Computer Vision

We present a dataset of human visual attention on 2D images during scene free viewing. This dataset includes 1900 images, which are corrputed by various image transformations. This dataset is manually annotated with human eye-movement data recorded by Tobii X120 eye-tracker. This dataset provides a new benchmark to measure the robustness of saliency prediction models on various transformed scenes.

38 views
  • Computer Vision
  • Last Updated On: 
    Fri, 10/18/2019 - 04:17

    The is a dataset for indoor depth estimation that contains 1803 synchronized image triples (left, right color image and depth map), from 6 different scenes, including a library, some bookshelves, a conference room, a cafe, a study area, and a hallway. Among these images, 1740 high-quality ones are marked as high-quality imagery. The left view and the depth map are aligned and synchronized and can be used to evaluate monocular depth estimation models. Standard training/testing splits are provided.

    48 views
  • Computer Vision
  • Last Updated On: 
    Thu, 10/17/2019 - 20:30

    PRECIS HAR represents a RGB-D dataset for human activity recognition, captured with the 3D camera Orbbec Astra Pro. It consists of 16 different activities (stand up, sit down, sit still, read, write, cheer up, walk, throw paper, drink from a bottle, drink from a mug, move hands in front of the body, move hands close to the body, raise one hand up, raise one leg up, fall from bed, and faint), performed by 50 subjects.

    1258 views
  • Computer Vision
  • Last Updated On: 
    Mon, 10/21/2019 - 09:42

    The dataset consists of 60285 character image files which has been randomly divided into 54239 (90%) images as training set 6046 (10%) images as test set. The collection of data samples was carried out in two phases. The first phase consists of distributing a tabular form and asking people to write the characters five times each. Filled-in forms were collected from around 200 different individuals in the age group 12-23 years. The second phase was the collection of handwritten sheets such as answer sheets and classroom notes from students in the same age group.

    127 views
  • Computer Vision
  • Last Updated On: 
    Mon, 10/28/2019 - 01:08

    Water meter dataset. Contains 1244 water meter images. Assembled using a crowdsourcing platform Yandex.Toloka.

    117 views
  • Computer Vision
  • Last Updated On: 
    Mon, 10/14/2019 - 05:00

    As one of the research directions at OLIVES Lab @ Georgia Tech, we focus on the robustness of data-driven algorithms under diverse challenging conditions where trained models can possibly be depolyed. To achieve this goal, we introduced a large-sacle (1.M images) object recognition dataset (CURE-OR) which is among the most comprehensive datasets with controlled synthetic challenging conditions. In CURE

    144 views
  • Artificial Intelligence
  • Last Updated On: 
    Sun, 10/13/2019 - 17:05

    As one of the research directions at OLIVES Lab @ Georgia Tech, we focus on the robustness of data-driven algorithms under diverse challenging conditions where trained models can possibly be depolyed. To achieve this goal, we introduced a large-sacle (~1.72M frames) traffic sign detection video dataset (CURE-TSD) which is among the most comprehensive datasets with controlled synthetic challenging conditions. The video sequences in the 

    260 views
  • Artificial Intelligence
  • Last Updated On: 
    Sun, 10/13/2019 - 17:07

    "The dataset was built by capturing the static gestures of the American Sign Language (ASL) alphabet, from 8 people, except for the letters J and Z, since they are dynamic gestures. To capture the images, we used a Logitech Brio webcam, with a resolution of 1920 × 1080 pixels, in a university laboratory with artificial lighting. By extracting only the hand region, we defined an area of 400 × 400 pixels for the final image of our dataset." removed from https://doi.org/10.1155/2019/4167890 .

    172 views
  • Computer Vision
  • Last Updated On: 
    Fri, 10/11/2019 - 23:30

    As one of the research directions at OLIVES Lab @ Georgia Tech, we focus on the robustness of data-driven algorithms under diverse challenging conditions where trained models can possibly be depolyed.

    193 views
  • Artificial Intelligence
  • Last Updated On: 
    Sun, 10/13/2019 - 17:08

    The Dataset

    The Onera Satellite Change Detection dataset addresses the issue of detecting changes between satellite images from different dates.

    782 views
  • Computer Vision
  • Last Updated On: 
    Wed, 10/09/2019 - 08:34

    Pages