Katerina Fragkiadaki

26

Papers

422

Total Citations

Papers (26)

Self-supervised Learning of Motion Capture

NeurIPS 2017arXiv

PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers

Video Depth without Video Models

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

AllTracker: Efficient Dense Point Tracking at High Resolution

Unifying 2D and 3D Vision-Language Understanding

Reward Learning From Narrated Demonstrations

Learning Spatial Common Sense With Geometry-Aware Recurrent Networks

Embodied Language Grounding With 3D Visual Feature Representations

CoCoNets: Continuous Contrastive 3D Scene Representations

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

Recurrent Network Models for Human Dynamics

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

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

Particle Video Revisited: Tracking through Occlusions Using Point Trajectories

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

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

Epipolar Transformers

Robust Multi-Object 4D Generation for In-the-wild Videos

Diffusion-ES: Gradient-free Planning with Diffusion for Autonomous and Instruction-guided Driving

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

Learning to Segment Moving Objects in Videos

Human Pose Estimation With Iterative Error Feedback

Geometry-Aware Recurrent Neural Networks for Active Visual Recognition

Diffusion-TTA: Test-time Adaptation of Discriminative Models via Generative Feedback

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