Dashboard regarding self-induced loss cases in brazil, made with panel and hvplot.

Public repository for the DETECT follow-up interviews.

Slides about my research at the Oxford Internet Institute.

Thesis name: Comparative evaluation of deep neural networks for automatic detection of violence scenes within videos

CCTV Violence Detection System for Children's Hospitals

This project is designed to detect and alert authorities about violent incidents in school environments in real-time. Utilizes a pretrained RESNET model for image classification and Twilio API for sending notifications. Achieves approximately 93% accuracy on the test dataset.

Violence Detection with LSTM and CNN

A violence detection module that can inform authorities about the details of individuals present at the site of the incident using face recognition.

AiVision is an AI based software designed to automate the process of manually monitoring the surveillance system, detects threats and alerts the concerned authorities.

Code repository for the EACL 2023 long paper Extracting Victim Counts from Text

This project is done at Jimma University in 2021EC for our mini/semester project. As we know now a day the violence is occurring in Ethiopia in different areas, due to this reason, we try to solve our community and government problems using artificial intelligence (AI) using both Fine-tuning using VGG-16, motion detection using Cnn+BiLstm, and u…

Two neural networks to detect weapons and violence in videos

Violence recognition in streaming video using Transfer Learning and MoViNets. The project leverages state-of-the-art deep learning techniques to create an efficient and accurate violence detection system.

This project focuses on the comparative analysis of machine learning models for the task of violence detection in images or videos. Violence detection is a crucial application with various real-world use cases, including surveillance, content moderation, and public safety.

realtime violence detection from videos using cnn-lstm model

Deep Learning-Based Approach to Detect Violence

Explainable Content Moderation performed using CNNs and visualized using Grad-CAM

Deeply Supervised Practical Implementation of Violence Detection from Videos for Maximizing Performance