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challenge to current state-of-the-art recognition pipelines, since the assumption of a mostly upright camera is no longer valid.
no code implementations • 16 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.
no code implementations • 29 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.
no code implementations • 19 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.
1 code implementation • 18 Jan 2024 • Shu Ishida, Gianluca Corrado, George Fedoseev, Hudson Yeo, Lloyd Russell, Jamie Shotton, João F. Henriques, Anthony Hu
LangProp is a framework for iteratively optimizing code generated by large language models (LLMs) in a supervised/reinforcement learning setting.
no code implementations • 27 Nov 2023 • 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.
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.
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.
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.
no code implementations • 2 Apr 2023 • Samuel Albanie, Liliane Momeni, João F. Henriques
Driven by recent advances AI, we passengers are entering a golden age of scientific discovery.
no code implementations • 23 Mar 2023 • Stephanie Milani, Anssi Kanervisto, Karolis Ramanauskas, Sander Schulhoff, Brandon Houghton, Sharada Mohanty, Byron Galbraith, Ke Chen, Yan Song, Tianze Zhou, Bingquan Yu, He Liu, Kai Guan, Yujing Hu, Tangjie Lv, Federico Malato, Florian Leopold, Amogh Raut, Ville Hautamäki, Andrew Melnik, Shu Ishida, João F. Henriques, Robert Klassert, Walter Laurito, Ellen Novoseller, Vinicius G. Goecks, Nicholas Waytowich, David Watkins, Josh Miller, Rohin Shah
To facilitate research in the direction of fine-tuning foundation models from human feedback, we held the MineRL BASALT Competition on Fine-Tuning from Human Feedback at NeurIPS 2022.
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)
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.
no code implementations • 24 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.
no code implementations • 20 Jul 2022 • Tim Franzmeyer, Stephen Mcaleer, João F. Henriques, Jakob N. Foerster, Philip H. S. Torr, Adel Bibi, Christian Schroeder de Witt
Autonomous agents deployed in the real world need to be robust against adversarial attacks on sensory inputs.
no code implementations • 13 Jun 2022 • Eldar Insafutdinov, Dylan Campbell, João F. Henriques, Andrea Vedaldi
We present a method for the accurate 3D reconstruction of partly-symmetric objects.
no code implementations • 31 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.
1 code implementation • 17 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.
Ranked #1 on Audio to Text Retrieval on SoundDescs
no code implementations • 25 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.
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.
no code implementations • ICLR 2022 • Tim Franzmeyer, Mateusz Malinowski, João F. Henriques
Such an approach assumes that other agents' goals are known so that the altruistic agent can cooperate in achieving those goals.
2 code implementations • NeurIPS 2021 • Mandela Patrick, Dylan Campbell, Yuki M. Asano, Ishan Misra, Florian Metze, Christoph Feichtenhofer, Andrea Vedaldi, João F. Henriques
In video transformers, the time dimension is often treated in the same way as the two spatial dimensions.
Ranked #15 on Action Recognition on EPIC-KITCHENS-100 (using extra training data)
1 code implementation • 5 May 2021 • Andreea-Maria Oncescu, A. Sophia Koepke, João F. Henriques, Zeynep Akata, Samuel Albanie
We consider the task of retrieving audio using free-form natural language queries.
Ranked #1 on Audio/Video to Text Retrieval on AudioCaps
2 code implementations • 22 Nov 2020 • Andreea-Maria Oncescu, João F. Henriques, Yang Liu, Andrew Zisserman, Samuel Albanie
We introduce QuerYD, a new large-scale dataset for retrieval and event localisation in video.
1 code implementation • ICCV 2021 • Mandela Patrick, Yuki M. Asano, Polina Kuznetsova, Ruth Fong, João F. Henriques, Geoffrey Zweig, Andrea Vedaldi
In the image domain, excellent representations can be learned by inducing invariance to content-preserving transformations via noise contrastive learning.
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.
Ranked #1 on Unsupervised MNIST on MNIST
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.
1 code implementation • 21 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.
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.
no code implementations • ECCV 2018 • Jack Valmadre, Luca Bertinetto, João F. Henriques, Ran Tao, Andrea Vedaldi, Arnold Smeulders, Philip Torr, Efstratios Gavves
We introduce the OxUvA dataset and benchmark for evaluating single-object tracking algorithms.
no code implementations • CVPR 2017 • Jack Valmadre, Luca Bertinetto, João F. Henriques, Andrea Vedaldi, Philip H. S. Torr
The Correlation Filter is an algorithm that trains a linear template to discriminate between images and their translations.
Ranked #3 on Visual Object Tracking on OTB-50
1 code implementation • 7 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.
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.
10 code implementations • 30 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.
Ranked #3 on Visual Object Tracking on OTB-50
no code implementations • NeurIPS 2016 • Luca Bertinetto, João F. Henriques, Jack Valmadre, Philip H. S. Torr, Andrea Vedaldi
In this paper, we propose a method to learn the parameters of a deep model in one shot.
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.
9 code implementations • 30 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.