625 citations · 1.2k across the 22 of their papers we have counts for
25 papers
Towards a Real-Time Facial Analysis System
Bishwo Adhikari, Xingyang Ni, Esa Rahtu +1
Facial analysis is an active research area in computer vision, with many practical applications. Most of the existing studies focus on addressing one specific task and maximizing i…
On the Importance of Encrypting Deep Features
Xingyang Ni, Heikki Huttunen, Esa Rahtu
In this study, we analyze model inversion attacks with only two assumptions: feature vectors of user data are known, and a black-box API for inference is provided. On the one hand,…
using multiple losses for accurate facial age estimation
Yi Zhou, Heikki Huttunen, Tapio Elomaa
Age estimation is an essential challenge in computer vision. With the advances of convolutional neural networks, the performance of age estimation has been dramatically improved. E…
Selective Probabilistic Classifier Based on Hypothesis Testing
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. Previous works tend to apply a threshold either…
Sample selection for efficient image annotation
Bishwo Adhikari, Esa Rahtu, Heikki Huttunen
Supervised object detection has been proven to be successful in many benchmark datasets achieving human-level performances. However, acquiring a large amount of labeled image sampl…
Handwritten Character Recognition from Wearable Passive RFID
Leevi Raivio, Han He, Johanna Virkki +1
In this paper we study the recognition of handwritten characters from data captured by a novel wearable electro-textile sensor panel. The data is collected sequentially, such that…
Iterative Bounding Box Annotation for Object Detection
Bishwo Adhikari, Heikki Huttunen
Manual annotation of bounding boxes for object detection in digital images is tedious, and time and resource consuming. In this paper, we propose a semi-automatic method for effici…
Adaptive L2 Regularization in Person Re-Identification
Xingyang Ni, Liang Fang, Heikki Huttunen
We introduce an adaptive L2 regularization mechanism in the setting of person re-identification. In the literature, it is common practice to utilize hand-picked regularization fact…
Vehicle Attribute Recognition by Appearance: Computer Vision Methods for Vehicle Type, Make and Model Classification
Xingyang Ni, Heikki Huttunen
This paper studies vehicle attribute recognition by appearance. In the literature, image-based target recognition has been extensively investigated in many use cases, such as facia…
Bayesian Receiver Operating Characteristic Metric for Linear Classifiers
Syeda Sakira Hassan, Heikki Huttunen, Jari Niemi +1
We propose a novel classifier accuracy metric: the Bayesian Area Under the Receiver Operating Characteristic Curve (CBAUC). The method estimates the area under the ROC curve and is…
Are SonarQube Rules Inducing Bugs?
Valentina Lenarduzzi, Francesco Lomio, Heikki Huttunen +1
Background. The popularity of tools for analyzing Technical Debt, and particularly the popularity of SonarQube, is increasing rapidly. SonarQube proposes a set of coding rules, whi…
Surface Type Classification for Autonomous Robot Indoor Navigation
Francesco Lomio, Erjon Skenderi, Damoon Mohamadi +3
In this work we describe the preparation of a time series dataset of inertial measurements for determining the surface type under a wheeled robot. The data consists of over 7600 la…
HARK Side of Deep Learning -- From Grad Student Descent to Automated Machine Learning
Oguzhan Gencoglu, Mark van Gils, Esin Guldogan +5
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 fro…
Elastic Neural Networks for Classification
Yi Zhou, Yue Bai, Shuvra S. Bhattacharyya +1
In this work we propose a framework for improving the performance of any deep neural network that may suffer from vanishing gradients. To address the vanishing gradient issue, we s…
Real Time System for Facial Analysis
Janne Tommola, Pedram Ghazi, Bishwo Adhikari +1
In this paper we describe the anatomy of a real-time facial analysis system. The system recognizes the age, gender and facial expression from users in appearing in front of the cam…
Acoustic Scene Classification: A Competition Review
Shayan Gharib, Honain Derrar, Daisuke Niizumi +5
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. We des…
Classification of Building Information Model (BIM) Structures with Deep Learning
Francesco Lomio, Ricardo Farinha, Mauri Laasonen +1
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 desi…
Binarized Convolutional Neural Networks for Efficient Inference on GPUs
Mir Khan, Heikki Huttunen, Jani Boutellier
Convolutional neural networks have recently achieved significant breakthroughs in various image classification tasks. However, they are computationally expensive,which can make the…
Embedded Implementation of a Deep Learning Smile Detector
Pedram Ghazi, Antti P. Happonen, Jani Boutellier +1
In this paper we study the real time deployment of deep learning algorithms in low resource computational environments. As the use case, we compare the accuracy and speed of neural…
Faster Bounding Box Annotation for Object Detection in Indoor Scenes
Bishwo Adhikari, Jukka Peltomäki, Jussi Puura +1
This paper proposes an approach for rapid bounding box annotation for object detection datasets. The procedure consists of two stages: The first step is to annotate a part of the d…
Elastic Neural Networks: A Scalable Framework for Embedded Computer Vision
Yue Bai, Shuvra S. Bhattacharyya, Antti P. Happonen +1
We propose a new framework for image classification with deep neural networks. The framework introduces intermediate outputs to the computational graph of a network. This enables f…
PRUNE: Dynamic and Decidable Dataflow for Signal Processing on Heterogeneous Platforms
Jani Boutellier, Jiahao Wu, Heikki Huttunen +1
The majority of contemporary mobile devices and personal computers are based on heterogeneous computing platforms that consist of a number of CPU cores and one or more Graphics Pro…
Convolutional Recurrent Neural Networks for Polyphonic Sound Event Detection
Emre Çakır, Giambattista Parascandolo, Toni Heittola +2
Sound events often occur in unstructured environments where they exhibit wide variations in their frequency content and temporal structure. Convolutional neural networks (CNN) are…
Recurrent Neural Networks for Polyphonic Sound Event Detection in Real Life Recordings
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 (R…