86 citations · 296 across the 22 of their papers we have counts for
30 papers
End-to-End (Instance)-Image Goal Navigation through Correspondence as an Emergent Phenomenon
Guillaume Bono, Leonid Antsfeld, Boris Chidlovskii +2
Most recent work in goal oriented visual navigation resorts to large-scale machine learning in simulated environments. The main challenge lies in learning compact representations g…
Filtered-CoPhy: Unsupervised Learning of Counterfactual Physics in Pixel Space
Steeven Janny, Fabien Baradel, Natalia Neverova +3
Learning causal relationships in high-dimensional data (images, videos) is a hard task, as they are often defined on low dimensional manifolds and must be extracted from complex si…
Satellite Image Semantic Segmentation
Eric Guérin, Killian Oechslin, Christian Wolf +1
In this paper, we propose a method for the automatic semantic segmentation of satellite images into six classes (sparse forest, dense forest, moor, herbaceous formation, building,…
SIM2REALVIZ: Visualizing the Sim2Real Gap in Robot Ego-Pose Estimation
Theo Jaunet, Guillaume Bono, Romain Vuillemot +1
The Robotics community has started to heavily rely on increasingly realistic 3D simulators for large-scale training of robots on massive amounts of data. But once robots are deploy…
Teaching Agents how to Map: Spatial Reasoning for Multi-Object Navigation
Pierre Marza, Laetitia Matignon, Olivier Simonin +1
In the context of visual navigation, the capacity to map a novel environment is necessary for an agent to exploit its observation history in the considered place and efficiently re…
Supervising the Transfer of Reasoning Patterns in VQA
Corentin Kervadec, Christian Wolf, Grigory Antipov +2
Methods for Visual Question Anwering (VQA) are notorious for leveraging dataset biases rather than performing reasoning, hindering generalization. It has been recently shown that b…
Universal Domain Adaptation in Ordinal Regression
Boris Chidlovskii, Assem Sadek, Christian Wolf
We address the problem of universal domain adaptation (UDA) in ordinal regression (OR), which attempts to solve classification problems in which labels are not independent, but fol…
How Transferable are Reasoning Patterns in VQA?
Corentin Kervadec, Theo Jaunet, Grigory Antipov +3
Since its inception, Visual Question Answering (VQA) is notoriously known as a task, where models are prone to exploit biases in datasets to find shortcuts instead of performing hi…
VisQA: X-raying Vision and Language Reasoning in Transformers
Theo Jaunet, Corentin Kervadec, Romain Vuillemot +3
Visual Question Answering systems target answering open-ended textual questions given input images. They are a testbed for learning high-level reasoning with a primary use in HCI,…
SSTVOS: Sparse Spatiotemporal Transformers for Video Object Segmentation
Brendan Duke, Abdalla Ahmed, Christian Wolf +2
In this paper we introduce a Transformer-based approach to video object segmentation (VOS). To address compounding error and scalability issues of prior work, we propose a scalable…
Learning to plan with uncertain topological maps
Edward Beeching, Jilles Dibangoye, Olivier Simonin +1
We train an agent to navigate in 3D environments using a hierarchical strategy including a high-level graph based planner and a local policy. Our main contribution is a data driven…
Estimating semantic structure for the VQA answer space
Corentin Kervadec, Grigory Antipov, Moez Baccouche +1
Since its appearance, Visual Question Answering (VQA, i.e. answering a question posed over an image), has always been treated as a classification problem over a set of predefined a…
Roses Are Red, Violets Are Blue... but Should Vqa Expect Them To?
Corentin Kervadec, Grigory Antipov, Moez Baccouche +1
Models for Visual Question Answering (VQA) are notorious for their tendency to rely on dataset biases, as the large and unbalanced diversity of questions and concepts involved and…
EgoMap: Projective mapping and structured egocentric memory for Deep RL
Edward Beeching, Christian Wolf, Jilles Dibangoye +1
Tasks involving localization, memorization and planning in partially observable 3D environments are an ongoing challenge in Deep Reinforcement Learning. We present EgoMap, a spatia…
Weak Supervision helps Emergence of Word-Object Alignment and improves Vision-Language Tasks
Corentin Kervadec, Grigory Antipov, Moez Baccouche +1
The large adoption of the self-attention (i.e. transformer model) and BERT-like training principles has recently resulted in a number of high performing models on a large panoply o…
CoPhy: Counterfactual Learning of Physical Dynamics
Fabien Baradel, Natalia Neverova, Julien Mille +2
Understanding causes and effects in mechanical systems is an essential component of reasoning in the physical world. This work poses a new problem of counterfactual learning of obj…
DRLViz: Understanding Decisions and Memory in Deep Reinforcement Learning
Theo Jaunet, Romain Vuillemot, Christian Wolf
We present DRLViz, a visual analytics interface to interpret the internal memory of an agent (e.g. a robot) trained using deep reinforcement learning. This memory is composed of la…
Deep Reinforcement Learning on a Budget: 3D Control and Reasoning Without a Supercomputer
Edward Beeching, Christian Wolf, Jilles Dibangoye +1
An important goal of research in Deep Reinforcement Learning in mobile robotics is to train agents capable of solving complex tasks, which require a high level of scene understandi…
Learning 3D Navigation Protocols on Touch Interfaces with Cooperative Multi-Agent Reinforcement Learning
Quentin Debard, Jilles Steeve Dibangoye, Stéphane Canu +1
Using touch devices to navigate in virtual 3D environments such as computer assisted design (CAD) models or geographical information systems (GIS) is inherently difficult for human…
Object Level Visual Reasoning in Videos
Fabien Baradel, Natalia Neverova, Christian Wolf +2
Human activity recognition is typically addressed by detecting key concepts like global and local motion, features related to object classes present in the scene, as well as featur…
Learning to recognize touch gestures: recurrent vs. convolutional features and dynamic sampling
Quentin Debard, Christian Wolf, Stéphane Canu +1
We propose a fully automatic method for learning gestures on big touch devices in a potentially multi-user context. The goal is to learn general models capable of adapting to diffe…
Glimpse Clouds: Human Activity Recognition from Unstructured Feature Points
Fabien Baradel, Christian Wolf, Julien Mille +1
We propose a method for human activity recognition from RGB data that does not rely on any pose information during test time and does not explicitly calculate pose information inte…
Human Action Recognition: Pose-based Attention draws focus to Hands
Fabien Baradel, Christian Wolf, Julien Mille
We propose a new spatio-temporal attention based mechanism for human action recognition able to automatically attend to the hands most involved into the studied action and detect t…
Multi-view pose estimation with mixtures-of-parts and adaptive viewpoint selection
Emre Dogan, Gonen Eren, Christian Wolf +2
We propose a new method for human pose estimation which leverages information from multiple views to impose a strong prior on articulated pose. The novelty of the method concerns t…