27 citations · 27 across the 3 of their papers we have counts for
5 papers
FASTDIAR: Frame-level speaker encoder for Streaming Diarization
Nikita Torgashov, Okan Köpüklü
Real-time conversational agents require speaker diarization that streams and runs on a CPU. Most systems apply an utterance-level speaker encoder to short, heavily overlapping chun…
Inference-Adaptive Neural Steering for Real-Time Area-Based Sound Source Separation
Martin Strauss, Wolfgang Mack, María Luis Valero +1
We propose a novel Neural Steering technique that adapts the target area of a spatial-aware multi-microphone sound source separation algorithm during inference without the necessit…
Deep Compact Polyhedral Conic Classifier for Open and Closed Set Recognition
Hakan Cevikalp, Bedirhan Uzun, Okan Köpüklü +1
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 polyhed…
TRAT: Tracking by Attention Using Spatio-Temporal Features
Hasan Saribas, Hakan Cevikalp, Okan Köpüklü +1
Robust object tracking requires knowledge of tracked objects' appearance, motion and their evolution over time. Although motion provides distinctive and complementary information e…
Dissected 3D CNNs: Temporal Skip Connections for Efficient Online Video Processing
Okan Köpüklü, Stefan Hörmann, Fabian Herzog +2
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 fe…