1 code implementation • 15 Sep 2023 • Orhan Torun, Seniha Esen Yuksel, Erkut Erdem, Nevrez Imamoglu, Aykut Erdem
At the core of the model lies a novel block, which we call spectral self-modulating residual block (SSMRB), that allows the network to transform the features in an adaptive manner based on the adjacent spectral data, enhancing the network's ability to handle complex noise.
no code implementations • 28 Aug 2023 • Guanqun Ding, Nevrez Imamoglu, Ali Caglayan, Masahiro Murakawa, Ryosuke Nakamura
To address these challenges, we propose a saliency-guided approach that leverages attention information to improve the performance of LiDAR odometry estimation and semantic segmentation models.
1 code implementation • 24 Aug 2023 • Mert Cokelek, Nevrez Imamoglu, Cagri Ozcinar, Erkut Erdem, Aykut Erdem
The growing interest in omnidirectional videos (ODVs) that capture the full field-of-view (FOV) has gained 360-degree saliency prediction importance in computer vision.
1 code implementation • 13 Mar 2023 • Nafiseh Jabbari Tofighi, Mohamed Hedi Elfkir, Nevrez Imamoglu, Cagri Ozcinar, Erkut Erdem, Aykut Erdem
As their popularity has increased dramatically in recent years, evaluating the quality of 360 images has become a problem of interest since it provides insights for capturing, transmitting, and consuming this new media.
no code implementations • 28 Jan 2022 • Ali Caglayan, Nevrez Imamoglu, Oguzhan Guclu, Ali Osman Serhatoglu, Weimin WANG, Ahmet Burak Can, Ryosuke Nakamura
This can be very useful for visual tasks such as simultaneous localization and mapping (SLAM) where CNN representations of spatially attentive object locations may lead to improved performance.
1 code implementation • 7 Dec 2021 • Guanqun Ding, Nevrez Imamoglu, Ali Caglayan, Masahiro Murakawa, Ryosuke Nakamura
We first use the proposed feedback model to learn saliency distribution from pseudo-ground-truth.
1 code implementation • 26 Apr 2020 • Ali Caglayan, Nevrez Imamoglu, Ahmet Burak Can, Ryosuke Nakamura
The second stage maps these features into high level representations with a fully randomized structure of recursive neural networks (RNNs) efficiently.
Ranked #2 on Scene Recognition on SUN-RGBD
1 code implementation • 28 Feb 2019 • Nevrez Imamoglu, Guanqun Ding, Yuming Fang, Asako Kanezaki, Toru Kouyama, Ryosuke Nakamura
Various saliency detection algorithms from color images have been proposed to mimic eye fixation or attentive object detection response of human observers for the same scenes.
no code implementations • 4 Jul 2018 • Nevrez Imamoglu, Wataru Shimoda, Chi Zhang, Yuming Fang, Asako Kanezaki, Keiji Yanai, Yoshifumi Nishida
Bottom-up and top-down visual cues are two types of information that helps the visual saliency models.
2 code implementations • 29 Jun 2018 • Nevrez Imamoglu, Yu Oishi, Xiaoqiang Zhang, Guanqun Ding, Yuming Fang, Toru Kouyama, Ryosuke Nakamura
Many works have been done on salient object detection using supervised or unsupervised approaches on colour images.
1 code implementation • 21 Apr 2017 • Nevrez Imamoglu, Motoki Kimura, Hiroki Miyamoto, Aito Fujita, Ryosuke Nakamura
To express the strength of the top-down connections, we introduce feedback CNN network (FB-Net) to a baseline CNN model used for solar power plant classification on multi-spectral satellite data.
1 code implementation • 1 Mar 2017 • Nevrez Imamoglu, Chi Zhang, Wataru Shimoda, Yuming Fang, Boxin Shi
As prior knowledge of objects or object features helps us make relations for similar objects on attentional tasks, pre-trained deep convolutional neural networks (CNNs) can be used to detect salient objects on images regardless of the object class is in the network knowledge or not.
no code implementations • 1 Mar 2017 • Nevrez Imamoglu, Zhixuan Wei, Huangjun Shi, Yuki Yoshida, Myagmarbayar Nergui, Jose Gonzalez, Dongyun Gu, Weidong Chen, Kenzo Nonami, Wenwei Yu
Saliency computation has become a popular research field for many applications due to the useful information provided by saliency maps.