Memoona Tahira's Projects
BiConvLSTM for violence detection in videos
This Pytorch repo uses BiConvLSTM in a Spatiotemporal Encoder to detect violence in Videos. Three benchmark datasets namely Hockey, Movies and Violent Flows were used in this work.
Capstone Project for MLZoomcamp by DataTalks.Club
Here's a simple, yet powerful, way to cluster GPS locations with Python.
A language-agnostic interface to TensorBoard
IEEE published Eye-tracking dataset of Human Eye Fixations over Crowd Videos. This dataset is part of the MIT/TΓΌbingen Saliency Benchmark datasets.
Optical Flow Dataset and Benchmark for Visual Crowd Analysis
cvpaper.challenge working repository for surveying all papers of CVPR 2018
code and model of Pyramid Feature Selective Network for Saliency detection
2023 cohort Data Engineering Zoomcamp by DTC repo by Memoona Tahira
Free Data Engineering course!
Deep Residual Learning for Image Recognition
Deep Visual Attention Prediction (TIP18)
Revisiting Video Saliency: A Large-scale Benchmark and a New Model (CVPR2018)
FUSE driver to read/write Windows' BitLocker-ed volumes under Linux / Mac OSX
Documentation and API Reference
for fixation and eval code
Eye-tracking experiment with video stimuli, programmed using PyGaze and OpenCV
Experiment and analysis code to assess the usefulness of the EyeTribe tracker in psychological research.
EYMOL: Eye Movements Laws - for fixation and eval code
Code for visualizing and plotting eye movements, fixations, saliency maps.
A collection of Human Fixations Datasets and Metrics for Scanpath Similarity
Implementation of a simple image segmentation algorithm of a natural scene image containing text by using Laplacian of Gaussian in frequency domain and K-means algorithm
Stats hands on
Label Studio is a multi-type data labeling and annotation tool with standardized output format
The large-scale eye-tracking database called LEDOV for video salinecy
Tensorflow implementation of "Listen, Attend and Spell" authored by William Chan. This project utilizes input pipeline and estimator API of Tensorflow, which makes the training and evaluation truly end-to-end.