Article
Computer Science, Artificial Intelligence
Tingsong Ma, Wenhong Tian, Yuanlun Xie
Summary: This paper proposes a knowledge distillation approach to transfer high-resolution features from a teacher network to a simpler structured student network trained on low-resolution inputs. Experimental results show that the proposed approach achieves higher accuracy than existing models in object detection and facial expression recognition tasks.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Biochemistry & Molecular Biology
Christopher A. Henry, Adam Kohn
Summary: Visual perception is influenced by spatial context, and visual crowding is an example where nearby stimuli impede the discrimination of object features. This study recorded neuronal activity in V1 and V4 of macaque monkeys and found that the presence of distractors led to a reduction in information about target orientation. The information loss was more severe in V4 and could be attributed to systematic changes in neuronal tuning. The study provides insights into the neural mechanisms underlying crowding effects in different stages of the visual hierarchy.
Article
Multidisciplinary Sciences
Adi Shechter, Amit Yashar
Summary: Through experiments, it was found that in a crowded environment, outer flankers are more likely to be noticed than inner flankers, indicating the important role of inner-outer asymmetry in crowding effects.
SCIENTIFIC REPORTS
(2021)
Article
Computer Science, Artificial Intelligence
B. Janakiramaiah, G. Kalyani, A. Karuna, L. V. Narasimha Prasad, M. Krishna
Summary: Automatic target detection plays a significant role in war operations. However, conventional convolutional neural networks suffer from limitations in handling small training datasets and location invariance. To address these issues, this paper introduces a multi-level CapsNet framework based on capsule networks for efficient military object recognition and demonstrates its high recognition precision through experiments.
Article
Geochemistry & Geophysics
Wuyong Tao, Xianghong Hua, Kegen Yu, Xijiang Chen, Bufan Zhao
Summary: This article presents an object recognition pipeline using a highly descriptive, robust, and computationally efficient local shape descriptor (LSD) to establish correspondences, a clustering method utilizing local reference frames (LRFs) of keypoints to select correct correspondences, and an index to verify transformation hypotheses. Experimental results show high descriptor matching performance, effective grouping of correct correspondences, and efficient filtering of false transformation hypotheses, enhancing recognition performance.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2021)
Article
Environmental Studies
Steffen Lange, Florian Kern, Jan Peuckert, Tilman Santarius
Summary: Literature on the rebound phenomenon has grown significantly over the last decade, but is characterized by diverse definitions, discrepancies in empirical estimates and policy proposals. This article develops a novel typology that differentiates between rebound mechanisms and effects, aiming to establish common ground for future research and policy development.
ENERGY RESEARCH & SOCIAL SCIENCE
(2021)
Article
Computer Science, Artificial Intelligence
Ali Caglayan, Nevrez Imamoglu, Ahmet Burak Can, Ryosuke Nakamura
Summary: This paper proposes a two-stage framework based on multi-modal RGB-D images for object and scene recognition tasks. In the first stage, a pretrained CNN model is used to extract visual features at multiple levels, and in the second stage, a fully randomized structure of RNNs is employed to map these features into high level representations. Multi-modal fusion is achieved through a soft voting approach, resulting in consistent class label estimation.
COMPUTER VISION AND IMAGE UNDERSTANDING
(2022)
Article
Engineering, Electrical & Electronic
Yuanjing Luo, Jiaohua Qin, Xuyu Xiang, Yun Tan
Summary: The proposed method utilizes multi-object recognition to generate robust binary sequences, introduces a novel mapping rule, effectively resists geometric attacks and noise attacks, with images remaining unmodified during transmission, demonstrating strong robustness.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2021)
Article
Computer Science, Artificial Intelligence
Xin Shen, Xudong Sun, Huibing Wang, Xianping Fu
Summary: Underwater object detection is essential for autonomous operation and ocean exploration of underwater robots. To address the challenges of poor imaging quality, harsh underwater environments, and concealed underwater targets, we propose a multi-dimensional, multi-functional, and multi-level attention module (mDFLAM). Our approach enhances the robustness, flexibility, and diversity of attention perception through strategies such as multi-dimensional information collection, capturing channel semantic information, and extracting intrinsic information under different receptive fields.
NEURAL COMPUTING & APPLICATIONS
(2023)
Article
Engineering, Electrical & Electronic
Xiaoyu Chen, Hongliang Li, Qingbo Wu, King Ngi Ngan, Linfeng Xu
Summary: This paper introduces PDC-Net, a multi-path detection calibration network, to address the data distribution discrepancy between object proposals and refined bounding-boxes. Built on Faster R-CNN, PDC-Net utilizes a multi-path detection head to calibrate detection results and improve accuracy.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2021)
Article
Ophthalmology
Jan W. Kurzawski, Augustin Burchell, Darshan Thapa, Jonathan Winawer, Najib J. Majaj, Denis G. Pelli
Summary: This article reports a survey study on visual crowding. The study found that crowding distance increases linearly with eccentricity. Several asymmetries consistent with previous reports were also observed among the observers. Additionally, a correction factor b' was proposed to standardize the measurement of the Bouma factor b.
Article
Multidisciplinary Sciences
Tijl Grootswagers, Ivy Zhou, Amanda K. Robinson, Martin N. Hebart, Thomas A. Carlson
Summary: This paper presents the THINGS-EEG dataset, which includes electroencephalography responses from 50 subjects to 1,854 object concepts and 22,248 images. This dataset can support research in understanding how the brain recognizes and processes visual objects.
Article
Ophthalmology
Li Zhaoping, Yushi Liu
Summary: According to the central-peripheral dichotomy, feedback from higher to lower cortical areas for target recognition is weaker in the peripheral visual field. This study found that metacontrast masking effects were weaker at larger eccentricities, consistent with the central-peripheral dichotomy.
Article
Management
Uzma Batool, Muhammad Mustafa Raziq, Naukhez Sarwar
Summary: Organizational systems are filled with tensions and paradoxes. Leaders who address and engage these tensions in constructive ways can unlock greater benefits for followers, teams, and the organization. A leader with a paradox mindset successfully deals with contradictory yet interdependent demands using paradoxical thinking, but this can also lead to negative consequences.
HUMAN RESOURCE MANAGEMENT REVIEW
(2023)
Article
Engineering, Electrical & Electronic
Jingjia Huang, Wei Yan, Ge Li, Thomas Li, Shan Liu
Summary: This paper proposes a new view-based 3D object recognition method that disentangles information from multi-view images to learn comprehensive descriptors while maintaining robustness to variations in view permutation. The method demonstrates effectiveness and competitive performance on various datasets, with codes to be released soon for replication.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2022)
Correction
Multidisciplinary Sciences
Mauro Manassi, Arni Kristjansson, David Whitney
SCIENTIFIC REPORTS
(2020)
Article
Ophthalmology
Ye Xia, Mauro Manassi, Ken Nakayama, Karl Zipser, David Whitney
Article
Biochemical Research Methods
Adrien Doerig, Lynn Schmittwilken, Bilge Sayim, Mauro Manassi, Michael H. Herzog
PLOS COMPUTATIONAL BIOLOGY
(2020)
Article
Ophthalmology
Karin S. Pilz, Juho M. Aijala, Mauro Manassi
Article
Ophthalmology
Alban Bornet, Oh-Hyeon Choung, Adrien Doerig, David Whitney, Michael H. Herzog, Mauro Manassi
Summary: The traditional pooling models cannot explain the high-level effects in crowding, and grouping effects in crowding also cannot be predicted by post-perceptual factors. This highlights the idea that complex target-flanker interactions determine crowding and crowding occurs at multiple levels of the visual hierarchy.
Article
Multidisciplinary Sciences
Mauro Manassi, David Whitney
Summary: Despite the dynamic nature of the visual world, our perceptual experience remains stable over time. This study introduces a previously unknown visual illusion that provides direct evidence for an online mechanism that continuously smooths our perceptions. The findings suggest that past visual experiences up to 15 seconds ago can influence the appearance of objects, indicating a continuous merging of object representation over time. This illusion of stability is attributed to an underlying active mechanism of serial dependence in visual representations.
Article
Psychology, Experimental
Mauro Manassi, Cristina Ghirardo, Teresa Canas-Bajo, Zhihang Ren, William Prinzmetal, David Whitney
Summary: Research was conducted on the impact of serial dependence on radiologists' recognition of lesions in radiological screening, revealing that radiologists' perception is influenced by previously seen stimuli. The study suggests that some diagnostic errors exhibited by radiologists may be caused by serial dependence from previously seen radiographs.
COGNITIVE RESEARCH-PRINCIPLES AND IMPLICATIONS
(2021)
Editorial Material
Biochemistry & Molecular Biology
David Whitney, Mauro Manassi, Yuki Murai
Summary: The study provides a model for interpreting the complex relationship between neural physiology and behavior.
Editorial Material
Biochemistry & Molecular Biology
David Whitney, Mauro Manassi
Summary: Visual crowding, a phenomenon that hampers object recognition, is countered by ensemble perception, which condenses redundant information into summary statistics.
Article
Psychology, Multidisciplinary
Zixuan Wang, Mauro Manassi, Zhihang Ren, Cristina Ghirardo, Teresa Canas-Bajo, Yuki Murai, Min Zhou, David Whitney
Summary: Radiologists' decisions are significantly influenced by their individual differences and perceptual biases. This study found that each radiologist has unique and systematic perceptual biases, which can be observed in different imaging modalities and task settings. Understanding and characterizing these biases is crucial for training, pairing readers, and career selection for radiologists, and may also have important implications for other fields where individual observers make life-altering perceptual decisions.
FRONTIERS IN PSYCHOLOGY
(2022)
Article
Medicine, General & Internal
Zhihang Ren, Xinyu Li, Dana Pietralla, Mauro Manassi, David Whitney
Summary: Serial Dependence is a common visual phenomenon where sequentially viewed images appear more similar than they actually are, providing a stable perceptual experience. This study analyzed skin cancer diagnostic records and found that perceptual judgments of lesion malignancy showed significant serial dependence. The dependence was influenced by image similarity and decayed over time. These findings help understand and mitigate systematic bias and errors in medical image perception tasks.
Review
Ophthalmology
Mauro Manassi, Yuki Murai, David Whitney
Summary: This article presents a meta-analysis of serial dependence in visual perception. It quantitatively assesses the key diagnostic characteristics of serial dependence across various domains and outlines the four main kinds of tuning that define serial dependence. The study also highlights the importance of individual differences in serial dependence and discusses future research directions.
Article
Psychology, Experimental
Fiammetta Marini, Clare A. M. Sutherland, Ba rbala Ostrovska, Mauro Manassi
Summary: Trustworthiness impressions are fundamental social judgements with far-reaching consequences. Research shows that people can extract an ensemble perception of trustworthiness from multiple faces. These findings contribute to the development of a more ecological approach to the study of trust impressions and expand the understanding of ensemble perception.
Article
Radiology, Nuclear Medicine & Medical Imaging
Zhihang Ren, Teresa Canas-Bajo, Cristina Ghirardo, Mauro Manassi, Stella X. Yu, David Whitney
Summary: This study examined the impact of serial dependence on clinicians' judgments of mammograms using realistic simulated images generated by a generative adversarial network (GAN). The results showed that serial dependence affected the perception of naturalistic GAN-generated mammograms and could contribute to decision errors in medical image perception tasks.
JOURNAL OF MEDICAL IMAGING
(2023)
Meeting Abstract
Ophthalmology
Fiammetta Marini, Karin S. Pilz, Mauro Manassi