Filters








1,075 Hits in 10.2 sec

State-of-the-Art in Visual Attention Modeling

Ali Borji, Laurent Itti
2013 IEEE Transactions on Pattern Analysis and Machine Intelligence  
Furthermore, we address several challenging issues with models, including biological plausibility of the computations, correlation with eye movement datasets, bottom-up and top-down dissociation, and constructing  ...  Finally, we highlight current research trends in attention modeling and provide insights for future.  ...  ACKNOWLEDGMENTS This work was supported by Defense Advanced Research Projects Agency (government contract no.  ... 
doi:10.1109/tpami.2012.89 pmid:22487985 fatcat:unx6oe5wfracdcxhcrocwgfspm

Multi-focus Image Fusion Based on Adaptive Dual-channel Spiking Cortical Model in Non-subsampled Shearlet Domain

Shuaiqi Liu, Jie Wang, Yucong Lu, Hailiang Li, Jie Zhao, Zhihui Zhu
2019 IEEE Access  
First, a basic fused image is constructed in the NSST domain by registering the source image and adaptive dual channel SCM (dual-channel SCM).  ...  In the end, the final fused image generated in this paper is realized by combining the focal regions.  ...  We use five pairs of source images as comparisons, from top to bottom are the decision maps of different algorithms, the last line is the fused images, and the final result is shown in FIGURE 17.  ... 
doi:10.1109/access.2019.2900376 fatcat:p5yszxkuqvd3fplx754d3sx5ti

Recent Advances in Convolutional Neural Networks [article]

Jiuxiang Gu, Zhenhua Wang, Jason Kuen, Lianyang Ma, Amir Shahroudy, Bing Shuai, Ting Liu, Xingxing Wang, Li Wang, Gang Wang, Jianfei Cai, Tsuhan Chen
2017 arXiv   pre-print
Besides, we also introduce various applications of convolutional neural networks in computer vision, speech and natural language processing.  ...  In the last few years, deep learning has led to very good performance on a variety of problems, such as visual recognition, speech recognition and natural language processing.  ...  The ROSE Lab is supported by the Infocomm Media Development Authority, Singapore.  ... 
arXiv:1512.07108v6 fatcat:rwmmwcy4ezd6pmt6scuaambd7m

Deep Learning for SAR Ship Detection: Past, Present and Future

Jianwei Li, Congan Xu, Hang Su, Long Gao, Taoyang Wang
2022 Remote Sensing  
What we should do next is to bridge the gap between SAR ship detection and computer vision by merging the small datasets into a large one and formulating corresponding standards and benchmarks.  ...  After that, we introduce the use of single-stage, two-stage, anchor-free, train from scratch, oriented bounding box, multi-scale, and real-time detectors in detail in the 177 papers.  ...  [86] did not use a single feature map but fused the feature map in a bottom-up and top-down manner, and generated candidate boxes from each fused feature map.  ... 
doi:10.3390/rs14112712 fatcat:dbd6a4ugwjc65pook3wpcuj52a

From Show to Tell: A Survey on Deep Learning-based Image Captioning [article]

Matteo Stefanini, Marcella Cornia, Lorenzo Baraldi, Silvia Cascianelli, Giuseppe Fiameni, Rita Cucchiara
2021 arXiv   pre-print
The final goal of this work is to serve as a tool for understanding the existing literature and highlighting the future directions for a research area where Computer Vision and Natural Language Processing  ...  Starting from 2015 the task has generally been addressed with pipelines composed of a visual encoder and a language model for text generation.  ...  , and by the H2020 ICT-48-2020 HumanE-AI-NET and ELISE projects.  ... 
arXiv:2107.06912v3 fatcat:ezhutcovnvh4reiweedfmxjlve

HCNET: A Point Cloud Object Detection Network Based on Height and Channel Attention

Jing Zhang, Jiajun Wang, Da Xu, Yunsong Li
2021 Remote Sensing  
Inspired by the basic idea of an attention mechanism, a feature-fusion structure HC module with height attention and channel attention, weighted in parallel, is proposed to perform feature-fusion on multiple  ...  overcoming the sparse and uneven distribution of point clouds.  ...  The backbone has three parts: (1) the top-down part, which generates features at smaller and smaller resolutions; (2) the down-top part, which up-samples the feature map from the bottom up and stitches  ... 
doi:10.3390/rs13245071 fatcat:nquxy6ldvvbubnuqae7bj6jooa

2021 Index IEEE Transactions on Image Processing Vol. 30

2021 IEEE Transactions on Image Processing  
The primary entry includes the coauthors' names, the title of the paper or other item, and its location, specified by the publication abbreviation, year, month, and inclusive pagination.  ...  The Subject Index contains entries describing the item under all appropriate subject headings, plus the first author's name, the publication abbreviation, month, and year, and inclusive pages.  ...  ., +, TIP 2021 4571-4586 Predicting Task-Driven Attention via Integrating Bottom-Up Stimulus and Top-Down Guidance.  ... 
doi:10.1109/tip.2022.3142569 fatcat:z26yhwuecbgrnb2czhwjlf73qu

The Use of Saliency in Underwater Computer Vision: A Review

Marco Reggiannini, Davide Moroni
2020 Remote Sensing  
The informative properties of the data are systematically affected by a number of disturbing factors, such as the signal energy absorbed by the propagation medium or diverse noise categories contaminating  ...  Underwater survey and inspection are tasks of paramount relevance for a variety of applications.  ...  The dataset is freely available in Zenodo, split into two parts (see Reference [92, 93] ), and contains the ground-truth as a text file with the left, top, right, and bottom coordinates of each rectangle  ... 
doi:10.3390/rs13010022 fatcat:7i6r2jftdvdtzepcecm56pqqhi

Deep learning for radar data exploitation of autonomous vehicle [article]

Arthur Ouaknine
2022 arXiv   pre-print
It also introduces a method to open up research into the fusion of LiDAR and RADAR sensors for scene understanding.  ...  by adverse weather conditions.  ...  I would like to especially thank Domique Béréziat and Francesca Bovolo for reviewing my manuscript.  ... 
arXiv:2203.08038v1 fatcat:zjupxkpaffgavm45oqpwnhkczq

A New Sensory Skill Shows Automaticity and Integration Features in Multisensory Interactions [article]

James Negen, Laura-Ashleigh Bird, Heather Slater, Lore Thaler, Marko Nardini
2021 bioRxiv   pre-print
We show that use of this new skill met three key criteria for automaticity and sensory integration: (1) enhancing the speed of perceptual decisions; (2) processing through a non-verbal route and (3) integration  ...  These results demonstrate key ways in which new sensory skills can become automatic and integrated, and suggest that sensory augmentation systems may have benefits beyond current applications for sensory  ...  In other words, it is possible that top-down strategies eventually become actively harmful to the process of using a new sensory skill.  ... 
doi:10.1101/2021.01.05.425430 fatcat:xriugppkzna37h34tanpkpqqsu

Fine-grained Visual Textual Alignment for Cross-Modal Retrieval using Transformer Encoders [article]

Nicola Messina, Giuseppe Amato, Andrea Esuli, Fabrizio Falchi, Claudio Gennaro, Stéphane Marchand-Maillet
2021 arXiv   pre-print
We argue that the fine-grained alignments produced by TERAN pave the way towards the research for effective and efficient methods for large-scale cross-modal information retrieval.  ...  Cross-attention links invalidate any chance to separately extract visual and textual features needed for the online search and the offline indexing steps in large-scale retrieval systems.  ...  by the EC (H2020 -Contract n. 825619), and AI4Media under GA 951911.  ... 
arXiv:2008.05231v2 fatcat:h5ybwbeukjamviphhfykrcbpnu

Smartphone imaging technology and its applications

Vladan Blahnik, Oliver Schindelbeck
2021 Advanced Optical Technologies  
and manufacturing process.  ...  The evolution of complementary metal oxide semiconductor (CMOS) image sensors and basic image processing is then briefly summarized.  ...  Figure 18 : 18 Figure18: MTF of SPC lens "ff/8, original" scaled up (up to a factor of 8 to full format "ff") and down (down to a factor 16 to "ff/128") consecutively by a factor of 2 in each step.  ... 
doi:10.1515/aot-2021-0023 fatcat:sr4hssk7zbbuhhj532mqngh424

A Comprehensive Survey on Video Saliency Detection with Auditory Information: the Audio-visual Consistency Perceptual is the Key! [article]

Chenglizhao Chen and Mengke Song and Wenfeng Song and Li Guo and Muwei Jian
2022 arXiv   pre-print
In a word, both our ideas and new sets serve as a convenient platform with preliminaries and guidelines, all of which are very potential to facilitate future works in promoting state-of-the-art (SOTA)  ...  Thus, the ultimate goal of this paper is to provide an extensive review to bridge the gap between audio-visual fusion and saliency detection.  ...  The basic methodologies of VSOD and VFP are almost the same, where the existing hand-crafted methods [5] , [6] , [7] , [8] mainly follow either top-down or bottom-up rationale.  ... 
arXiv:2206.13390v1 fatcat:sraklh3yyvb4hhvg4flbpwrq7e

Natural Scene Text Understanding [chapter]

Celine Mancas, Bernard Gosseli
2007 Vision Systems: Segmentation and Pattern Recognition  
[149] where text was simultaneously detected, extracted and recognized by combining bottom-up learning-based algorithms and top-down generative models using the Data Driven Markov Chain Monte Carlo  ...  bottom-up.  ...  -APPENDIX A - Color Spaces Conversion This appendix details conversions and visualisation 1 of color spaces described in Chapter 2 for the D65 white point 2 , the 2 • observer and the sRGB working space  ... 
doi:10.5772/4966 fatcat:2vx67sdtrzfpfousqoagdukutm

Vezatin Is Essential for Dendritic Spine Morphogenesis and Functional Synaptic Maturation

L. Danglot, T. Freret, N. Le Roux, N. N. Neme, A. Burgo, V. Hyenne, A. Roumier, V. Contremoulins, F. Dauphin, J.-C. Bizot, G. Vodjdani, P. Gaspar (+4 others)
2012 Journal of Neuroscience  
Vezatin knock-down in cultured hippocampal neurons and Vezatin conditional knock-out in mice led to a significantly increased proportion of stubby spines and a reduced proportion of mature dendritic spines  ...  It is expressed in the developing and mature mammalian brain, but its neuronal function is unknown.  ...  ) neurons (left top/bottom).  ... 
doi:10.1523/jneurosci.3084-11.2012 pmid:22745500 pmcid:PMC6622322 fatcat:4itz7bkgabg63npfwivnyjmlre
« Previous Showing results 1 — 15 out of 1,075 results