Robinson Piramuthu

Decision Making for Human-in-the-loop Robotic Agents via Uncertainty-Aware Reinforcement Learning

Mar 14, 2023
Siddharth Singi, Zhanpeng He, Alvin Pan, Sandip Patel, Gunnar A. Sigurdsson, Robinson Piramuthu, Shuran Song, Matei Ciocarlie

Figure 2 for Decision Making for Human-in-the-loop Robotic Agents via Uncertainty-Aware Reinforcement Learning

Figure 3 for Decision Making for Human-in-the-loop Robotic Agents via Uncertainty-Aware Reinforcement Learning

Figure 4 for Decision Making for Human-in-the-loop Robotic Agents via Uncertainty-Aware Reinforcement Learning

Access Paper or Ask Questions

RREx-BoT: Remote Referring Expressions with a Bag of Tricks

Jan 30, 2023
Gunnar A. Sigurdsson, Jesse Thomason, Gaurav S. Sukhatme, Robinson Piramuthu

Figure 2 for RREx-BoT: Remote Referring Expressions with a Bag of Tricks

Figure 3 for RREx-BoT: Remote Referring Expressions with a Bag of Tricks

Figure 4 for RREx-BoT: Remote Referring Expressions with a Bag of Tricks

Access Paper or Ask Questions

CLIP-Nav: Using CLIP for Zero-Shot Vision-and-Language Navigation

Nov 30, 2022
Vishnu Sashank Dorbala, Gunnar Sigurdsson, Robinson Piramuthu, Jesse Thomason, Gaurav S. Sukhatme

Figure 2 for CLIP-Nav: Using CLIP for Zero-Shot Vision-and-Language Navigation

Figure 3 for CLIP-Nav: Using CLIP for Zero-Shot Vision-and-Language Navigation

Figure 4 for CLIP-Nav: Using CLIP for Zero-Shot Vision-and-Language Navigation

* 8 pages, Accepted at LangRob Workshop at Conference on Robot Learning (CoRL), 2022

Access Paper or Ask Questions

Video in 10 Bits: Few-Bit VideoQA for Efficiency and Privacy

Oct 18, 2022
Shiyuan Huang, Robinson Piramuthu, Shih-Fu Chang, Gunnar A. Sigurdsson

Figure 2 for Video in 10 Bits: Few-Bit VideoQA for Efficiency and Privacy

Figure 3 for Video in 10 Bits: Few-Bit VideoQA for Efficiency and Privacy

Figure 4 for Video in 10 Bits: Few-Bit VideoQA for Efficiency and Privacy

* ECCV Workshop 2022

Access Paper or Ask Questions

A Simple Approach for Visual Rearrangement: 3D Mapping and Semantic Search

Jun 21, 2022
Brandon Trabucco, Gunnar Sigurdsson, Robinson Piramuthu, Gaurav S. Sukhatme, Ruslan Salakhutdinov

Figure 2 for A Simple Approach for Visual Rearrangement: 3D Mapping and Semantic Search

Figure 3 for A Simple Approach for Visual Rearrangement: 3D Mapping and Semantic Search

Figure 4 for A Simple Approach for Visual Rearrangement: 3D Mapping and Semantic Search

* Winner of the Rearrangement Challenge at CVPR 2022

Access Paper or Ask Questions

TEACh: Task-driven Embodied Agents that Chat

Oct 15, 2021
Aishwarya Padmakumar, Jesse Thomason, Ayush Shrivastava, Patrick Lange, Anjali Narayan-Chen, Spandana Gella, Robinson Piramuthu, Gokhan Tur, Dilek Hakkani-Tur

Figure 2 for TEACh: Task-driven Embodied Agents that Chat

Figure 3 for TEACh: Task-driven Embodied Agents that Chat

Figure 4 for TEACh: Task-driven Embodied Agents that Chat

* 7 pages main, 28 pages total, 29 figures; Version 2 includes information on data cleaning and experimental results use a modified data split that has been released

Access Paper or Ask Questions

VISITRON: Visual Semantics-Aligned Interactively Trained Object-Navigator

May 25, 2021
Ayush Shrivastava, Karthik Gopalakrishnan, Yang Liu, Robinson Piramuthu, Gokhan Tür, Devi Parikh, Dilek Hakkani-Tür

Figure 2 for VISITRON: Visual Semantics-Aligned Interactively Trained Object-Navigator

Figure 3 for VISITRON: Visual Semantics-Aligned Interactively Trained Object-Navigator

Figure 4 for VISITRON: Visual Semantics-Aligned Interactively Trained Object-Navigator

* Accepted at NAACL 2021, Visually Grounded Interaction and Language (ViGIL) Workshop

Access Paper or Ask Questions

Self-Attentive 3D Human Pose and Shape Estimation from Videos

Mar 26, 2021
Yun-Chun Chen, Marco Piccirilli, Robinson Piramuthu, Ming-Hsuan Yang

Figure 2 for Self-Attentive 3D Human Pose and Shape Estimation from Videos

Figure 3 for Self-Attentive 3D Human Pose and Shape Estimation from Videos

Figure 4 for Self-Attentive 3D Human Pose and Shape Estimation from Videos

* This paper is under consideration at Computer Vision and Image Understanding

Access Paper or Ask Questions

Mixup-CAM: Weakly-supervised Semantic Segmentation via Uncertainty Regularization

Aug 03, 2020
Yu-Ting Chang, Qiaosong Wang, Wei-Chih Hung, Robinson Piramuthu, Yi-Hsuan Tsai, Ming-Hsuan Yang

Figure 2 for Mixup-CAM: Weakly-supervised Semantic Segmentation via Uncertainty Regularization

Figure 3 for Mixup-CAM: Weakly-supervised Semantic Segmentation via Uncertainty Regularization

Figure 4 for Mixup-CAM: Weakly-supervised Semantic Segmentation via Uncertainty Regularization

* Accepted at BMVC 2020

Access Paper or Ask Questions

Weakly-Supervised Semantic Segmentation via Sub-category Exploration

Aug 03, 2020
Yu-Ting Chang, Qiaosong Wang, Wei-Chih Hung, Robinson Piramuthu, Yi-Hsuan Tsai, Ming-Hsuan Yang

Figure 2 for Weakly-Supervised Semantic Segmentation via Sub-category Exploration

Figure 3 for Weakly-Supervised Semantic Segmentation via Sub-category Exploration

Figure 4 for Weakly-Supervised Semantic Segmentation via Sub-category Exploration

* Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020

Access Paper or Ask Questions