All software
CODaN
CODaN: Common Objects Day and Night, an image classification dataset.
- color invariants
- computer vision
- day-night
- + 2
- (Markdown)
- (Other)
- (Python)
Data underlying the publication/thesis chapter: FlexConv: Continuous Kernel Convolutions with Differentiable Kernel Sizes
Data underlying the publication/thesis chapter: FlexConv: Continuous Kernel Convolutions with Differentiable Kernel Sizes
- computer vision
- Convolutional Neural Network
- kernel size
- + 2
- ("Jupyter Notebook")
- (Markdown)
- (Other)
- + 2
MapReader
MapReader is an end-to-end computer vision (CV) pipeline for exploring and analyzing images at scale.
- computer vision
- digital humanities
- geospatial
- + 4
- (Dockerfile)
- (Python)
- (Shell)
- + 1
Data underlying the publication/thesis chapter: Scale Learning in Scale-Equivariant Convolutional Networks
Data underlying the publication/thesis chapter: Scale Learning in Scale-Equivariant Convolutional Networks
- computer vision
- Convolutional neural network (CNN)
- equivariance
- + 3
- (JSON)
- ("Jupyter Notebook")
- (Markdown)
- + 5
Code underlying the publication: "Video BagNet: short temporal receptive fields increase robustness in long-term action recognition"
Code underlying the publication: "Video BagNet: short temporal receptive fields increase robustness in long-term action recognition"
- 3D-CNN
- Action recognition
- BagNet
- + 2
- (Markdown)
- (Other)
- (Python)
- + 1
longterm_datasets
Code underlying the publication: "Are current long-term video understanding datasets long-term?"
- computer vision
- deep learning
- Long-term action recognition
- (HTML)
- (Markdown)
- (Other)
- + 2
Code underlying the publication: Using and Abusing Equivariance
Code underlying the publication: Using and Abusing Equivariance
- computer vision
- data efficient deep learning
- equivariance
- + 1
- (Markdown)
- (Other)
- (Python)
Data and code underlying the paper: "Can we predict the Most Replayed data of video streaming platforms?"
Data and code underlying the paper: "Can we predict the Most Replayed data of video streaming platforms?"
- computer vision
- Most Replayed Data
- Video streaming
- + 1
- (HTML)
- (JSON)
- ("Jupyter Notebook")
- + 4
Data and code underlying the PhD thesis: Pixels · People · Places: Computer Vision and Image Embeddings for Perception-Aware Urban Analytics
Data and code underlying the PhD thesis: Pixels · People · Places: Computer Vision and Image Embeddings for Perception-Aware Urban Analytics
- AI techniques
- computer vision
- multi-dimensional space
- + 1
- (JSON)
- ("Jupyter Notebook")
- (large-text-file)
- + 3
Data underlying the publication: Data-Efficient Challenges in Visual Inductive Priors: A Retrospective
Data underlying the publication: Data-Efficient Challenges in Visual Inductive Priors: A Retrospective
- computer vision
- Convolutional neural network (CNN)
- data efficiency
- + 2
- ("Jupyter Notebook")
- (Markdown)
- (Other)
Data underlying the publication/thesis chapter: Learning to Adapt to Position Bias in Vision Transformer Classifiers
Data underlying the publication/thesis chapter: Learning to Adapt to Position Bias in Vision Transformer Classifiers
- computer vision
- position bias
- position embeddings
- + 1
- (C++)
- ("Jupyter Notebook")
- (large-text-file)
- + 5
MATLAB script for a 3D marker tracking program
MATLAB script for a 3D marker tracking program
- computer vision
- marker detection
- object registration
- + 1
- (Markdown)
- (Matlab)
- (Other)