Article
Computer Science, Artificial Intelligence
Mingtao Pei, Bin Yan, Huiling Hao, Meng Zhao
Summary: This paper proposes a person-specific face spoofing detection method that utilizes client identity information for improved detection accuracy. The method detects face spoofing after face recognition, using the identified client's face to assist in the detection. Experimental results demonstrate the effectiveness of the proposed method.
PATTERN RECOGNITION
(2023)
Article
Psychology, Mathematical
Jiali Song, Anna Kosovicheva, Benjamin Wolfe
Summary: Driving requires vision and cognition, but there is little empirical data on how they support safe driving. Studying perception during natural driving is difficult and dangerous, so we propose using realistic driving footage as stimuli. We curated a set of annotated video clips and asked observers to rate their perceived hazardousness.
BEHAVIOR RESEARCH METHODS
(2023)
Article
Computer Science, Information Systems
Jianjun Li, Peiqi Tang, Yong Wu, Mian Pan, Zheng Tang, Guobao Hui
Summary: The paper introduces a novel approach to change detection that utilizes depth information to assist semantic information, achieving better depth estimation through a gradual modification strategy. Experimental results demonstrate superior performance compared to current state-of-the-art methods.
MULTIMEDIA TOOLS AND APPLICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Deyun Dai, Jikai Wang, Zonghai Chen, Hao Zhao
Summary: This paper proposes a novel 3D vehicle detection method that introduces visual information to complement the deficiency of sparse LiDAR point clouds. The method consists of two stages, with a novel proposal generator in the first stage and a modified IoU prediction branch in the second stage to achieve a better balance between confidence and localization accuracy of boxes.
Article
Computer Science, Information Systems
Xun Gong, Bin Luo
Summary: Person re-identification (Re-ID) is an important computer vision task that aims to identify a person of interest across multiple non-overlapping cameras. Video-based person Re-ID has gained popularity due to its advantage of obtaining more feature information, including temporal information. However, challenges such as occlusion, multiple people, and target changes still exist. To address these issues, a network is proposed to integrate person attributes and scene attributes with person features for assisting person Re-ID. Extensive experiments on MARS and DukeMTMC-VID datasets demonstrate the competitive performance of the proposed methods.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Huibing Wang, Tianxiang Cui, Mingze Yao, Huijuan Pang, Yushan Du
Summary: This article introduces a method for person search using Generative Adversarial Networks (GAN) to synthesize surveillance video data. The authors design an Assisted-Identity Query Module (AIDQ) to provide positive images and propose a GAN-based Scene Synthesis model to generate high-quality cross-id person images. Experimental results show that this method achieves excellent performance in person search tasks.
IMAGE AND VISION COMPUTING
(2023)
Article
Psychology, Multidisciplinary
Marco Gandolfo, Hendrik Nagele, Marius Peelen
Summary: Boundary extension is a memory illusion where observers recall more of a scene than was actually seen. It is influenced by visual input and expectations, as well as the distance at which the scene is typically viewed. In this study, the depth of field was found to significantly affect boundary extension, with naturalistic depth of field leading to larger extensions. These findings suggest that boundary extension is a predictive mechanism that is most effective for naturalistic views, and highlight the importance of considering depth of field in scene perception and memory research.
PSYCHOLOGICAL SCIENCE
(2023)
Article
Automation & Control Systems
Zifan Song, Cairong Zhao, Guosheng Hu, Duoqian Miao
Summary: This article proposes a novel scene-pedestrian graph (SPG) model to explicitly model the interplay between pedestrians and scenes, and introduces a strategy to improve the quality of pedestrian bounding boxes. By designing a contextual and temporal graph matching algorithm, the contextual and temporal information is effectively utilized to enhance pedestrian matching performance.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2023)
Article
Geochemistry & Geophysics
Junmin Liu, Shijie Li, Changsheng Zhou, Xiangyong Cao, Yong Gao, Bo Wang
Summary: This paper proposes an anchor-free network for object detection in remote sensing images, which captures scene-contextual features and improves detection accuracy and generalization by introducing a data augmentation module.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Computer Science, Information Systems
Manahil Waheed, Samia Allaoua Chelloug, Mohammad Shorfuzzaman, Abdulmajeed Alsufyani, Ahmad Jalal, Khaled Alnowaiser, Jeongmin Park
Summary: Identifying human actions and interactions is widely used in various fields, attracting many researchers. This paper proposes a new and efficient human-object interaction recognition model based on human pose and scene feature information. The main objectives of this research include evaluating the importance of different elements in determining interactions, estimating human pose using image foresting transform, and detecting interactions based on an optimized multi-feature vector.
CMC-COMPUTERS MATERIALS & CONTINUA
(2023)
Article
Computer Science, Artificial Intelligence
Bharathkumar Ramachandra, Michael J. Jones, Ranga Raju Vatsavai
Summary: This article summarizes the research trends on anomaly detection in video feeds of a single scene. It discusses problem formulations, available datasets, evaluation criteria, and provides a comprehensive comparison of algorithm accuracy on standard test sets. The article also offers best practices and suggests future research directions.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2022)
Article
Geochemistry & Geophysics
Xi Wu, Zhenwei Shi
Summary: This article introduces a new deep learning network called Scene Aggregation Network (SAN) for cloud detection. Unlike traditional cloud detection algorithms, SAN aggregates scene information in the framework and utilizes the fused features to generate cloud masks. Experimental results demonstrate the robustness of this method across different scenes, with performance surpassing other state-of-the-art methods.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2022)
Article
Computer Science, Artificial Intelligence
Yiheng Liu, Wengang Zhou, Qiaokang Xie, Houqiang Li
Summary: Existing unsupervised person re-identification methods only rely on visual clues, but introducing heterogeneous data can compensate for its limitations. In this paper, we propose an unsupervised multimodal training framework that combines visual data and wireless positioning trajectories under weak scene labeling. Our proposed framework effectively models the complementarity of both data sources and achieves a model that does not require human labeling. Experimental results on challenging datasets demonstrate the effectiveness of the proposed method.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2023)
Review
Computer Science, Information Systems
Ednawati Rainarli, Suprapto, Wahyono
Summary: The rapid development of scene text detection highlights the need for text recognition in scene images. This review analyzes the related research of scene text detection in the last decade, discussing the strengths and weaknesses of different methods and showcasing the application of deep learning in text detection. Researchers have been focusing on detecting horizontal text, multi-orientation text, multilingual text, curved text, and arbitrary-shaped text.
COMPUTER SCIENCE REVIEW
(2021)
Article
Computer Science, Interdisciplinary Applications
Xiaomeng Wang, Alan F. Blackwell, Richard Jones, Hieu T. Nguyen
Summary: Scene Walk is a video viewing technique suited to first-person video recorded from wearable cameras, allowing viewers to create a more accurate cognitive map of the captured environment. By integrating the camera trajectory visualization and non-photorealistic partial rendering of the 3D environment, it provides a more detailed experience than a conventional video browsing interface.
Article
Clinical Neurology
Steve Berggren, Sue Fletcher-Watson, Nina Milenkovic, Peter B. Marschik, Sven Bolte, Ulf Jonsson
DEVELOPMENTAL NEUROREHABILITATION
(2018)
Article
Psychiatry
Anders Nordahl-Hansen, Magnus Tondevold, Sue Fletcher-Watson
PSYCHIATRY RESEARCH
(2018)
Article
Psychology, Biological
Sheena K. Au-Yeung, Johanna K. Kaakinen, Simon P. Liversedge, Valerie Benson
QUARTERLY JOURNAL OF EXPERIMENTAL PSYCHOLOGY
(2018)
Article
Multidisciplinary Sciences
Sue Fletcher-Watson, Sarah Hampton
SCIENTIFIC REPORTS
(2018)
Article
Multidisciplinary Sciences
Jiayu Tao, Zhao Qin, Zhu Meng, Li Zhang, Lu Liu, Guoli Yan, Valerie Bensonid
Article
Multidisciplinary Sciences
Li Zhang, Guoli Yan, Valerie Benson
Summary: The study revealed that both children with ASD and typically developing children made more incorrect eye movements towards angry and happy emotional faces, indicating difficulties in disengaging attention from angry faces.
Article
Psychology, Developmental
Li Zhang, Guoli Yan, Li Zhou, Zebo Lan, Valerie Benson
JOURNAL OF AUTISM AND DEVELOPMENTAL DISORDERS
(2020)
Article
Psychology, Developmental
Sue Fletcher-Watson, Jon Adams, Kabie Brook, Tony Charman, Laura Crane, James Cusack, Susan Leekam, Damian Milton, Jeremy R. Parr, Elizabeth Pellicano
Article
Psychology, Developmental
Margaret Holmes Laurie, Petra Warreyn, Blanca Villamia Uriarte, Charlotte Boonen, Sue Fletcher-Watson
JOURNAL OF AUTISM AND DEVELOPMENTAL DISORDERS
(2019)
Article
Psychology, Developmental
Sue Fletcher-Watson, Kenneth Larsen, Erica Salomone, Fabio Apicella, Bonnie Auyeung, Stepanka Beranova, Frederique Bonnet-Brilhault, Ricardo Canal Bedia, Tony Charman, Natasha Chericoni, Ines C. Conceicao, Kim Davies, Teresa Faroni, Marie Gomot, Emily Jones, Anett Kaale, Katarzyna Kapica, Rafal Kawa, Anneil Kylliainen, Jeremy LeFort-Besnard, Joelle Malvy, Sara Manso de Dios, Silvana Markovska-Simoska, Inbal Millo, Natercia Miranda, Greg Pasco, Ewa Pisula, Marija Raleva, Bernadette Roge, Synnve Schjolberg, Przemyslaw Tomalski, Astrid M. Vicente, Nurit Yirmiya
Proceedings Paper
Computer Science, Hardware & Architecture
Mihaela Dragomir, Andrew Manches, Sue Fletcher-Watson, Helen Pain
ASSETS'18: PROCEEDINGS OF THE 20TH INTERNATIONAL ACM SIGACCESS CONFERENCE ON COMPUTERS AND ACCESSIBILITY
(2018)
Article
Behavioral Sciences
Philippa L. Howard, Simon P. Liversedge, Valerie Benson
Article
Education, Special
Hsiao-Wei Joy Tsai, Katie Cebula, S. H. Liang, Sue Fletcher-Watson
RESEARCH IN DEVELOPMENTAL DISABILITIES
(2018)
Article
Rehabilitation
Katie L. Meadmore, Timothy A. Exell, Jane H. Burridge, Ann-Marie Hughes, Christopher T. Freeman, Valerie Benson
DISABILITY AND REHABILITATION
(2018)
Article
Psychology, Developmental
Anders Nordahl-Hansen, Roald A. Oien, Sue Fletcher-Watson
JOURNAL OF AUTISM AND DEVELOPMENTAL DISORDERS
(2018)