anindex

Multi-modal Cluttered Scene Analysis in Knowledge Intensive Scenarios (GSOC 2017)

Introduction

Unstructured information such as video, text, and audio represents the largest and fastest-growing source of information nowadays. The goal of AI is to approach the human abilities to process efficiently the vast amount of Unstructured Data in this complex real world. This project focuses on Object Hypotheses and Segmentation tasks using Symmetry Constraints in cluttered and occluded scenarios, which is developed as Rotational and Bilateral Symmetry Segmentation Analysis Engines on Robosherlock framework. This project enables RoboSherlock to operate in a knowledge-intensive real world. The project was done to fulfill the requirements of Google Summer of Code 2017.

The project is merged with the branch master. It was designed to not use any other library dependencies than the main repo. The system is now able to robustly detect rotational, bilateral symmetries and segment objects

bmhatfield

# In order for gpg to find gpg-agent, gpg-agent must be running, and there must be an env
# variable pointing GPG to the gpg-agent socket. This little script, which must be sourced
# in your shell's init script (ie, .bash_profile, .zshrc, whatever), will either start
# gpg-agent or set up the GPG_AGENT_INFO variable if it's already running.

# Add the following to your shell init to set up gpg-agent automatically for every shell
if [ -f ~/.gnupg/.gpg-agent-info ] && [ -n "$(pgrep gpg-agent)" ]; then
    source ~/.gnupg/.gpg-agent-info
    export GPG_AGENT_INFO
else

jacquerie

#!/usr/bin/env python
# -*- coding: utf-8 -*-

import base64

MESSAGE = '''
EUYQGhMMSx0cU0FIU1MCFAQPG01NQ0gTAEICChUGBxZTRVxBSQoZFQYKHQpKSUNURhcVEgoUFR1I
SltDSBkBTRwKEAgQHxFCSkFJDgkJCgoGCkMLAQBGUklUQhMPAgAJCgYLV0MOSR0VAxAaABZBQVRP
TRICCRVIAk5IEg4dVFRfRkYZBgRARBI=
'''