Katerina Fragkiadaki

发表

Recurrent Network Models for Kinematic Tracking pdf

Jitendra Malik, Sergey Levine, Katerina Fragkiadaki, 2015, ArXiv.

The three R's of computer vision: Recognition, reconstruction and reorganization

Jitendra Malik, Katerina Fragkiadaki, Saurabh Gupta, 2016, Pattern Recognit. Lett..

Learning Visual Predictive Models of Physics for Playing Billiards pdf

Jitendra Malik, Sergey Levine, Katerina Fragkiadaki, 2015, ICLR.

Learning to segment moving objects in videos

Jitendra Malik, Katerina Fragkiadaki, Pablo Andrés Arbeláez, 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

Recurrent Network Models for Human Dynamics

Jitendra Malik, Sergey Levine, Katerina Fragkiadaki, 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

HyperDynamics: Meta-Learning Object and Agent Dynamics with Hypernetworks pdf

Shamit Lal, Katerina Fragkiadaki, Emmanouil Antonios Platanios, 2021, ICLR.

3D-OES: Viewpoint-Invariant Object-Factorized Environment Simulators

Katerina Fragkiadaki, H. Tung, Shamit Lal, 2020, CoRL.

Grouping-Based Low-Rank Trajectory Completion and 3D Reconstruction

Jitendra Malik, Katerina Fragkiadaki, Pablo Andrés Arbeláez, 2014, NIPS.

Human Pose Estimation with Iterative Error Feedback

Jitendra Malik, Katerina Fragkiadaki, João Carreira, 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

SfM-Net: Learning of Structure and Motion from Video pdf

Cordelia Schmid, Katerina Fragkiadaki, Rahul Sukthankar, 2017, ArXiv.

Detection free tracking: Exploiting motion and topology for segmenting and tracking under entanglement

Katerina Fragkiadaki, Jianbo Shi, Katerina Fragkiadaki, 2011, CVPR 2011.

Geometry-Aware Recurrent Neural Networks for Active Visual Recognition

Katerina Fragkiadaki, Ziyan Wang, Ricson Cheng, 2018, NeurIPS.

Embodied View-Contrastive 3D Feature Learning pdf

Katerina Fragkiadaki, Fangyu Li, Xian Zhou, 2019, ArXiv.

Embodied Language Grounding with Implicit 3D Visual Feature Representations pdf

Mihir Prabhudesai, Katerina Fragkiadaki, Adam W. Harley, 2019, ArXiv.

Smart And Autonomous Systems For Repair And Improvisation

C. Atkeson, Katerina Fragkiadaki, 2018 .

ROBLEMS IN C OMPUTER V ISION USING A DVERSARIAL I MAGINATION P RIORS

Katerina Fragkiadaki, H. Tung, 2016 .

Learning Feature Hierarchies from Long-Range Temporal Associations in Videos

Jitendra Malik, Katerina Fragkiadaki, Panna Felsen, 2016 .

Likelihood-free Inference of Fornax Dark Matter Density Profile

Katerina Fragkiadaki, M. Walker, Mao-Sheng Liu, 2018 .

Structural-Flow Trajectories for Unravelling 3D Tubular Bundles

Katerina Fragkiadaki, Jianbo Shi, Weiyu Zhang, 2012, MICCAI.

Visually-Grounded Library of Behaviors for Manipulating Diverse Objects across Diverse Configurations and Views

C. Atkeson, Katerina Fragkiadaki, H. Tung, 2021 .

Move to See Better: Self-Improving Embodied Object Detection

Adam W. Harley, Katerina Fragkiadaki, Zhaoyuan Fang, 2021, BMVC.

Looking Outside the Box to Ground Language in 3D Scenes

Katerina Fragkiadaki, N. Gkanatsios, Ishita Mediratta, 2021 .

Bottom Up Top Down Detection Transformers for Language Grounding in Images and Point Clouds

Katerina Fragkiadaki, N. Gkanatsios, Ishita Mediratta, 2021, ECCV.

A Simple Baseline for BEV Perception Without LiDAR

Adam W. Harley, Katerina Fragkiadaki, Rares Ambrus, 2022, ArXiv.

Particle Video Revisited: Tracking Through Occlusions Using Point Trajectories

Adam W. Harley, Katerina Fragkiadaki, Zhaoyuan Fang, 2022, ECCV.

Learning to segment moving objects in videos

Pablo Arbeláez, Jitendra Malik, Katerina Fragkiadaki, 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

Planning with Spatial-Temporal Abstraction from Point Clouds for Deformable Object Manipulation

David Held, Katerina Fragkiadaki, Yunzhu Li, 2022, CoRL.

TIDEE: Tidying Up Novel Rooms using Visuo-Semantic Commonsense Priors

Adam W. Harley, M. Tarr, Katerina Fragkiadaki, 2022, ECCV.

Test-time adaptation with slot-centric models

Sjoerd van Steenkiste, Mehdi S. M. Sajjadi, Thomas Kipf, 2022, 2203.11194.

Graph-Structured Visual Imitation pdf

Oliver Kroemer, Katerina Fragkiadaki, Maximilian Sieb, 2019, CoRL.

Data Dreaming for Object Detection: Learning Object-Centric State Representations for Visual Imitation

Katerina Fragkiadaki, Maximilian Sieb, Katerina Fragkiadaki, 2018, 2018 IEEE-RAS 18th International Conference on Humanoid Robots (Humanoids).

Not for distribution COVER SHEET FOR PROPOSAL TO THE NATIONAL SCIENCE FOUNDATION

Katerina Fragkiadaki, Katerina Fragkiadaki, Seth L Danielson, 2015 .

Track, Check, Repeat: An EM Approach to Unsupervised Tracking

Katerina Fragkiadaki, Adam W. Harley, Ayush Mangal, 2021, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

Figure-Ground Image Segmentation Helps Weakly-Supervised Learning of Objects

Katerina Fragkiadaki, Jianbo Shi, Katerina Fragkiadaki, 2010, ECCV.

Model Learning for Look-ahead Exploration in Continuous Control pdf

Arpit Agarwal, Katerina Fragkiadaki, Katharina Muelling, 2018, AAAI.

Predictive Visual Models of Physics for Playing Billiards

S. Levine, Jitendra Malik, Katerina Fragkiadaki, 2015 .

Self-supervised Learning of Motion Capture

Ersin Yumer, Katerina Fragkiadaki, Hsiao-Yu Fish Tung, 2017, NIPS.

Simple-BEV: What Really Matters for Multi-Sensor BEV Perception?

Adam W. Harley, Katerina Fragkiadaki, Rares Ambrus, 2022, 2023 IEEE International Conference on Robotics and Automation (ICRA).

Adversarial Inverse Graphics Networks: Learning 2D-to-3D Lifting and Image-to-Image Translation from Unpaired Supervision

Katerina Fragkiadaki, Adam W. Harley, Hsiao-Yu Fish Tung, 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

Analogy-Forming Transformers for Few-Shot 3D Parsing

Katerina Fragkiadaki, Shubham Tulsiani, N. Gkanatsios, 2023, 2304.14382.

3D-OES: Viewpoint-Invariant Object-Factorized Environment Simulators pdf

Mihir Prabhudesai, Shamit Lal, Katerina Fragkiadaki, 2020, CoRL.

Reinforcement Learning of Active Vision for Manipulating Objects under Occlusions

Arpit Agarwal, Katerina Fragkiadaki, Ricson Cheng, 2018, CoRL.

FluidLab: A Differentiable Environment for Benchmarking Complex Fluid Manipulation

A. Torralba, Katerina Fragkiadaki, H. Tung, 2023, ICLR.

Energy-based Models as Zero-Shot Planners for Compositional Scene Rearrangement

C. Atkeson, Katerina Fragkiadaki, Zhou Xian, 2023, ArXiv.

Video segmentation by tracing discontinuities in a trajectory embedding

Katerina Fragkiadaki, Jianbo Shi, Geng Zhang, 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

Embodied Language Grounding With 3D Visual Feature Representations

Adam W. Harley, Katerina Fragkiadaki, H. Tung, 2019, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

Embodied Language Grounding with Implicit 3D Visual Feature Representations

Adam W. Harley, Katerina Fragkiadaki, H. Tung, 2019, ArXiv.

Learning Spatial Common Sense With Geometry-Aware Recurrent Networks

Katerina Fragkiadaki, Hsiao-Yu Fish Tung, Ricson Cheng, 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

CoCoNets: Continuous Contrastive 3D Scene Representations

Mihir Prabhudesai, Shamit Lal, Katerina Fragkiadaki, 2021, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

Motion Prediction Under Multimodality with Conditional Stochastic Networks pdf

Katerina Fragkiadaki, Rahul Sukthankar, Alex Alemi, 2017, ArXiv.

Disentangling 3D Prototypical Networks For Few-Shot Concept Learning

Adam W. Harley, Katerina Fragkiadaki, H. Tung, 2020, ICLR.

Generating Fast and Slow: Scene Decomposition via Reconstruction

Katerina Fragkiadaki, Deepak Pathak, Mihir Prabhudesai, 2022, ArXiv.

Pose from Flow and Flow from Pose

Katerina Fragkiadaki, Jianbo Shi, Han Hu, 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

Planning with Spatial-Temporal Abstraction from Point Clouds for Deformable Object Manipulation

David Held, Katerina Fragkiadaki, Yunzhu Li, 2022, CoRL.

Epipolar Transformers

Katerina Fragkiadaki, Yihui He, Shoou-I Yu, 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

F LUID L AB : A D IFFERENTIABLE E NVIRONMENT FOR B ENCHMARKING C OMPLEX F LUID M ANIPULATION

Katerina Fragkiadaki, Zhou Xian, Zhenjia Xu, 2023 .

3D Object Recognition By Corresponding and Quantizing Neural 3D Scene Representations pdf

Mihir Prabhudesai, Shamit Lal, Katerina Fragkiadaki, 2020, ArXiv.

Learning from Unlabelled Videos Using Contrastive Predictive Neural 3D Mapping

Katerina Fragkiadaki, Fangyu Li, Adam W. Harley, 2019, ICLR.

Visual Representation Learning with 3D View-Contrastive Inverse Graphics Networks

Katerina Fragkiadaki, Fangyu Li, Adam W. Harley, 2019, ICLR 2020.

Move to See Better: Towards Self-Supervised Amodal Object Detection pdf

Katerina Fragkiadaki, Adam W. Harley, Zhaoyuan Fang, 2020, ArXiv.

Epipolar Transformer for Multi-view Human Pose Estimation

Katerina Fragkiadaki, Yihui He, Shoou-I Yu, 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

Act3D: 3D Feature Field Transformers for Multi-Task Robotic Manipulation

Katerina Fragkiadaki, Zhou Xian, N. Gkanatsios, 2023, 2306.17817.

Energy-based Models are Zero-Shot Planners for Compositional Scene Rearrangement

C. Atkeson, Katerina Fragkiadaki, Zhou Xian, 2023, Robotics: Science and Systems.

Material for “ Adversarial Inverse Graphics Networks : Learning 2 Dto-3 D Lifting and Image-to-Image Translation from Unpaired Supervision ”

Katerina Fragkiadaki, Adam W. Harley, Hsiao-Yu Fish Tung, 2017 .

Test-time Adaptation with Slot-Centric Models

Sjoerd van Steenkiste, Mehdi S. M. Sajjadi, Thomas Kipf, 2022, ICML.

Reward Learning from Narrated Demonstrations

Katerina Fragkiadaki, Adam W. Harley, Hsiao-Yu Fish Tung, 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

Embodied Symbiotic Assistants that See, Act, Infer and Chat

Katerina Fragkiadaki, Xian Zhou, Shikhar Sharma, 2023 .

Analogy-Forming Transformers for Few-Shot 3D Parsing

Katerina Fragkiadaki, Shubham Tulsiani, M. Singh, 2023, ICLR.

Open-Ended Instructable Embodied Agents with Memory-Augmented Large Language Models

Katerina Fragkiadaki, Gabriel H. Sarch, Yue Wu, 2023, EMNLP.

Energy-based Models as Zero-Shot Planners for Compositional Scene Rearrangement

C. Atkeson, Katerina Fragkiadaki, Zhou Xian, 2023, ArXiv.

ChainedDiffuser: Unifying Trajectory Diffusion and Keypose Prediction for Robotic Manipulation

Katerina Fragkiadaki, Zhou Xian, N. Gkanatsios, 2023, CoRL.

RoboGen: Towards Unleashing Infinite Data for Automated Robot Learning via Generative Simulation

Zackory M. Erickson, Katerina Fragkiadaki, Zhou Xian, 2023, ArXiv.

Gen2Sim: Scaling up Robot Learning in Simulation with Generative Models

Katerina Fragkiadaki, Zhou Xian, Pushkal Katara, 2023, ArXiv.

Tracking Emerges by Looking Around Static Scenes, with Neural 3D Mapping

Adam W. Harley, Katerina Fragkiadaki, S. K. Lakshmikanth, 2020, ECCV.

Zero-Shot Open-Vocabulary Tracking with Large Pre-Trained Models

Adam W. Harley, Katerina Fragkiadaki, Achal Dave, 2023, 2310.06992.

Particle Videos Revisited: Tracking Through Occlusions Using Point Trajectories

Adam W. Harley, Katerina Fragkiadaki, Zhaoyuan Fang, 2022, ArXiv.

Brain Dissection: fMRI-trained Networks Reveal Spatial Selectivity in the Processing of Natural Images

Katerina Fragkiadaki, M. Tarr, Katerina Fragkiadaki, 2023, bioRxiv.

Image Disentanglement and Uncooperative Re-Entanglement for High-Fidelity Image-to-Image Translation

Katerina Fragkiadaki, Adam W. Harley, Shih-En Wei, 2019, 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW).

ODIN: A Single Model for 2D and 3D Perception

Adam W. Harley, Katerina Fragkiadaki, Vishrav Chaudhary, 2024, ArXiv.

Detection free tracking: Exploiting motion and topology for segmenting and tracking under entanglement

Katerina Fragkiadaki, Jianbo Shi, 2011, CVPR 2011.

Diffusion-ES: Gradient-free Planning with Diffusion for Autonomous Driving and Zero-Shot Instruction Following

Katerina Fragkiadaki, N. Gkanatsios, Ayush Jain, 2024, ArXiv.

Aligning Text-to-Image Diffusion Models with Reward Backpropagation

Katerina Fragkiadaki, Mihir Prabhudesai, Anirudh Goyal, 2023, ArXiv.

Learning to segment moving objects in videos

Pablo Arbeláez, Jitendra Malik, Katerina Fragkiadaki, 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

Adversarial Generation of Acoustic Waves with Pair Supervision

Katerina Fragkiadaki, Hongyu Zhu, 2018 .

3DQ-Nets: Visual Concepts Emerge in Pose Equivariant 3D Quantized Neural Scene Representations

Mihir Prabhudesai, Shamit Lal, Katerina Fragkiadaki, 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

Depth-Adaptive Computational Policies for Efficient Visual Tracking

Katerina Fragkiadaki, Chris Ying, Katerina Fragkiadaki, 2017, EMMCVPR.

Two-Granularity Tracking: Mediating Trajectory and Detection Graphs for Tracking under Occlusions

Katerina Fragkiadaki, Jianbo Shi, Weiyu Zhang, 2012, ECCV.

ICAL: Continual Learning of Multimodal Agents by Transforming Trajectories into Actionable Insights

Katerina Fragkiadaki, Gabriel H. Sarch, Michael J. Tarr, 2024, 2406.14596.