Search Results for author: João F. Henriques

Found 41 papers, 18 papers with code

360(o) Camera Alignment via Segmentation

no code implementations ECCV 2020 Benjamin Davidson, Mohsan S. Alvi, João F. Henriques

Panoramic 360º images taken under unconstrained conditions present a significant challenge to current state-of-the-art recognition pipelines, since the assumption of a mostly upright camera is no longer valid.

Segmentation valid

Unsupervised Object Detection with Theoretical Guarantees

no code implementations11 Jun 2024 Marian Longa, João F. Henriques

Unsupervised object detection using deep neural networks is typically a difficult problem with few to no guarantees about the learned representation.

Decoder Object +3

HelloFresh: LLM Evaluations on Streams of Real-World Human Editorial Actions across X Community Notes and Wikipedia edits

no code implementations5 Jun 2024 Tim Franzmeyer, Aleksandar Shtedritski, Samuel Albanie, Philip Torr, João F. Henriques, Jakob N. Foerster

Verifying whether an X note is helpful or whether a Wikipedia edit should be accepted are hard tasks that require grounding by querying the web.

RapidVol: Rapid Reconstruction of 3D Ultrasound Volumes from Sensorless 2D Scans

no code implementations16 Apr 2024 Mark C. Eid, Pak-Hei Yeung, Madeleine K. Wyburd, João F. Henriques, Ana I. L. Namburete

Two-dimensional (2D) freehand ultrasonography is one of the most commonly used medical imaging modalities, particularly in obstetrics and gynaecology.

3D Reconstruction

N2F2: Hierarchical Scene Understanding with Nested Neural Feature Fields

no code implementations16 Mar 2024 Yash Bhalgat, Iro Laina, João F. Henriques, Andrew Zisserman, Andrea Vedaldi

To address this, we introduce Nested Neural Feature Fields (N2F2), a novel approach that employs hierarchical supervision to learn a single feature field, wherein different dimensions within the same high-dimensional feature encode scene properties at varying granularities.

Scene Understanding

A SOUND APPROACH: Using Large Language Models to generate audio descriptions for egocentric text-audio retrieval

no code implementations29 Feb 2024 Andreea-Maria Oncescu, João F. Henriques, Andrew Zisserman, Samuel Albanie, A. Sophia Koepke

Furthermore, we show that using the same prompts, we can successfully employ LLMs to improve the retrieval on EpicSounds, compared to using the original audio class labels of the dataset.

Retrieval

SCENES: Subpixel Correspondence Estimation With Epipolar Supervision

no code implementations19 Jan 2024 Dominik A. Kloepfer, João F. Henriques, Dylan Campbell

We relax this assumption by removing the requirement of 3D structure, e. g., depth maps or point clouds, and only require camera pose information, which can be obtained from odometry.

Pose Estimation

LangProp: A code optimization framework using Large Language Models applied to driving

1 code implementation18 Jan 2024 Shu Ishida, Gianluca Corrado, George Fedoseev, Hudson Yeo, Lloyd Russell, Jamie Shotton, João F. Henriques, Anthony Hu

LangProp automatically evaluates the code performance on a dataset of input-output pairs, catches any exceptions, and feeds the results back to the LLM in the training loop, so that the LLM can iteratively improve the code it generates.

Autonomous Driving Code Generation +2

Text2Loc: 3D Point Cloud Localization from Natural Language

no code implementations CVPR 2024 Yan Xia, Letian Shi, Zifeng Ding, João F. Henriques, Daniel Cremers

We tackle the problem of 3D point cloud localization based on a few natural linguistic descriptions and introduce a novel neural network, Text2Loc, that fully interprets the semantic relationship between points and text.

Contrastive Learning

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

no code implementations ICCV 2023 Dominik A. Kloepfer, Dylan Campbell, João F. Henriques

We start from the idea that the training objective can be framed as a patch retrieval problem: given an image patch in one view of a scene, we would like to retrieve (with high precision and recall) all patches in other views that map to the same real-world location.

Instance Segmentation Retrieval +1

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

1 code implementation NeurIPS 2023 Yash Bhalgat, Iro Laina, João F. Henriques, Andrew Zisserman, Andrea Vedaldi

Our approach outperforms the state-of-the-art on challenging scenes from the ScanNet, Hypersim, and Replica datasets, as well as on our newly created Messy Rooms dataset, demonstrating the effectiveness and scalability of our slow-fast clustering method.

Clustering Instance Segmentation +2

Extracting Reward Functions from Diffusion Models

1 code implementation NeurIPS 2023 Felipe Nuti, Tim Franzmeyer, João F. Henriques

Diffusion models have achieved remarkable results in image generation, and have similarly been used to learn high-performing policies in sequential decision-making tasks.

Decision Making Image Generation

Large Language Models are Few-shot Publication Scoopers

no code implementations2 Apr 2023 Samuel Albanie, Liliane Momeni, João F. Henriques

Driven by recent advances AI, we passengers are entering a golden age of scientific discovery.

RbA: Segmenting Unknown Regions Rejected by All

1 code implementation ICCV 2023 Nazir Nayal, Mısra Yavuz, João F. Henriques, Fatma Güney

Our extensive experiments show that mask classification improves the performance of the existing outlier detection methods, and the best results are achieved with the proposed RbA.

 Ranked #1 on Anomaly Detection on Road Anomaly (using extra training data)

Anomaly Detection Classification +2

CASSPR: Cross Attention Single Scan Place Recognition

1 code implementation ICCV 2023 Yan Xia, Mariia Gladkova, Rui Wang, Qianyun Li, Uwe Stilla, João F. Henriques, Daniel Cremers

CASSPR uses queries from one branch to try to match structures in the other branch, ensuring that both extract self-contained descriptors of the point cloud (rather than one branch dominating), but using both to inform the output global descriptor of the point cloud.

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

no code implementations24 Sep 2022 Tim Franzmeyer, Philip H. S. Torr, João F. Henriques

We study how an autonomous agent learns to perform a task from demonstrations in a different domain, such as a different environment or different agent.

Imitation Learning

A 23 MW data centre is all you need

no code implementations31 Mar 2022 Samuel Albanie, Dylan Campbell, João F. Henriques

The field of machine learning has achieved striking progress in recent years, witnessing breakthrough results on language modelling, protein folding and nitpickingly fine-grained dog breed classification.

Board Games Language Modelling +1

Audio Retrieval with Natural Language Queries: A Benchmark Study

1 code implementation17 Dec 2021 A. Sophia Koepke, Andreea-Maria Oncescu, João F. Henriques, Zeynep Akata, Samuel Albanie

Additionally, we introduce the SoundDescs benchmark, which consists of paired audio and natural language descriptions for a diverse collection of sounds that are complementary to those found in AudioCaps and Clotho.

AudioCaps Audio captioning +5

Quantised Transforming Auto-Encoders: Achieving Equivariance to Arbitrary Transformations in Deep Networks

no code implementations25 Nov 2021 Jianbo Jiao, João F. Henriques

In this work we investigate how to achieve equivariance to input transformations in deep networks, purely from data, without being given a model of those transformations.

Pose Estimation Translation

Towards real-world navigation with deep differentiable planners

1 code implementation CVPR 2022 Shu Ishida, João F. Henriques

To avoid the potentially hazardous trial-and-error of reinforcement learning, we focus on differentiable planners such as Value Iteration Networks (VIN), which are trained offline from safe expert demonstrations.

Imitation Learning Motion Planning +3

Invariant Information Clustering for Unsupervised Image Classification and Segmentation

6 code implementations ICCV 2019 Xu Ji, João F. Henriques, Andrea Vedaldi

The method is not specialised to computer vision and operates on any paired dataset samples; in our experiments we use random transforms to obtain a pair from each image.

Clustering General Classification +4

Small steps and giant leaps: Minimal Newton solvers for Deep Learning

6 code implementations ICLR 2019 João F. Henriques, Sebastien Ehrhardt, Samuel Albanie, Andrea Vedaldi

Instead, we propose to keep a single estimate of the gradient projected by the inverse Hessian matrix, and update it once per iteration.

Meta-learning with differentiable closed-form solvers

5 code implementations ICLR 2019 Luca Bertinetto, João F. Henriques, Philip H. S. Torr, Andrea Vedaldi

The main idea is to teach a deep network to use standard machine learning tools, such as ridge regression, as part of its own internal model, enabling it to quickly adapt to novel data.

BIG-bench Machine Learning Few-Shot Learning +1

PyTorch CurveBall - A second-order optimizer for deep networks

1 code implementation21 May 2018 João F. Henriques, Sebastien Ehrhardt, Samuel Albanie, Andrea Vedaldi

We propose a fast second-order method that can be used as a drop-in replacementfor current deep learning solvers.

Stopping GAN Violence: Generative Unadversarial Networks

1 code implementation7 Mar 2017 Samuel Albanie, Sébastien Ehrhardt, João F. Henriques

While the costs of human violence have attracted a great deal of attention from the research community, the effects of the network-on-network (NoN) violence popularised by Generative Adversarial Networks have yet to be addressed.

Warped Convolutions: Efficient Invariance to Spatial Transformations

no code implementations ICML 2017 João F. Henriques, Andrea Vedaldi

Convolutional Neural Networks (CNNs) are extremely efficient, since they exploit the inherent translation-invariance of natural images.

Translation

Fully-Convolutional Siamese Networks for Object Tracking

10 code implementations30 Jun 2016 Luca Bertinetto, Jack Valmadre, João F. Henriques, Andrea Vedaldi, Philip H. S. Torr

The problem of arbitrary object tracking has traditionally been tackled by learning a model of the object's appearance exclusively online, using as sole training data the video itself.

Object object-detection +2

Fast Training of Pose Detectors in the Fourier Domain

no code implementations NeurIPS 2014 João F. Henriques, Pedro Martins, Rui F. Caseiro, Jorge Batista

In many datasets, the samples are related by a known image transformation, such as rotation, or a repeatable non-rigid deformation.

Pose Estimation

High-Speed Tracking with Kernelized Correlation Filters

9 code implementations30 Apr 2014 João F. Henriques, Rui Caseiro, Pedro Martins, Jorge Batista

Interestingly, for linear regression our formulation is equivalent to a correlation filter, used by some of the fastest competitive trackers.

regression Vocal Bursts Intensity Prediction

Cannot find the paper you are looking for? You can Submit a new open access paper.