1 code implementation • 21 Sep 2021 • Bishwo Adhikari, Xingyang Ni, Esa Rahtu, Heikki Huttunen
Facial analysis is an active research area in computer vision, with many practical applications.
1 code implementation • 16 Aug 2021 • Xingyang Ni, Heikki Huttunen, Esa Rahtu
On the other hand, it is advisable to encrypt feature vectors, especially for a machine learning model in production.
1 code implementation • 17 Jun 2021 • Yi Zhou, Heikki Huttunen, Tapio Elomaa
Age estimation is an essential challenge in computer vision.
no code implementations • 10 May 2021 • Bishwo Adhikari, Esa Rahtu, Heikki Huttunen
Supervised object detection has been proven to be successful in many benchmark datasets achieving human-level performances.
no code implementations • 9 May 2021 • Saeed Bakhshi Germi, Esa Rahtu, Heikki Huttunen
In this paper, we propose a simple yet effective method to deal with the violation of the Closed-World Assumption for a classifier.
no code implementations • 6 Aug 2020 • Leevi Raivio, Han He, Johanna Virkki, Heikki Huttunen
The data is collected sequentially, such that we record both the stroke order and the resulting bitmap.
1 code implementation • 15 Jul 2020 • Xingyang Ni, Liang Fang, Heikki Huttunen
We introduce an adaptive L2 regularization mechanism in the setting of person re-identification.
Ranked #4 on Person Re-Identification on MSMT17
no code implementations • 2 Jul 2020 • Bishwo Adhikari, Heikki Huttunen
Manual annotation of bounding boxes for object detection in digital images is tedious, and time and resource consuming.
no code implementations • 29 Jun 2020 • Xingyang Ni, Heikki Huttunen
This paper studies vehicle attribute recognition by appearance.
no code implementations • 23 Aug 2019 • Syeda Sakira Hassan, Heikki Huttunen, Jari Niemi, Jussi Tohka
We derive a closed-form solution of the proposed accuracy metric for any linear binary classifier under the Gaussianity assumption, and study the accuracy of the proposed estimator using simulated and real-world data.
no code implementations • 1 May 2019 • Francesco Lomio, Erjon Skenderi, Damoon Mohamadi, Jussi Collin, Reza Ghabcheloo, Heikki Huttunen
In this work we describe the preparation of a time series dataset of inertial measurements for determining the surface type under a wheeled robot.
no code implementations • 16 Apr 2019 • Oguzhan Gencoglu, Mark van Gils, Esin Guldogan, Chamin Morikawa, Mehmet Süzen, Mathias Gruber, Jussi Leinonen, Heikki Huttunen
Recent advancements in machine learning research, i. e., deep learning, introduced methods that excel conventional algorithms as well as humans in several complex tasks, ranging from detection of objects in images and speech recognition to playing difficult strategic games.
3 code implementations • 1 Oct 2018 • Yi Zhou, Yue Bai, Shuvra S. Bhattacharyya, Heikki Huttunen
In this work we propose a framework for improving the performance of any deep neural network that may suffer from vanishing gradients.
1 code implementation • 14 Sep 2018 • Janne Tommola, Pedram Ghazi, Bishwo Adhikari, Heikki Huttunen
In this paper we describe the anatomy of a real-time facial analysis system.
no code implementations • 2 Aug 2018 • Shayan Gharib, Honain Derrar, Daisuke Niizumi, Tuukka Senttula, Janne Tommola, Toni Heittola, Tuomas Virtanen, Heikki Huttunen
In this paper we study the problem of acoustic scene classification, i. e., categorization of audio sequences into mutually exclusive classes based on their spectral content.
no code implementations • 1 Aug 2018 • Mir Khan, Heikki Huttunen, Jani Boutellier
This representation completely eliminates the need for floating point multiplications and additions and decreases both the computational load and the memory footprint compared to a full-precision network implemented in floating point, making it well-suited for resource-constrained environments.
no code implementations • 1 Aug 2018 • Francesco Lomio, Ricardo Farinha, Mauri Laasonen, Heikki Huttunen
In this work we study an application of machine learning to the construction industry and we use classical and modern machine learning methods to categorize images of building designs into three classes: Apartment building, Industrial building or Other.
no code implementations • 3 Jul 2018 • Bishwo Adhikari, Jukka Peltomäki, Jussi Puura, Heikki Huttunen
The procedure consists of two stages: The first step is to annotate a part of the dataset manually, and the second step proposes annotations for the remaining samples using a model trained with the first stage annotations.
no code implementations • 2 Jul 2018 • Yue Bai, Shuvra S. Bhattacharyya, Antti P. Happonen, Heikki Huttunen
We propose a new framework for image classification with deep neural networks.
1 code implementation • 21 Feb 2017 • Emre Çakır, Giambattista Parascandolo, Toni Heittola, Heikki Huttunen, Tuomas Virtanen
Sound events often occur in unstructured environments where they exhibit wide variations in their frequency content and temporal structure.
2 code implementations • 4 Apr 2016 • Giambattista Parascandolo, Heikki Huttunen, Tuomas Virtanen
In this paper we present an approach to polyphonic sound event detection in real life recordings based on bi-directional long short term memory (BLSTM) recurrent neural networks (RNNs).
2 code implementations • 23 Feb 2016 • Heikki Huttunen, Fatemeh Shokrollahi Yancheshmeh, Ke Chen
In this paper we study automatic recognition of cars of four types: Bus, Truck, Van and Small car.