Results 301 to 310 of about 311,283 (352)
Digit-Tracking Reveals Curiosity-Driven Visual Attention in Macaque Monkeys
Yang Y +4 more
europepmc +1 more source
Some of the next articles are maybe not open access.
Related searches:
Related searches:
International Conference on Learning Representations, 2023
With evolving data regulations, machine unlearning (MU) has become an important tool for fostering trust and safety in today's AI models. However, existing MU methods focusing on data and/or weight perspectives often grapple with limitations in ...
Chongyu Fan +5 more
semanticscholar +1 more source
With evolving data regulations, machine unlearning (MU) has become an important tool for fostering trust and safety in today's AI models. However, existing MU methods focusing on data and/or weight perspectives often grapple with limitations in ...
Chongyu Fan +5 more
semanticscholar +1 more source
RSSFormer: Foreground Saliency Enhancement for Remote Sensing Land-Cover Segmentation
IEEE Transactions on Image Processing, 2023High spatial resolution (HSR) remote sensing images contain complex foreground-background relationships, which makes the remote sensing land cover segmentation a special semantic segmentation task. The main challenges come from the large-scale variation,
Rongtao Xu +5 more
semanticscholar +1 more source
Revisiting Video Saliency Prediction in the Deep Learning Era
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021Predicting where people look in static scenes, a.k.a visual saliency, has received significant research interest recently. However, relatively less effort has been spent in understanding and modeling visual attention over dynamic scenes.
Wenguan Wang +5 more
semanticscholar +1 more source
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017
Most existing bottom-up algorithms measure the foreground saliency of a pixel or region based on its contrast within a local context or the entire image, whereas a few methods focus on segmenting out background regions and thereby salient objects.
Lihe, Zhang +4 more
openaire +2 more sources
Most existing bottom-up algorithms measure the foreground saliency of a pixel or region based on its contrast within a local context or the entire image, whereas a few methods focus on segmenting out background regions and thereby salient objects.
Lihe, Zhang +4 more
openaire +2 more sources
Classification Saliency-Based Rule for Visible and Infrared Image Fusion
IEEE Transactions on Computational Imaging, 2021Existing image fusion methods always use hand-crafted fusion rules due to the uninterpretability of deep feature maps, which restrict the performance of networks and result in distortion.
Han Xu, Hao Zhang, Jiayi Ma
semanticscholar +1 more source
Static saliency vs. dynamic saliency
Proceedings of the 21st ACM international conference on Multimedia, 2013Recently visual saliency has attracted wide attention of researchers in the computer vision and multimedia field. However, most of the visual saliency-related research was conducted on still images for studying static saliency. In this paper, we give a comprehensive comparative study for the first time of dynamic saliency (video shots) and static ...
Nguyen, Tam +5 more
openaire +1 more source
Interactive Two-Stream Decoder for Accurate and Fast Saliency Detection
Computer Vision and Pattern Recognition, 2020Recently, contour information largely improves the performance of saliency detection. However, the discussion on the correlation between saliency and contour remains scarce. In this paper, we first analyze such correlation and then propose an interactive
Huajun Zhou +4 more
semanticscholar +1 more source
Depth-Induced Multi-Scale Recurrent Attention Network for Saliency Detection
IEEE International Conference on Computer Vision, 2019In this work, we propose a novel depth-induced multi-scale recurrent attention network for saliency detection. It achieves dramatic performance especially in complex scenarios.
Yongri Piao +4 more
semanticscholar +1 more source