activity
20162026
most citedImage coding for machines: an end-to-end learned approach

118 citations · 321 across the 37 of their papers we have counts for

collaborators
Showing 2017Show all

9 papers · 1 filter

cs.CV2017★ 1 cited

Image Patch Matching Using Convolutional Descriptors with Euclidean Distance

Iaroslav Melekhov, Juho Kannala, Esa Rahtu

In this work we propose a neural network based image descriptor suitable for image patch matching, which is an important task in many computer vision applications. Our approach is…

cs.CV2017

Automatic Knee Osteoarthritis Diagnosis from Plain Radiographs: A Deep Learning-Based Approach

Aleksei Tiulpin, Jérôme Thevenot, Esa Rahtu +2

Knee osteoarthritis (OA) is the most common musculoskeletal disorder. OA diagnosis is currently conducted by assessing symptoms and evaluating plain radiographs, but this process s…

cs.CV2017

Summarization of User-Generated Sports Video by Using Deep Action Recognition Features

Antonio Tejero-de-Pablos, Yuta Nakashima, Tomokazu Sato +3

Automatically generating a summary of sports video poses the challenge of detecting interesting moments, or highlights, of a game. Traditional sports video summarization methods le…

cs.CV2017★ 38 cited

PIVO: Probabilistic Inertial-Visual Odometry for Occlusion-Robust Navigation

Arno Solin, Santiago Cortes, Esa Rahtu +1

This paper presents a novel method for visual-inertial odometry. The method is based on an information fusion framework employing low-cost IMU sensors and the monocular camera in a…

cs.CV2017

Investigating Natural Image Pleasantness Recognition using Deep Features and Eye Tracking for Loosely Controlled Human-computer Interaction

Hamed R. Tavakoli, Jorma Laaksonen, Esa Rahtu

This paper revisits recognition of natural image pleasantness by employing deep convolutional neural networks and affordable eye trackers. There exist several approaches to recogni…

cs.CV2017

Image-based Localization using Hourglass Networks

Iaroslav Melekhov, Juha Ylioinas, Juho Kannala +1

In this paper, we propose an encoder-decoder convolutional neural network (CNN) architecture for estimating camera pose (orientation and location) from a single RGB-image. The arch…