Article
Computer Science, Artificial Intelligence
Ammar Mansoor Kamoona, Amirali Khodadadian Gostar, Alireza Bab-Hadiashar, Reza Hoseinnezhad
Summary: In this paper, a weakly supervised deep temporal encoding-decoding solution for anomaly detection in surveillance videos using multiple instance learning is proposed. The approach considers the temporal relations between video instances and employs a deep temporal encoding-decoding network to capture the spatio-temporal evolution. The new loss function ensures a low false alarm rate.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Fang Wan, Qixiang Ye, Tianning Yuan, Songcen Xu, Jianzhuang Liu, Xiangyang Ji, Qingming Huang
Summary: This paper proposes a Multiple Instance Differentiation Learning (MIDL) method for instance-level active learning, which unifies instance uncertainty with image uncertainty for informative image selection. Extensive experiments on commonly used object detection datasets validate that MIDL outperforms other state-of-the-art methods, especially when the labeled sets are small.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2023)
Article
Biochemical Research Methods
Younghoon Kim, Tao Wang, Danyi Xiong, Xinlei Wang, Seongoh Park
Summary: This paper proposes a multiple instance neural network based on sparse attention (MINN-SA) to enhance the performance and explainability of cancer detection. The research shows that MINN-SA outperforms existing multiple instance learning methods in predicting various types of cancers and can identify TCRs specific to tumor antigens.
BMC BIOINFORMATICS
(2022)
Article
Computer Science, Artificial Intelligence
Qun Li, Rui Yang, Fu Xiao, Bir Bhanu, Feng Zhang
Summary: This paper proposes a method for anomaly detection using future frame prediction framework and Multiple Instance Learning framework, with introduction of memory addressing module and novel loss function. A multi-view dataset containing various anomalies and normal activities was also introduced, and experimental results demonstrate the effectiveness of the methods on multiple datasets.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Wei Gao, Fang Wan, Jun Yue, Songcen Xu, Qixiang Ye
Summary: D-MIL introduces discrepantly collaborative modules into MIL, creating complementary solutions for precise object localization through multiple MIL learners. The teachers-students model improves performance by providing rich information and absorbing complementary knowledge from multiple teachers. D-MIL achieves state-of-the-art performance on the challenging MS-COCO object detection benchmark.
PATTERN RECOGNITION
(2022)
Article
Engineering, Multidisciplinary
Lin Wang, Xiangjun Wang, Feng Liu, Mingyang Li, Xin Hao, Nianfu Zhao
Summary: This paper proposes an anomaly detection method based on weakly supervised learning, which transforms the weakly supervised learning problem into a fully supervised learning problem through a pseudo-label generation technique. The network combines attention and guidance augmentation modules to improve the model's spatial localization capability. Experimental results show that the method achieves high AUC values on datasets with different scales and scene complexity.
Article
Computer Science, Information Systems
Mengting Liu, Xinrui Li, Yongge Liu, Yahong Han
Summary: Due to the low frequency and complexity of abnormal behaviors in the real world, anomaly detection in surveillance video is challenging. Weakly supervised video anomaly detection, formulated as a multiple instance learning task, shows effective detection performance but faces challenges in distinguishing abnormal behaviors similar to normal behaviors. Current methods sometimes overlook the impact of temporal factors. To address these issues, we propose a cascaded multi-level contextual content analysis module (CMC) that adapts temporal-aware graph convolutional network and non-local neural network to aggregate contextual features. Our method demonstrates improved performance and effectiveness.
MULTIMEDIA SYSTEMS
(2023)
Article
Chemistry, Analytical
Mohammad Ibrahim Sarker, Cristina Losada-Gutierrez, Marta Marron-Romera, David Fuentes-Jimenez, Sara Luengo-Sanchez
Summary: Surveillance cameras are crucial for public safety in daily living places, with automatic detection of anomalies being increasingly important. Supervised approaches outperform unsupervised ones in anomaly detection, and a weakly supervised learning algorithm shows competitive performance with high sensitivity in detecting anomalies in video-surveillance scenes.
Article
Geochemistry & Geophysics
Bo Yang, Yi He, Changzhe Jiao, Xiao Pan, Guozhen Wang, Lei Wang, Jinjian Wu
Summary: This article proposes a multiple-instance metric learning neural network (MIML-Net) for hyperspectral target detection tasks, which only requires region-level labels and greatly alleviates the laborious pixel-level annotation problems.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2023)
Article
Multidisciplinary Sciences
Ahad Alloqmani, Yoosef B. Abushark, Asif Irshad Khan
Summary: This article proposes an efficient and accurate deep learning-based anomaly detection framework for recognizing breast abnormalities. The framework consists of two stages: data pre-processing and feature extraction. The evaluation results showed that the framework outperforms recent works and overcomes their limitations.
ARABIAN JOURNAL FOR SCIENCE AND ENGINEERING
(2023)
Article
Computer Science, Artificial Intelligence
Jian Cheng, Fengquan Zhang, Guiling Wang, Wancai Zhang
Summary: In this paper, a multi-stage fusion instance learning method (MFIL) is proposed for inferring anomalous event pattern and predicting anomaly appearance in videos. The method utilizes object-aware and action-aware models, as well as cascaded deep network models, to represent regularities of human objects and actions among frames. Experimental results demonstrate the effectiveness of the proposed method for anomalous event detection in videos gathered from real world.
INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS
(2023)
Article
Computer Science, Information Systems
R. Pourhashemi, E. Mahmoudzadeh
Summary: This paper proposes an approach for anomaly detection using convolutional sparse representation method, which captures the characteristics of normal structures and utilizes sparse coding technique for feature extraction and detection. The results show higher True Positive Rate (TPR) and lower False Positive Rate (FPR) compared to existing methods.
MULTIMEDIA TOOLS AND APPLICATIONS
(2022)
Article
Engineering, Biomedical
Liu Cheng, Shengqiong Luo, Baozhu Li, Ran Liu, Yuan Zhang, Haibo Zhang
Summary: This paper proposes an automatic OSA detection framework based on EEG signals. By extracting features from sub-frames and mining the interactive relationship between different instances, the framework can effectively distinguish OSA event fragments. It also introduces instance-level and bag-level tasks for OSA event detection, and redefines evaluation criteria to comprehensively evaluate the model's performance.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2023)
Article
Geochemistry & Geophysics
Binglu Wang, Yongqiang Zhao, Xuelong Li
Summary: This study proposes a multiple instance graph (MIG) learning framework for weakly supervised object detection (WSOD) in remote sensing images (RSIs). The framework utilizes spatial and appearance graphs to detect high-quality objects and mine possible instances with the same class.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Computer Science, Artificial Intelligence
Thakare Kamalakar Vijay, Nitin Sharma, Debi Prosad Dogra, Heeseung Choi, Ig-Jae Kim
Summary: This paper proposes a method for abnormal event detection using spatio-temporal deep feature extractors and multiple instance learning classifier. By injecting temporal information in feature extraction, the accuracy of anomaly detection is improved. Experimental results show significant improvements in detecting long-duration anomalies and increasing detection accuracy across various categories.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Biophysics
Mathieu Lempereur, Francois Rousseau, Olivier Remy-Neris, Christelle Pons, Laetitia Houx, Gwenole Quellec, Sylvain Brochard
JOURNAL OF BIOMECHANICS
(2020)
Article
Computer Science, Artificial Intelligence
Prasanna Porwal, Samiksha Pachade, Manesh Kokare, Girish Deshmukh, Jaemin Son, Woong Bae, Lihong Liu, Jianzong Wang, Xinhui Liu, Liangxin Gao, TianBo Wu, Jing Xiao, Fengyan Wang, Baocai Yin, Yunzhi Wang, Gopichandh Danala, Linsheng He, Yoon Ho Choi, Yeong Chan Lee, Sang-Hyuk Jung, Zhongyu Li, Xiaodan Sui, Junyan Wu, Xiaolong Li, Ting Zhou, Janos Toth, Agnes Bara, Avinash Kori, Sai Saketh Chennamsetty, Mohammed Safwan, Varghese Alex, Xingzheng Lyu, Li Cheng, Qinhao Chu, Pengcheng Li, Xin Ji, Sanyuan Zhang, Yaxin Shen, Ling Dai, Oindrila Saha, Rachana Sathish, Tania Melo, Teresa Araujo, Balazs Harangi, Bin Sheng, Ruogu Fang, Debdoot Sheet, Andras Hajdu, Yuanjie Zheng, Ana Maria Mendonca, Shaoting Zhang, Aurelio Campilho, Bin Zheng, Dinggang Shen, Luca Giancardo, Gwenole Quellec, Fabrice Meriaudeau
MEDICAL IMAGE ANALYSIS
(2020)
Article
Computer Science, Artificial Intelligence
Gwenole Quellec, Mathieu Lamard, Pierre-Henri Conze, Pascale Massin, Beatrice Cochener
MEDICAL IMAGE ANALYSIS
(2020)
Article
Computer Science, Artificial Intelligence
Yutong Yan, Pierre-Henri Conze, Mathieu Lamard, Gwenole Quellec, Beatrice Cochener, Gouenou Coatrieux
Summary: This study introduces a multi-tasking framework combining craniocaudal and mediolateral-oblique mammograms to jointly learn breast mass matching and classification using deep networks, resulting in improved breast cancer detection performance.
MEDICAL IMAGE ANALYSIS
(2021)
Article
Computer Science, Artificial Intelligence
Gwenole Quellec, Hassan Al Hajj, Mathieu Lamard, Pierre-Henri Conze, Pascale Massin, Beatrice Cochener
Summary: This paper introduces an explanatory Artificial Intelligence algorithm called ExplAIn, which achieves the same performance level as black-box AI algorithms in classifying the severity of diabetic retinopathy. The algorithm is trained with image supervision, allowing the concepts of lesions and lesion categories to emerge by themselves for explainable automatic diagnoses.
MEDICAL IMAGE ANALYSIS
(2021)
Article
Computer Science, Artificial Intelligence
Maria Grammatikopoulou, Evangello Flouty, Abdolrahim Kadkhodamohammadi, Gwenole Quellec, Andre Chow, Jean Nehme, Imanol Luengo, Danail Stoyanov
Summary: Video feedback is crucial for surgical procedures and scene understanding in computer assisted interventions. Semantic segmentation is essential for identifying and localizing surgical instruments and anatomical structures, with deep learning advancing techniques in recent years. This paper introduces a dataset for semantic segmentation of cataract surgery videos and benchmarks the performance of deep learning models.
MEDICAL IMAGE ANALYSIS
(2021)
Review
Ophthalmology
Ikram Brahim, Mathieu Lamard, Anas-Alexis Benyoussef, Gwenole Quellec
Summary: This review examines the diagnosis methods of dry eye disease (DED), exploring the incorporation of automation. The diagnostic methods are categorized into classical, semi-automated, and promising AI-based automated methods.
CLINICAL AND EXPERIMENTAL OPHTHALMOLOGY
(2022)
Article
Computer Science, Interdisciplinary Applications
Huihui Fang, Fei Li, Huazhu Fu, Xu Sun, Xingxing Cao, Fengbin Lin, Jaemin Son, Sunho Kim, Gwenole Quellec, Sarah Matta, Sharath M. Shankaranarayana, Yi-Ting Chen, Chuen-Heng Wang, Nisarg A. Shah, Chia-Yen Lee, Chih-Chung Hsu, Hai Xie, Baiying Lei, Ujjwal Baid, Shubham Innani, Kang Dang, Wenxiu Shi, Ravi Kamble, Nitin Singhal, Ching-Wei Wang, Shih-Chang Lo, Jose Ignacio Orlando, Hrvoje Bogunovic, Xiulan Zhang, Yanwu Xu
Summary: This paper introduces the ADAM challenge, dataset, evaluation methods, and summarizes the participating methods and their results. It is found that the ensembling strategy and the incorporation of clinical domain knowledge are key to improving the performance of deep learning models.
IEEE TRANSACTIONS ON MEDICAL IMAGING
(2022)
Article
Computer Science, Information Systems
Samiksha Pachade, Prasanna Porwal, Dhanshree Thulkar, Manesh Kokare, Girish Deshmukh, Vivek Sahasrabuddhe, Luca Giancardo, Gwenole Quellec, Fabrice Meriaudeau
Summary: The world faces challenges in eye care, particularly in detecting and diagnosing rare pathologies, while common diseases have received more attention.
Meeting Abstract
Ophthalmology
Mathieu Lamard, Jean-Bernard Rottier, Beatrice Cochener, Pascale Massin, Gwenole Quellec, Sarah Christina Zahida Matta
INVESTIGATIVE OPHTHALMOLOGY & VISUAL SCIENCE
(2020)
Meeting Abstract
Ophthalmology
Bruno Lay, Ronan Danno, Gwenole Quellec, Mathieu Lamard, Beatrice Cochener, Ali Erginay, Pascale Massin, Alexandre Le Guilcher
INVESTIGATIVE OPHTHALMOLOGY & VISUAL SCIENCE
(2020)
Meeting Abstract
Ophthalmology
Sarah Matta, Mathieu Lamard, Pascale Massin, Gwenole Quellec, Beatrice Cochener
INVESTIGATIVE OPHTHALMOLOGY & VISUAL SCIENCE
(2020)
Meeting Abstract
Ophthalmology
Gwenole Quellec, Mathieu Lamard, Pierre-Henri Conze, Pascale Massin, Beatrice Cochener
INVESTIGATIVE OPHTHALMOLOGY & VISUAL SCIENCE
(2020)
Meeting Abstract
Ophthalmology
Guillaume Normand, Gwenole Quellec, Ronan Danno, Bruno Lay, Georges Weissgerber, Nadia Zakaria, Sudeep Chandra
INVESTIGATIVE OPHTHALMOLOGY & VISUAL SCIENCE
(2019)
Meeting Abstract
Ophthalmology
Bruno Lay, Ronan Danno, Gwenole Quellec, Etienne Decenciere, Ali Erginay, Pascale Massin, Alexandre Le Guilcher, Mathieu Lamard, Beatrice Cochener, Robin Alais
INVESTIGATIVE OPHTHALMOLOGY & VISUAL SCIENCE
(2019)