no code implementations • 15 Apr 2024 • Önder Tuzcuoğlu, Aybora Köksal, Buğra Sofu, Sinan Kalkan, A. Aydin Alatan
We introduce, XoFTR, a cross-modal cross-view method for local feature matching between thermal infrared (TIR) and visible images.
1 code implementation • 6 Sep 2023 • Ada Gorgun, Yeti Z. Gurbuz, A. Aydin Alatan
Albeit useful especially in the penultimate layer and beyond, its action on student's feature transform is rather implicit, limiting its practice in the intermediate layers.
1 code implementation • ICCV 2023 • Yeti Z. Gurbuz, Ozan Sener, A. Aydin Alatan
GSP improves GAP with two distinct abilities: i) the ability to choose a subset of semantic entities, effectively learning to ignore nuisance information, and ii) learning the weights corresponding to the importance of each entity.
no code implementations • 14 Jul 2023 • Yeti Z. Gurbuz, A. Aydin Alatan
Global average pooling (GAP) is a popular component in deep metric learning (DML) for aggregating features.
1 code implementation • 3 Mar 2023 • Ahmet Akman, Onur Selim Kılıç, A. Aydin Alatan
Utilization of event-based cameras is expected to improve the visual quality of video frame interpolation solutions.
no code implementations • 3 Oct 2022 • Ada Gorgun, Yeti Z. Gurbuz, A. Aydin Alatan
Convolution blocks serve as local feature extractors and are the key to success of the neural networks.
1 code implementation • 19 Sep 2022 • Yeti Z. Gurbuz, Ogul Can, A. Aydin Alatan
Deep metric learning (DML) aims to minimize empirical expected loss of the pairwise intra-/inter- class proximity violations in the embedding space.
1 code implementation • 19 Sep 2022 • Onur Selim Kılıç, Ahmet Akman, A. Aydin Alatan
E-VFIA fuses event information with standard video frames by deformable convolutions to generate high quality interpolated frames.
1 code implementation • 26 Feb 2022 • Aybora Koksal, Onder Tuzcuoglu, Kutalmis Gokalp Ince, Yoldas Ataseven, A. Aydin Alatan
Hard example mining methods generally improve the performance of the object detectors, which suffer from imbalanced training sets.
no code implementations • 29 Sep 2021 • Yeti Z. Gürbüz, Oğul Can, A. Aydin Alatan
Deep metric learning (DML) aims to minimize empirical expected loss of the pairwise intra-/inter- class proximity violations in the embedding image.
1 code implementation • 18 Aug 2021 • Ufuk Efe, Kutalmis Gokalp Ince, A. Aydin Alatan
After a fair comparison, the experimental results on HPatches dataset reveal that the performance gap between classical and learning-based methods is not that significant.
1 code implementation • 14 Jun 2021 • Ufuk Efe, Kutalmis Gokalp Ince, A. Aydin Alatan
A novel image matching method is proposed that utilizes learned features extracted by an off-the-shelf deep neural network to obtain a promising performance.
1 code implementation • 18 Jan 2021 • Kutalmis Gokalp Ince, Aybora Koksal, Arda Fazla, A. Aydin Alatan
For detection, we use an off-the-shelf object detector which is trained iteratively with the annotations generated by the proposed method, and we perform object detection on each frame independently.
no code implementations • 24 Oct 2020 • Oğul Can, Yeti Z. Gürbüz, Berkin Yıldırım, A. Aydin Alatan
We propose an end-to-end learning approach to address deinterleaving of patterns in time series, in particular, radar signals.
1 code implementation • 3 Aug 2020 • M. Esat Kalfaoglu, Sinan Kalkan, A. Aydin Alatan
In this work, we combine 3D convolution with late temporal modeling for action recognition.
Ranked #1 on Action Recognition on UCF 101
1 code implementation • 2 Apr 2020 • Aybora Koksal, Kutalmis Gokalp Ince, A. Aydin Alatan
Following the recent advances in deep networks, object detection and tracking algorithms with deep learning backbones have been improved significantly; however, this rapid development resulted in the necessity of large amounts of annotated labels.
no code implementations • 22 Jul 2019 • Kaan Karaman, Erhan Gundogdu, Aykut Koc, A. Aydin Alatan
Recognition of objects with subtle differences has been used in many practical applications, such as car model recognition and maritime vessel identification.
no code implementations • 17 Jul 2019 • Oğul Can, Yeti Ziya Gürbüz, A. Aydin Alatan
The feasible set induced by the constraint set is expressed as the intersection of the relaxed feasible sets which enforce the proximity constraints only for particular samples (a sample from each class) of the training data.
1 code implementation • 20 Apr 2017 • Erhan Gundogdu, A. Aydin Alatan
The proposed learning framework enables the network model to be flexible for a custom design.
Ranked #2 on Visual Object Tracking on VOT2016
no code implementations • 22 Jan 2013 • Ozan Sener, Kemal Ugur, A. Aydin Alatan
Depending on the application, automatic or interactive methods are desired; however, regardless of the application type, efficient computation of video object segmentation is crucial for time-critical applications; specifically, mobile and interactive applications require near real-time efficiencies.