Picture for Okan Köpüklü

Okan Köpüklü

Inference-Adaptive Neural Steering for Real-Time Area-Based Sound Source Separation

Add code
Aug 23, 2024
Viaarxiv icon

Efficient Area-based and Speaker-Agnostic Source Separation

Add code
Aug 19, 2024
Viaarxiv icon

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

Add code
Jun 07, 2021
Figure 1 for How to Design a Three-Stage Architecture for Audio-Visual Active Speaker Detection in the Wild
Figure 2 for How to Design a Three-Stage Architecture for Audio-Visual Active Speaker Detection in the Wild
Figure 3 for How to Design a Three-Stage Architecture for Audio-Visual Active Speaker Detection in the Wild
Figure 4 for How to Design a Three-Stage Architecture for Audio-Visual Active Speaker Detection in the Wild
Viaarxiv icon

Deep Compact Polyhedral Conic Classifier for Open and Closed Set Recognition

Add code
Feb 24, 2021
Figure 1 for Deep Compact Polyhedral Conic Classifier for Open and Closed Set Recognition
Figure 2 for Deep Compact Polyhedral Conic Classifier for Open and Closed Set Recognition
Figure 3 for Deep Compact Polyhedral Conic Classifier for Open and Closed Set Recognition
Figure 4 for Deep Compact Polyhedral Conic Classifier for Open and Closed Set Recognition
Viaarxiv icon

TRAT: Tracking by Attention Using Spatio-Temporal Features

Add code
Nov 18, 2020
Figure 1 for TRAT: Tracking by Attention Using Spatio-Temporal Features
Figure 2 for TRAT: Tracking by Attention Using Spatio-Temporal Features
Figure 3 for TRAT: Tracking by Attention Using Spatio-Temporal Features
Figure 4 for TRAT: Tracking by Attention Using Spatio-Temporal Features
Viaarxiv icon

Driver Anomaly Detection: A Dataset and Contrastive Learning Approach

Add code
Sep 30, 2020
Figure 1 for Driver Anomaly Detection: A Dataset and Contrastive Learning Approach
Figure 2 for Driver Anomaly Detection: A Dataset and Contrastive Learning Approach
Figure 3 for Driver Anomaly Detection: A Dataset and Contrastive Learning Approach
Figure 4 for Driver Anomaly Detection: A Dataset and Contrastive Learning Approach
Viaarxiv icon

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

Add code
Sep 30, 2020
Figure 1 for Dissected 3D CNNs: Temporal Skip Connections for Efficient Online Video Processing
Figure 2 for Dissected 3D CNNs: Temporal Skip Connections for Efficient Online Video Processing
Figure 3 for Dissected 3D CNNs: Temporal Skip Connections for Efficient Online Video Processing
Figure 4 for Dissected 3D CNNs: Temporal Skip Connections for Efficient Online Video Processing
Viaarxiv icon

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

Add code
Mar 02, 2020
Figure 1 for DriverMHG: A Multi-Modal Dataset for Dynamic Recognition of Driver Micro Hand Gestures and a Real-Time Recognition Framework
Figure 2 for DriverMHG: A Multi-Modal Dataset for Dynamic Recognition of Driver Micro Hand Gestures and a Real-Time Recognition Framework
Figure 3 for DriverMHG: A Multi-Modal Dataset for Dynamic Recognition of Driver Micro Hand Gestures and a Real-Time Recognition Framework
Figure 4 for DriverMHG: A Multi-Modal Dataset for Dynamic Recognition of Driver Micro Hand Gestures and a Real-Time Recognition Framework
Viaarxiv icon

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

Add code
Dec 10, 2019
Figure 1 for Deep Attention Based Semi-Supervised 2D-Pose Estimation for Surgical Instruments
Figure 2 for Deep Attention Based Semi-Supervised 2D-Pose Estimation for Surgical Instruments
Figure 3 for Deep Attention Based Semi-Supervised 2D-Pose Estimation for Surgical Instruments
Figure 4 for Deep Attention Based Semi-Supervised 2D-Pose Estimation for Surgical Instruments
Viaarxiv icon

Unsupervised Monocular Depth Prediction for Indoor Continuous Video Streams

Add code
Nov 20, 2019
Figure 1 for Unsupervised Monocular Depth Prediction for Indoor Continuous Video Streams
Figure 2 for Unsupervised Monocular Depth Prediction for Indoor Continuous Video Streams
Figure 3 for Unsupervised Monocular Depth Prediction for Indoor Continuous Video Streams
Figure 4 for Unsupervised Monocular Depth Prediction for Indoor Continuous Video Streams
Viaarxiv icon