Article
Neurosciences
Dimokratis Karamanlis, Tim Gollisch
Summary: The study found that while some cells in the early visual system can be accurately predicted using linear receptive field models, many others show pronounced sensitivity to fine spatial contrast and local signal rectification. This highlights the diversity of receptive field nonlinearities as a crucial component for understanding early sensory encoding.
JOURNAL OF NEUROSCIENCE
(2021)
Article
Computer Science, Artificial Intelligence
Jiajing Liu, Weili Fang, Peter E. D. Love, Timo Hartmann, Hanbin Luo, Lulu Wang
Summary: This research presents an approach that uses computer vision and deep learning to identify and locate multiple unsafe behaviours in digital images from a construction site, achieving good results.
ADVANCED ENGINEERING INFORMATICS
(2022)
Article
Energy & Fuels
Alexey Korovin, Artem Vasilev, Fedor Egorov, Dmitry Saykin, Evgeny Terukov, Igor Shakhray, Leonid Zhukov, Semen Budennyy
Summary: Efficient defect detection in solar cell manufacturing is crucial for stable green energy technology manufacturing. This paper presents a deep-learning-based automatic detection model SeMaCNN for classification and anomaly detection of electroluminescent images for solar cell quality evaluation. The model demonstrates a good balance between its performance and computational complexity, which make it applicable for integrating into quality control systems of solar cell manufacturing.
Article
Psychology, Experimental
Brandon Birmingham, Adrian Muscat
Summary: This paper investigates the automatic selection of prepositions for spatial relations between objects in images. Through the development and comparison of machine learning models, it is found that the Multi-label Neural Network (ML-NN) exhibits the best overall performance, but still has some limitations.
SPATIAL COGNITION AND COMPUTATION
(2022)
Article
Computer Science, Artificial Intelligence
Suhad Lateef Al-Khafaji, Jun Zhou, Xiao Bai, Yuntao Qian, Alan Wee-Chung Liew
Summary: In this paper, a novel method for boundary detection in close-range hyperspectral images is proposed. The method effectively predicts the boundaries of objects with similar color but different materials. By estimating the spatial distribution of spectral responses and using abundance maps and spectral feature vectors, the method constructs a boundary map. Experimental results show that the proposed method outperforms alternative methods when dealing with boundaries of objects with similar color but different materials.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2022)
Article
Computer Science, Artificial Intelligence
Swapandeep Kaur, Sheifali Gupta, Swati Singh, Deepika Koundal, Atef Zaguia
Summary: This paper proposes a Convolutional Neural Network model designed using satellite images to assess the damage caused by hurricanes and provide relief aid to the affected people.
Article
Ophthalmology
Tapan P. Patel, Hursuong Vongsachang, Andrew Schilling, Xiangrong Kong, Mandeep S. Singh
Summary: The study evaluated the spatial characteristics of retained peripheral visual field (pVF) in individuals with retinitis pigmentosa (RP) using a computational platform. The results showed that inferotemporal pVF loci were most likely to be preserved over time in the longitudinal dataset. The area of pVF retention corresponded anatomically to the pre-equatorial superonasal retina, suggesting resilience of retinal cells in this region to RP-related functional decline.
INVESTIGATIVE OPHTHALMOLOGY & VISUAL SCIENCE
(2022)
Article
Biology
Zhenggong Han, Haisong Huang, Dan Lu, Qingsong Fan, Chi Ma, Xingran Chen, Qiang Gu, Qipeng Chen
Summary: In this paper, a one-stage and lightweight CNN detector with an attention mechanism for detecting microscopic WBC images is proposed. The proposed method integrates different optimizing strategies to improve the examination precision and efficiency. Extensive experiments on multiple datasets verify the effectiveness and robustness of the proposed detector for blood cell detection.
COMPUTERS IN BIOLOGY AND MEDICINE
(2023)
Article
Neurosciences
Junhan Wei, Deying Kong, Xi Yu, Lili Wei, Yue Xiong, Adeline Yang, Bjorn Drobe, Jinhua Bao, Jiawei Zhou, Yi Gao, Zhifen He
Summary: The study aimed to investigate the impact of myopia on peripheral motion detection, finding that there was no significant difference in thresholds between refractive groups. However, lower motion detection thresholds were associated with higher myopia, particularly with low spatial frequency targets at 20 degrees.
FRONTIERS IN NEUROSCIENCE
(2021)
Article
Multidisciplinary Sciences
Matias A. Goldin, Baptiste Lefebvre, Samuele Virgili, Alexander Ecker, Thierry Mora, Ulisse Ferrari, Olivier Marre, Mathieu Kim Pham Van Cang
Summary: Retina ganglion cells extract specific features from natural scenes and respond to light increase or decrease depending on the visual context, and contrast is reliably encoded in these responses.
NATURE COMMUNICATIONS
(2022)
Article
Plant Sciences
Zane K. J. Hartley, Andrew P. French
Summary: This paper explores the impact of using synthetic data for wheat head detection on the global wheat head challenge dataset, demonstrating the challenges of domain augmentation and proposing a novel approach to improve scores.
Article
Computer Science, Artificial Intelligence
Aitzol Elu, Gorka Azkune, Oier Lopez de Lacalle, Ignacio Arganda-Carreras, Aitor Soroa, Eneko Agirre
Summary: This work focuses on inferring the spatial relationship between entities from textual descriptions, presenting a system that predicts the size and location of objects mentioned in captions directly from the text, showing that this approach is more effective than using manually annotated relations.
PATTERN RECOGNITION
(2021)
Article
Optics
Margarita B. Zlatkova, Kalina Racheva, Tsvetalin Totev, Milena Mihaylova, Ivan Hristov, Roger S. Anderson
Summary: In this study, it was found that green stimuli are more difficult to detect than red stimuli in the retinal periphery, showing a marked red-green asymmetry, with significant individual variations. This asymmetry is likely to have a postreceptoral origin, possibly at the cortical level.
JOURNAL OF THE OPTICAL SOCIETY OF AMERICA A-OPTICS IMAGE SCIENCE AND VISION
(2021)
Article
Neurosciences
Manuel Schottdorf, Barry B. Lee
Summary: Research shows that primate ganglion cell responses to natural scenes are primarily driven by temporal variations in color and luminance caused by eye movements, with little influence from interaction with receptive field structure. Model predictions suggest that responses derive from the temporal pattern of stimulation from eye movements, reducing redundancy in the retinal signal. The magnocellular pathway is better suited to transmit detailed structure of natural scenes than the parvocellular pathway.
JOURNAL OF PHYSIOLOGY-LONDON
(2021)
Article
Geography, Physical
Dima Kagan, Galit Fuhrmann Alpert, Michael Fire
Summary: A novel method for surveillance of Red Palm Weevil infested palm trees using deep learning algorithms and aerial/street-level imagery has been proposed, demonstrating efficiency in detecting infested trees in urban and open environments through large-scale testing.
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
(2021)
Review
Neurosciences
Eyal Seidemann, Wilson S. Geisler
ANNUAL REVIEW OF VISION SCIENCE, VOL 4
(2018)
Article
Multidisciplinary Sciences
Stephen Sebastian, Jared Abrams, Wilson S. Geisler
PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA
(2017)
Article
Ophthalmology
Brian C. McCann, Mary M. Hayhoe, Wilson S. Geisler
Article
Ophthalmology
Stephen Sebastian, Wilson S. Geisler
Article
Ophthalmology
Wilson S. Geisler
Article
Neurosciences
Melchi M. Michel, Yuzhi Chen, Eyal Seidemann, Wilson S. Geisler
JOURNAL OF NEUROSCIENCE
(2018)
Article
Neurosciences
Jason M. Samonds, Wilson S. Geisler, Nicholas J. Priebe
NATURE NEUROSCIENCE
(2018)
Correction
Neurosciences
Giacomo Benvenuti, Yuzhi Chen, Charu Ramakrishnan, Karl Deisseroth, Wilson S. Geisler, Eyal Seidemann
Article
Neurosciences
Giacomo Benvenuti, Yuzhi Chen, Charu Ramakrishnan, Karl Deisseroth, Wilson S. Geisler, Eyal Seidemann
Article
Ophthalmology
R. Calen Walshe, Wilson S. Geisler
Article
Multidisciplinary Sciences
Stephen Sebastian, Eric S. Seemiller, Wilson S. Geisler
PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA
(2020)
Article
Neurosciences
Yoon Bai, Spencer Chen, Yuzhi Chen, Wilson S. Geisler, Eyal Seidemann
Summary: In this study, macaque detection performance in natural images was measured, and their performance was compared to the detection sensitivity of neurophysiological responses recorded in the primary visual cortex (V1), as well as the performance of human subjects. The results showed that human and macaque behavioral performances are quantitatively in agreement and consistent with near-optimal decoding of V1 population responses.
JOURNAL OF NEUROPHYSIOLOGY
(2021)
Article
Ophthalmology
Abhranil Das, Wilson S. Geisler
Summary: The article discusses the use of univariate and multivariate normal probability distributions in modeling decisions under uncertainty, and presents mathematical results and open-source software for computing the performance of these models.
Article
Biochemistry & Molecular Biology
R. Calen Walshe, Wilson S. Geisler
Summary: The human visual system has a high-resolution fovea and a low-resolution periphery. Previous studies have shown that humans process all potential target locations with the same efficiency when searching for simple and small displays. However, when the target can appear anywhere within a large display, the sensitivity in the fovea and parafovea is greatly diminished.
Article
Biology
Spencer Chin-Yu Chen, Giacomo Benvenuti, Yuzhi Chen, Satwant Kumar, Charu Ramakrishnan, Karl Deisseroth, Wilson S. Geisler, Eyal Seidemann
Summary: The study investigates whether direct stimulation of primate V1 can substitute for a visual stimulus and mimic its perceptual effect. The researchers developed an optical-genetic toolkit to 'read' and 'write' neural population responses in behaving macaques. The results show that low-power optogenetic stimulation in V1 can mimic the visual masking effect, and there is a sublinear interaction between visual and optogenetic-evoked V1 responses that accounts for this effect. These findings provide further insights into perceptual substitutions by direct stimulation of sensory cortex.