Tagged "Computer Vision"

Siamese Neural Network (SNN)

A deep dive into the architecture and intuition behind Siamese Neural Networks, exploring how they use shared weights and distance metrics to solve few-shot learning and verification tasks.

Mar 2023

COLMAN: Collaborative Multi-Agent Navigation using Textual-Visual Embeddings

COLMAN explores object goal navigation using embodied AI agents, leveraging Transformer-based architectures and CLIP semantic embeddings for improved scene understanding.

YEAR 2022

Deep Imitation Learning for Complex Manipulation Task from Virtual Reality Teleoperation

Research focused on robot skill acquisition through imitation learning and VR teleoperation, mapping raw pixels to complex robotic manipulation actions.

YEAR 2021

FAZE: Few-Shot Adaptive Gaze Estimation using Meta-Learning

Implementation of a personalized gaze estimation framework using DT-ED networks and meta-learning to achieve high accuracy with minimal calibration samples.

YEAR 2021