Search Results for author: Okan Köpüklü

Found 15 papers, 10 papers with code

How to Design a Three-Stage Architecture for Audio-Visual Active Speaker Detection in the Wild

1 code implementation ICCV 2021 Okan Köpüklü, Maja Taseska, Gerhard Rigoll

Successful active speaker detection requires a three-stage pipeline: (i) audio-visual encoding for all speakers in the clip, (ii) inter-speaker relation modeling between a reference speaker and the background speakers within each frame, and (iii) temporal modeling for the reference speaker.

Audio-Visual Active Speaker Detection

Deep Compact Polyhedral Conic Classifier for Open and Closed Set Recognition

no code implementations24 Feb 2021 Hakan Cevikalp, Bedirhan Uzun, Okan Köpüklü, Gurkan Ozturk

In this paper, we propose a new deep neural network classifier that simultaneously maximizes the inter-class separation and minimizes the intra-class variation by using the polyhedral conic classification function.

Anomaly Detection General Classification +1

TRAT: Tracking by Attention Using Spatio-Temporal Features

no code implementations18 Nov 2020 Hasan Saribas, Hakan Cevikalp, Okan Köpüklü, Bedirhan Uzun

Although motion provides distinctive and complementary information especially for fast moving objects, most of the recent tracking architectures primarily focus on the objects' appearance information.

Object Tracking

Driver Anomaly Detection: A Dataset and Contrastive Learning Approach

1 code implementation30 Sep 2020 Okan Köpüklü, Jiapeng Zheng, Hang Xu, Gerhard Rigoll

For this task, we introduce a new video-based benchmark, the Driver Anomaly Detection (DAD) dataset, which contains normal driving videos together with a set of anomalous actions in its training set.

Anomaly Detection Contrastive Learning +2

Dissected 3D CNNs: Temporal Skip Connections for Efficient Online Video Processing

1 code implementation30 Sep 2020 Okan Köpüklü, Stefan Hörmann, Fabian Herzog, Hakan Cevikalp, Gerhard Rigoll

Convolutional Neural Networks with 3D kernels (3D-CNNs) currently achieve state-of-the-art results in video recognition tasks due to their supremacy in extracting spatiotemporal features within video frames.

Action Classification Video Recognition

DriverMHG: A Multi-Modal Dataset for Dynamic Recognition of Driver Micro Hand Gestures and a Real-Time Recognition Framework

no code implementations2 Mar 2020 Okan Köpüklü, Thomas Ledwon, Yao Rong, Neslihan Kose, Gerhard Rigoll

In this work, we propose an HCI system for dynamic recognition of driver micro hand gestures, which can have a crucial impact in automotive sector especially for safety related issues.

Deep Attention Based Semi-Supervised 2D-Pose Estimation for Surgical Instruments

1 code implementation10 Dec 2019 Mert Kayhan, Okan Köpüklü, Mhd Hasan Sarhan, Mehmet Yigitsoy, Abouzar Eslami, Gerhard Rigoll

To this end, a lightweight network architecture is introduced and mean teacher, virtual adversarial training and pseudo-labeling algorithms are evaluated on 2D-pose estimation for surgical instruments.

2D Pose Estimation Deep Attention +1

You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action Localization

4 code implementations15 Nov 2019 Okan Köpüklü, Xiangyu Wei, Gerhard Rigoll

YOWO is a single-stage architecture with two branches to extract temporal and spatial information concurrently and predict bounding boxes and action probabilities directly from video clips in one evaluation.

Actin Detection Action Detection +1

Comparative Analysis of CNN-based Spatiotemporal Reasoning in Videos

1 code implementation arXiv preprint 2019 Okan Köpüklü, Fabian Herzog, Gerhard Rigoll

Understanding actions and gestures in video streams requires temporal reasoning of the spatial content from different time instants, i. e., spatiotemporal (ST) modeling.

Action Recognition Human-Object Interaction Detection

Talking With Your Hands: Scaling Hand Gestures and Recognition With CNNs

no code implementations10 May 2019 Okan Köpüklü, Yao Rong, Gerhard Rigoll

The use of hand gestures provides a natural alternative to cumbersome interface devices for Human-Computer Interaction (HCI) systems.


Resource Efficient 3D Convolutional Neural Networks

2 code implementations4 Apr 2019 Okan Köpüklü, Neslihan Kose, Ahmet Gunduz, Gerhard Rigoll

Recently, convolutional neural networks with 3D kernels (3D CNNs) have been very popular in computer vision community as a result of their superior ability of extracting spatio-temporal features within video frames compared to 2D CNNs.

Action Recognition In Videos Transfer Learning

Real-time Hand Gesture Detection and Classification Using Convolutional Neural Networks

5 code implementations29 Jan 2019 Okan Köpüklü, Ahmet Gunduz, Neslihan Kose, Gerhard Rigoll

We evaluate our architecture on two publicly available datasets - EgoGesture and NVIDIA Dynamic Hand Gesture Datasets - which require temporal detection and classification of the performed hand gestures.

Action Recognition General Classification +2

Convolutional Neural Networks with Layer Reuse

1 code implementation28 Jan 2019 Okan Köpüklü, Maryam Babaee, Stefan Hörmann, Gerhard Rigoll

In this paper, we propose a CNN architecture, Layer Reuse Network (LruNet), where the convolutional layers are used repeatedly without the need of introducing new layers to get a better performance.

Image Classification

Cannot find the paper you are looking for? You can Submit a new open access paper.