319 citations · 384 across the 13 of their papers we have counts for
13 papers
MinMaxCAM: Improving object coverage for CAM-basedWeakly Supervised Object Localization
Kaili Wang, Jose Oramas, Tinne Tuytelaars
One of the most common problems of weakly supervised object localization is that of inaccurate object coverage. In the context of state-of-the-art methods based on Class Activation…
Towards Human-Understandable Visual Explanations:Imperceptible High-frequency Cues Can Better Be Removed
Kaili Wang, Jose Oramas, Tinne Tuytelaars
Explainable AI (XAI) methods focus on explaining what a neural network has learned - in other words, identifying the features that are the most influential to the prediction. In th…
Can the state of relevant neurons in a deep neural networks serve as indicators for detecting adversarial attacks?
Roger Granda, Tinne Tuytelaars, Jose Oramas
We present a method for adversarial attack detection based on the inspection of a sparse set of neurons. We follow the hypothesis that adversarial attacks introduce imperceptible p…
Multiple Exemplars-based Hallucinationfor Face Super-resolution and Editing
Kaili Wang, Jose Oramas, Tinne Tuytelaars
Given a really low-resolution input image of a face (say 16x16 or 8x8 pixels), the goal of this paper is to reconstruct a high-resolution version thereof. This, by itself, is an il…
Information Compensation for Deep Conditional Generative Networks
Zehao Wang, Kaili Wang, Tinne Tuytelaars +1
In recent years, unsupervised/weakly-supervised conditional generative adversarial networks (GANs) have achieved many successes on the task of modeling and generating data. However…
In Defense of LSTMs for Addressing Multiple Instance Learning Problems
Kaili Wang, Jose Oramas, Tinne Tuytelaars
LSTMs have a proven track record in analyzing sequential data. But what about unordered instance bags, as found under a Multiple Instance Learning (MIL) setting? While not often us…
Visual Explanation by Interpretation: Improving Visual Feedback Capabilities of Deep Neural Networks
Jose Oramas, Kaili Wang, Tinne Tuytelaars
Interpretation and explanation of deep models is critical towards wide adoption of systems that rely on them. In this paper, we propose a novel scheme for both interpretation as we…
An Analysis of Human-centered Geolocation
Kaili Wang, Yu-Hui Huang, Jose Oramas +2
Online social networks contain a constantly increasing amount of images - most of them focusing on people. Due to cultural and climate factors, fashion trends and physical appearan…
Context-based Object Viewpoint Estimation: A 2D Relational Approach
Jose Oramas, Luc De Raedt, Tinne Tuytelaars
The task of object viewpoint estimation has been a challenge since the early days of computer vision. To estimate the viewpoint (or pose) of an object, people have mostly looked at…
Reasoning about Body-Parts Relations for Sign Language Recognition
Marc Martínez-Camarena, Jose Oramas, Mario Montagud-Climent +1
Over the years, hand gesture recognition has been mostly addressed considering hand trajectories in isolation. However, in most sign languages, hand gestures are defined on a parti…
Modeling Visual Compatibility through Hierarchical Mid-level Elements
Jose Oramas, Tinne Tuytelaars
In this paper we present a hierarchical method to discover mid-level elements with the objective of modeling visual compatibility between objects. At the base-level, our method ide…
Rank Pooling for Action Recognition
Basura Fernando, Efstratios Gavves, Jose Oramas +2
We propose a function-based temporal pooling method that captures the latent structure of the video sequence data - e.g. how frame-level features evolve over time in a video. We sh…
Recovering hard-to-find object instances by sampling context-based object proposals
Jose Oramas M., Tinne Tuytelaars
In this paper we focus on improving object detection performance in terms of recall. We propose a post-detection stage during which we explore the image with the objective of recov…