Computer Vision - Groups

Image as Data: Automated Visual Content Analysis for Political Science

Image data provide unique information about political events, actors, and their interactions which are difficult to measure from or not available in text data.

Dataset
JSON

Detection of vertebral fractures in CT using 3D Convolutional Neural Networks

A dataset of 90 CT image series for training a 3D Convolutional Neural Network for vertebral fracture detection.

Dataset
JSON

Squared Curvature Regularization

The dataset used in the paper for testing the proposed squared curvature regularization approach.

Dataset
JSON

Pose for Everything

Pose for Everything: Towards Category-Agnostic Pose Estimation

Dataset
JSON

Meta-Point Learning and Refining for Category-Agnostic Pose Estimation

Category-agnostic pose estimation (CAPE) aims to predict keypoints for arbitrary classes given a few support images annotated with keypoints.

Dataset
JSON

Discrete Radon Transform

The dataset used in this paper for computing 4th order 2D image moments using the Discrete Radon Transform.

Dataset
JSON

Movie Description dataset

A novel dataset of movies with aligned descriptions sourced from movie scripts and DVS (Descriptive Video Service) audio descriptions.

Dataset
JSON

AniDress

The dataset for the paper AniDress: Animatable Loose-Dressed Avatars from Sparse Views Using Garment Rigging Models

Dataset
JSON

CRD-CGAN: Category-Consistent and Relativistic Constraints for Diverse Text-t...

Generating photo-realistic images from a text description is a challenging problem in computer vision. Previ- ous works have shown promising performance to generate synthetic...

Dataset
JSON

NPBG++

A new system for novel view synthesis that can rapidly obtain the neural representation of a scene, passing a single time through all available source views.

Dataset
JSON

PatchZero

PatchZero: Defending against Adversarial Patch Attacks by Detecting and Zeroing the Patch

Dataset
JSON

Main Product Detection with Graph Networks for Fashion

Main product detection is a crucial step of vision-based fashion product feed parsing pipelines, focused in identifying the bounding boxes that contain the product being sold in...