Scene understanding in a contested battlefield is one of the very difficult tasks for detecting and identifying threats. In a complex battlefield, multiple autonomous robots for multi-domain operations are likely to track the activities of the same threat/objects leading to inefficient and redundant tasks. To address this problem, we propose a novel and effective object clustering framework that takes into account the position and depth of objects scattered in the scene. This framework enables the robot to focus solely on the objects of interest.

The "Sanskrit Character Dataset" includes 44 classes of handwritten Sanskrit characters, designed to support research in optical character recognition (OCR) and machine learning for ancient languages. Each class represents a unique Sanskrit letter, collected in various handwriting styles to ensure diversity and robustness. For each class, 50 to 80 images are included. To ensure diversity and real-world applicability, the letters were written in various handwriting styles.

Most existing machine learning classifiers are highly vulnerable to adversarial examples. An adversarial example is a sample of input data which has been modified very slightly in a way that is intended to cause a machine learning classifier to misclassify it. In many cases, these modifications can be so subtle that a human observer does not even notice the modification at all, yet the classifier still makes a mistake.

This Dataset is a self-harm dataset developed by ZIOVISION Co. Ltd. It consists of 1,120 videos. Actors were hired to simulate self-harm behaviors, and the scenes were recorded using four cameras to ensure full coverage without blind spots. Self-harm behaviors in the dataset are limited to "cutting" actions targeting specific body parts. The designated self-harm areas include the wrists, forearms, and thighs.

 The full dataset can be accesssed through https://github.com/zv-ai/ZV_Self-harm-Dataset.git