Search Results for author:
Found 6 papers, 4 papers with code
4M: Massively Multimodal Masked Modeling
Current machine learning models for vision are often highly specialized and limited to a single modality and task.
Modality-invariant Visual Odometry for Embodied Vision
Our model outperforms previous methods while training on only a fraction of the data.
MultiMAE: Multi-modal Multi-task Masked Autoencoders
We show this pre-training strategy leads to a flexible, simple, and efficient framework with improved transfer results to downstream tasks.
Ranked #1 on
Semantic Segmentation
on Hypersim
Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scans
This paper introduces a pipeline to parametrically sample and render multi-task vision datasets from comprehensive 3D scans from the real world.
Training Binary Neural Networks using the Bayesian Learning Rule
Our work provides a principled approach for training binary neural networks which justifies and extends existing approaches.
Motion Capture from Pan-Tilt Cameras with Unknown Orientation
We propose a method for estimating an athlete's global 3D position and articulated pose using multiple cameras.
