. These elements hinder the process of extracting robust and discriminative representati…
View article
SAR Ship Detection Dataset (SSDD): Official Release and Comprehensive Data Analysis Open
SAR Ship Detection Dataset (SSDD) is the first open dataset that is widely used to research state-of-the-art technology of ship detection from Synthetic Aperture Radar (SAR) imagery based on deep learning (DL). According to our investigati…
View article
SIoU Loss: More Powerful Learning for Bounding Box Regression Open
The effectiveness of Object Detection, one of the central problems in computer vision tasks, highly depends on the definition of the loss function - a measure of how accurately your ML model can predict the expected outcome. Conventional o…
View article
Sensitivity Analysis Without Assumptions Open
Unmeasured confounding may undermine the validity of causal inference with observational studies. Sensitivity analysis provides an attractive way to partially circumvent this issue by assessing the potential influence of unmeasured confoun…
View article
Automated Indent Scanning: Artificial intelligence assisted scanning of large regular and irregular nanoindentation arrays in scanning electron microscopes Open
Recording larger arrays of indents is a tedious and time intensive task. This project aims to automate this process through the use of the Python API provided by the Tescan microscope (SharkSEM), simple automation scripts, and the use of o…
View article
R2CNN: Rotational Region CNN for Orientation Robust Scene Text Detection Open
In this paper, we propose a novel method called Rotational Region CNN (R2CNN) for detecting arbitrary-oriented texts in natural scene images. The framework is based on Faster R-CNN [1] architecture. First, we use the Region Proposal Networ…
View article
Gradient Harmonized Single-Stage Detector Open
Despite the great success of two-stage detectors, single-stage detector is still a more elegant and efficient way, yet suffers from the two well-known disharmonies during training, i.e. the huge difference in quantity between positive and …
View article
Weakly Supervised Object Localization with Multi-Fold Multiple Instance Learning Open
Object category localization is a challenging problem in computer vision. Standard supervised training requires bounding box annotations of object instances. This time-consuming annotation process is sidestepped in weakly supervised learni…