
-
A Survey on Neural Network Interpretability
Along with the great success of deep neural networks, there is also grow...
read it
-
Diagnosing and Preventing Instabilities in Recurrent Video Processing
Recurrent models are becoming a popular choice for video enhancement tas...
read it
-
Many-shot from Low-shot: Learning to Annotate using Mixed Supervision for Object Detection
Object detection has witnessed significant progress by relying on large,...
read it
-
Wavelet-Based Dual-Branch Network for Image Demoireing
When smartphone cameras are used to take photos of digital screens, usua...
read it
-
NTIRE 2020 Challenge on Image Demoireing: Methods and Results
This paper reviews the Challenge on Image Demoireing that was part of th...
read it
-
Image Demoireing with Learnable Bandpass Filters
Image demoireing is a multi-faceted image restoration task involving bot...
read it
-
Unsupervised Model Personalization while Preserving Privacy and Scalability: An Open Problem
This work investigates the task of unsupervised model personalization, a...
read it
-
G2L-Net: Global to Local Network for Real-time 6D Pose Estimation with Embedding Vector Features
In this paper, we propose a novel real-time 6D object pose estimation fr...
read it
-
A Multi-Hypothesis Classification Approach to Color Constancy
Contemporary approaches frame the color constancy problem as learning ca...
read it
-
A Multi-Hypothesis Approach to Color Constancy
Contemporary approaches frame the color constancy problem as learning ca...
read it
-
AIM 2019 Challenge on Image Demoireing: Methods and Results
This paper reviews the first-ever image demoireing challenge that was pa...
read it
-
AIM 2019 Challenge on Image Demoireing: Dataset and Study
This paper introduces a novel dataset, called LCDMoire, which was create...
read it
-
Continual learning: A comparative study on how to defy forgetting in classification tasks
Artificial neural networks thrive in solving the classification problem ...
read it
-
Deep Dexterous Grasping of Novel Objects from a Single View
Dexterous grasping of a novel object given a single view is an open prob...
read it
-
Learning Manipulation under Physics Constraints with Visual Perception
Understanding physical phenomena is a key competence that enables humans...
read it
-
Assessing Capsule Networks With Biased Data
Machine learning based methods achieves impressive results in object cla...
read it
-
Spatially-Adaptive Filter Units for Compact and Efficient Deep Neural Networks
Convolutional neural networks excel in a number of computer vision tasks...
read it
-
A Summary of the 4th International Workshop on Recovering 6D Object Pose
This document summarizes the 4th International Workshop on Recovering 6D...
read it
-
Exploring object-centric and scene-centric CNN features and their complementarity for human rights violations recognition in images
Identifying potential abuses of human rights through imagery is a novel ...
read it
-
Spatially-Adaptive Filter Units for Deep Neural Networks
Classical deep convolutional networks increase receptive field size by e...
read it
-
Material Classification in the Wild: Do Synthesized Training Data Generalise Better than Real-World Training Data?
We question the dominant role of real-world training images in the field...
read it
-
Performance Characterization of Image Feature Detectors in Relation to the Scene Content Utilizing a Large Image Database
Selecting the most suitable local invariant feature detector for a parti...
read it
-
Detection of Human Rights Violations in Images: Can Convolutional Neural Networks help?
After setting the performance benchmarks for image, video, speech and au...
read it
-
Evaluating Deep Convolutional Neural Networks for Material Classification
Determining the material category of a surface from an image is a demand...
read it
-
Beyond standard benchmarks: Parameterizing performance evaluation in visual object tracking
Object-to-camera motion produces a variety of apparent motion patterns t...
read it
-
Semantic tracking: Single-target tracking with inter-supervised convolutional networks
This article presents a semantic tracker which simultaneously tracks a s...
read it
-
Visual Stability Prediction and Its Application to Manipulation
Understanding physical phenomena is a key competence that enables humans...
read it
-
Towards Deep Compositional Networks
Hierarchical feature learning based on convolutional neural networks (CN...
read it
-
Automatic Selection of the Optimal Local Feature Detector
A large number of different feature detectors has been proposed so far. ...
read it
-
To Fall Or Not To Fall: A Visual Approach to Physical Stability Prediction
Understanding physical phenomena is a key competence that enables humans...
read it
-
A Hierarchical Approach for Joint Multi-view Object Pose Estimation and Categorization
We propose a joint object pose estimation and categorization approach wh...
read it
-
A Novel Performance Evaluation Methodology for Single-Target Trackers
This paper addresses the problem of single-target tracker performance ev...
read it
-
Visual object tracking performance measures revisited
The problem of visual tracking evaluation is sporting a large variety of...
read it
-
A Graph Theoretic Approach for Object Shape Representation in Compositional Hierarchies Using a Hybrid Generative-Descriptive Model
A graph theoretic approach is proposed for object shape representation i...
read it
-
Learning a Hierarchical Compositional Shape Vocabulary for Multi-class Object Representation
Hierarchies allow feature sharing between objects at multiple levels of ...
read it