João F. Henriques

17

Papers

538

Total Citations

Papers (17)

Learning feed-forward one-shot learners

NeurIPS 2016arXiv

Text2Loc: 3D Point Cloud Localization from Natural Language

Towards Real-World Navigation With Deep Differentiable Planners

A Light Touch Approach to Teaching Transformers Multi-View Geometry

On Compositions of Transformations in Contrastive Self-Supervised Learning

Space-Time Crop & Attend: Improving Cross-Modal Video Representation Learning

LoCUS: Learning Multiscale 3D-consistent Features from Posed Images

RbA: Segmenting Unknown Regions Rejected by All

360(o) Camera Alignment via Segmentation

SNeS: Learning Probably Symmetric Neural Surfaces from Incomplete Data

Rapid Motor Adaptation for Robotic Manipulator Arms

MapNet: An Allocentric Spatial Memory for Mapping Environments

Keeping Your Eye on the Ball: Trajectory Attention in Video Transformers

Learn what matters: cross-domain imitation learning with task-relevant embeddings

Contrastive Lift: 3D Object Instance Segmentation by Slow-Fast Contrastive Fusion

Extracting Reward Functions from Diffusion Models

Warped Convolutions: Efficient Invariance to Spatial Transformations