Picture for Pooyan Fazli

Pooyan Fazli

VidComposition: Can MLLMs Analyze Compositions in Compiled Videos?

Add code
Nov 19, 2024
Viaarxiv icon

OSCaR: Object State Captioning and State Change Representation

Add code
Feb 28, 2024
Viaarxiv icon

CLearViD: Curriculum Learning for Video Description

Add code
Nov 08, 2023
Viaarxiv icon

Clustering Social Touch Gestures for Human-Robot Interaction

Add code
Apr 03, 2023
Viaarxiv icon

Charting Visual Impression of Robot Hands

Add code
Nov 17, 2022
Viaarxiv icon

NarrationBot and InfoBot: A Hybrid System for Automated Video Description

Add code
Nov 07, 2021
Figure 1 for NarrationBot and InfoBot: A Hybrid System for Automated Video Description
Figure 2 for NarrationBot and InfoBot: A Hybrid System for Automated Video Description
Figure 3 for NarrationBot and InfoBot: A Hybrid System for Automated Video Description
Figure 4 for NarrationBot and InfoBot: A Hybrid System for Automated Video Description
Viaarxiv icon

Real-time Policy Distillation in Deep Reinforcement Learning

Add code
Dec 29, 2019
Figure 1 for Real-time Policy Distillation in Deep Reinforcement Learning
Figure 2 for Real-time Policy Distillation in Deep Reinforcement Learning
Viaarxiv icon

DeepMoTIon: Learning to Navigate Like Humans

Add code
Mar 02, 2019
Figure 1 for DeepMoTIon: Learning to Navigate Like Humans
Viaarxiv icon

Setting Up the Beam for Human-Centered Service Tasks

Add code
Oct 18, 2017
Figure 1 for Setting Up the Beam for Human-Centered Service Tasks
Figure 2 for Setting Up the Beam for Human-Centered Service Tasks
Figure 3 for Setting Up the Beam for Human-Centered Service Tasks
Viaarxiv icon

Semantic Robot Vision Challenge: Current State and Future Directions

Add code
Aug 19, 2009
Viaarxiv icon