Vadclip: Adapting Vision-Language Models For Weakly Supervised Video Anomaly Detection,
2024
Singapore Management University
Vadclip: Adapting Vision-Language Models For Weakly Supervised Video Anomaly Detection, Peng Wu, Xuerong Zhou, Guansong Pang, Lingru Zhou, Qingsen Yan, Peng Wang, Yanning Zhang
Research Collection School Of Computing and Information Systems
The recent contrastive language-image pre-training (CLIP) model has shown great success in a wide range of image-level tasks, revealing remarkable ability for learning powerful visual representations with rich semantics. An open and worthwhile problem is efficiently adapting such a strong model to the video domain and designing a robust video anomaly detector. In this work, we propose VadCLIP, a new paradigm for weakly supervised video anomaly detection (WSVAD) by leveraging the frozen CLIP model directly without any pre-training and fine-tuning process. Unlike current works that directly feed extracted features into the weakly supervised classifier for frame-level binary classification, VadCLIP makes …
Imitate The Good And Avoid The Bad: An Incremental Approach To Safe Reinforcement Learning,
2024
Singapore Management University
Imitate The Good And Avoid The Bad: An Incremental Approach To Safe Reinforcement Learning, Minh Huy Hoang, Tien Mai, Pradeep Varakantham
Research Collection School Of Computing and Information Systems
A popular framework for enforcing safe actions in Rein- forcement Learning (RL) is Constrained RL, where trajectory based constraints on expected cost (or other cost measures) are employed to enforce safety and more importantly these constraints are enforced while maximizing expected reward. Most recent approaches for solving Constrained RL convert the trajectory based cost constraint into a surrogate problem that can be solved using minor modifications to RL methods. A key drawback with such approaches is an over or under- estimation of the cost constraint at each state. Therefore, we provide an approach that does not modify the trajectory based …
Harnessing Holistic Discourse Features And Triadic Interaction For Sentiment Quadruple Extraction In Dialogues,
2024
Singapore Management University
Harnessing Holistic Discourse Features And Triadic Interaction For Sentiment Quadruple Extraction In Dialogues, Bobo Li, Hao Fei, Lizi Liao, Et Al
Research Collection School Of Computing and Information Systems
Dialogue Aspect-based Sentiment Quadruple (DiaASQ) is a newly-emergent task aiming to extract the sentiment quadruple (i.e., targets, aspects, opinions, and sentiments) from conversations. While showing promising performance, the prior DiaASQ approach unfortunately falls prey to the key crux of DiaASQ, including insufficient modeling of discourse features, and lacking quadruple extraction, which hinders furthertask improvement. To this end, we introduce a novel framework that not only capitalizes on comprehensive discourse feature modeling, but also captures the intrinsic interaction for optimal quadruple extraction. On the one hand, drawing upon multiple discourse features, our approach constructs a token-level heterogeneous graph and enhances token …
Unsupervised Training Sequence Design: Efficient And Generalizable Agent Training,
2024
Singapore Management University
Unsupervised Training Sequence Design: Efficient And Generalizable Agent Training, Wenjun Li, Pradeep Varakantham
Research Collection School Of Computing and Information Systems
To train generalizable Reinforcement Learning (RL) agents, researchers recently proposed the Unsupervised Environment Design (UED) framework, in which a teacher agent creates a very large number of training environments and a student agent trains on the experiences in these environments to be robust against unseen testing scenarios. For example, to train a student to master the “stepping over stumps” task, the teacher will create numerous training environments with varying stump heights and shapes. In this paper, we argue that UED neglects training efficiency and its need for very large number of environments (henceforth referred to as infinite horizon training) makes …
Broadening Participation Of Teachers In Computing: Examining Postsecondary Educational Experiences And Prospective Educators’ Cs Teaching Interests,
2024
American Institutes for Research
Broadening Participation Of Teachers In Computing: Examining Postsecondary Educational Experiences And Prospective Educators’ Cs Teaching Interests, Robert Schwarzhaupt, Alexsandra Galanis, Joanna Goode, Kate Blanchard, Jill Bowdon, Joseph P. Wilson
Journal of Computer Science Integration
Teacher shortages in K–12 computer science (CS) education negatively impact students’ access to CS courses, exposure to CS concepts, and interest in CS-related careers. To address CS teacher shortages, this study seeks to understand factors related to expressing a preference to teach CS among prospective teachers. The study team analyzed data from 27,700 prospective teacher applications accepted into the 2016–2020 Teach For America (TFA) corps (cohorts). The TFA corps is an alternative teacher development program that recruits and prepares participants to obtain their teaching certification while they work for at least two years in underserved communities on a temporary teaching …
Does Chatgpt Know Calculus?,
2024
St. John Fisher University
Does Chatgpt Know Calculus?, Kris H. Green
Journal of Humanistic Mathematics
Academics and educators across the world are grappling with how OpenAI’s new software, ChatGPT, will impact teaching and learning. This essay explores ChatGPT’s response to a typical calculus problem as a way of illustrating its functionality and limitations.
Dynamic Prognosis Prediction For Patients On Dapt After Drug-Eluting Stent Implantation: Model Development And Validation,
2024
University of Texas Health Science Center at Houston
Dynamic Prognosis Prediction For Patients On Dapt After Drug-Eluting Stent Implantation: Model Development And Validation, Fang Li, Laila Rasmy, Yang Xiang, Jingna Feng, Ahmed Abdelhameed, Xinyue Hu, Zenan Sun, David Aguilar, Abhijeet Dhoble, Jingcheng Du, Qing Wang, Shuteng Niu, Yifang Dang, Xinyuan Zhang, Ziqian Xie, Yi Nian, Jianping He, Yujia Zhou, Jianfu Li, Mattia Prosperi, Jiang Bian, Degui Zhi, Cui Tao
School of Medicine Faculty Publications
BACKGROUND: The rapid evolution of artificial intelligence (AI) in conjunction with recent updates in dual antiplatelet therapy (DAPT) management guidelines emphasizes the necessity for innovative models to predict ischemic or bleeding events after drug-eluting stent implantation. Leveraging AI for dynamic prediction has the potential to revolutionize risk stratification and provide personalized decision support for DAPT management. METHODS AND RESULTS: We developed and validated a new AI-based pipeline using retrospective data of drug-eluting stent-treated patients, sourced from the Cerner Health Facts data set (n=98 236) and Optum’s de-identified Clinformatics Data Mart Database (n=9978). The 36 months following drug-eluting stent implantation were …
Promises And Risks Of Applying Ai Medical Imaging To Early Detection Of Cancers, And Regulation For Ai Medical Imaging,
2024
The Johns Hopkins University
Promises And Risks Of Applying Ai Medical Imaging To Early Detection Of Cancers, And Regulation For Ai Medical Imaging, Yiyao Zhang
The Journal of Purdue Undergraduate Research
No abstract provided.
A Survey On Training Challenges In Generative Adversarial Networks For Biomedical Image Analysis,
2024
Department of Computer Science, Munster Technological University (MTU), Cork, Ireland
A Survey On Training Challenges In Generative Adversarial Networks For Biomedical Image Analysis, Muhammad Muneeb Saad, Ruairi O'Reilly, Mubashir Husain Rehmani
Department of Computer Science Publications
In biomedical image analysis, the applicability of deep learning methods is directly impacted by the quantity of image data available. This is due to deep learning models requiring large image datasets to provide high-level performance. Generative Adversarial Networks (GANs) have been widely utilized to address data limitations through the generation of synthetic biomedical images. GANs consist of two models. The generator, a model that learns how to produce synthetic images based on the feedback it receives. The discriminator, a model that classifies an image as synthetic or real and provides feedback to the generator. Throughout the training process, a GAN …
Natural Language Processing Analysis Of Online Reviews For Small Business: Extracting Insight From Small Corpora,
2024
Air Force Institute of Technology
Natural Language Processing Analysis Of Online Reviews For Small Business: Extracting Insight From Small Corpora, Benjamin J. Mccloskey, Phillip M. Lacasse, Bruce A. Cox
Faculty Publications
Receiving and acting on customer input is essential to sustaining and growing any service organization, particularly a small family business whose livelihood depends on strong relationships with its customers. The competitive advantage offered by advanced analytical approaches for supporting decisions is not trivial, and enterprises across virtually all domains of society are investing heavily in this emerging discipline. Natural Language Processing (NLP) is a subset of computer science that employs computational approaches to analyze human language; it is effective at extracting insight from text data but frequently requires large corpora to train its models, in the scale of thousands or …
De Novo Drug Design Using Transformer-Based Machine Translation And Reinforcement Learning Of An Adaptive Monte Carlo Tree Search,
2024
Chapman University
De Novo Drug Design Using Transformer-Based Machine Translation And Reinforcement Learning Of An Adaptive Monte Carlo Tree Search, Dony Ang, Cyril Rakovski, Hagop S. Atamian
Biology, Chemistry, and Environmental Sciences Faculty Articles and Research
The discovery of novel therapeutic compounds through de novo drug design represents a critical challenge in the field of pharmaceutical research. Traditional drug discovery approaches are often resource intensive and time consuming, leading researchers to explore innovative methods that harness the power of deep learning and reinforcement learning techniques. Here, we introduce a novel drug design approach called drugAI that leverages the Encoder–Decoder Transformer architecture in tandem with Reinforcement Learning via a Monte Carlo Tree Search (RL-MCTS) to expedite the process of drug discovery while ensuring the production of valid small molecules with drug-like characteristics and strong binding affinities towards …
Anthropomorphism And Human-Robot Interaction,
2024
Montclair State University
Anthropomorphism And Human-Robot Interaction, Rae Yule Kim
Department of Economics Faculty Scholarship and Creative Works
Exploring how human appreciation for and interactions with robots are influenced by anthropomorphic features.
Scene Graph Generation: A Comprehensive Survey,
2024
Edith Cowan University
Scene Graph Generation: A Comprehensive Survey, Hongsheng Li, Guangming Zhu, Liang Zhang, Youliang Jiang, Yixuan Dang, Haoran Hou, Peiyi Shen, Xia Zhao, Syed A. A. Shah, Mohammed Bennamoun
Research outputs 2022 to 2026
Deep learning techniques have led to remarkable breakthroughs in the field of object detection and have spawned a lot of scene-understanding tasks in recent years. Scene graph has been the focus of research because of its powerful semantic representation and applications to scene understanding. Scene Graph Generation (SGG) refers to the task of automatically mapping an image or a video into a semantic structural scene graph, which requires the correct labeling of detected objects and their relationships. In this paper, a comprehensive survey of recent achievements is provided. This survey attempts to connect and systematize the existing visual relationship detection …
Spatio-Temporal Association Rule Mining Of Traffic Congestion In A Large-Scale Road Network Based On
Trajectory Data,
2024
School of Transportation and Logistics, Southwest Jiaotong University, Chengdu 611756, China
Spatio-Temporal Association Rule Mining Of Traffic Congestion In A Large-Scale Road Network Based On Trajectory Data, Qifan Zhou, Haixu Liu, Zhipeng Dong, Yin Xu
Journal of System Simulation
Abstract: A K neighbor-RElim (KNR) algorithm and a sequential KNbr-RElim (SKNR) algorithm are proposed to mine traffic congestion association rules and congestion propagation spatio-temporal association rules by vehicle trajectory data in a large-scale road network. The KNR algorithm extends the spatial topology constraint based on the RElim algorithm. The KNR can be used to mine the road links prone to congestion from the large-scale trajectory dataset in a large-scale road network and quantify the strength of association for congested road links. The SKNR algorithm expands the time dimension in the form of sliding window and can be applied for mining …
Modeling And Analysing Of Complex Combat Systems Based On Symbiosis Theory,
2024
College of Automation Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China
Modeling And Analysing Of Complex Combat Systems Based On Symbiosis Theory, Xiangrui Tian, Jie Ying, Rui Yao, Xiaodong Wan
Journal of System Simulation
Abstract: As the combat systems develop towards clustering, coordination, unmanned, and intelligent direction, traditional combat system modeling methods are unable to reflect the complexity and intelligence of the combat systems. By drawing on symbiosis theory, this paper models and analyzes complex combat systems, and decomposes the complex combat system into various subsystems according to combat missions. The combat units, interaction modes, and combat environments in the subsystems are analyzed. The paper builds mathematical models to capture the collaborative interaction relationships between combat units, finally constructing a symbiotic model of complex combat systems. By the symbiosis principles and methods, quantitative analysis …
Action Recognition Model Of Directed Attention Based On Cosine Similarity,
2024
Command & Control Engineering College, Army Engineering University of PLA, Nanjing 210007, China
Action Recognition Model Of Directed Attention Based On Cosine Similarity, Chen Li, Ming He, Chen Dong, Wei Li
Journal of System Simulation
Abstract: Aiming at the lack of directionality of traditional dot product attention, this paper proposes a directed attention model (DAM) based on cosine similarity. To effectively represent the direction relationship between the spatial and temporal features of video frames, the paper defines the relationship function in the attention mechanism using the cosine similarity theory, which can remove the absolute value of the relationship between features. To reduce the computational burden of the attention mechanism, the operation is decomposed from two dimensions of time and space. The computational complexity is further optimized by combining linear attention operation. The experiment is divided …
Overall Scheme Design And Integration Testing Of Hardware-In-The-Loop Simulation Of Guidance And Control
System,
2024
Unmanned System Research Institute, Northwestern Polytechnical University, Xi'an 710072, China
Overall Scheme Design And Integration Testing Of Hardware-In-The-Loop Simulation Of Guidance And Control System, Xiaofei Chang, Jiayue Jiao, Kang Chen, Wenxing Fu, Jie Yan
Journal of System Simulation
Abstract: Hardware-in-the-loop simulation system is a complex distributed simulation system, and its design and integration directly affect the system performance and construction goals. Based on years of experience, this paper first summarizes the design of the overall scheme and analyzes the performance requirements of real-time, compatibility, scalability, and security. Then, the paper describes the overall scheme of a typical hardware-in-the-loop simulation system, including the functional hierarchy, operation mechanism, and structural composition. Finally, it summarizes the contents and steps of the system integration testing, acceptance testing, and credibility evaluation method.
Emergency Material Scheduling Based On Discrete Shuffled Frog Leaping Algorithm,
2024
School of Automation, Nanjing University of Information Science & Technology, Nanjing 210044, China; Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology, Nanjing 210044, China; Jiangsu Key Laboratory of Big Data Analysis Technology, Nanjing 210044, China;
Emergency Material Scheduling Based On Discrete Shuffled Frog Leaping Algorithm, Xiaoning Shen, Zhongpei Ge, Chengbin Yao, Liyan Song, Yufang Wang
Journal of System Simulation
Abstract: A mathematical model of emergency material scheduling after earthquakes is built. The model evaluates the emergency degree of each disaster area based on the disaster situation and designs a method to split the demand of the disaster area, improving the efficiency of vehicle utilization. To solve the model, this paper proposes a discrete shuffled frog leaping algorithm with multi-resource learning. The multiple information sources introduced by the proposed algorithm can expand the search direction and reduce the assimilation speed of the population in the algorithm. Second, the worst individual in each subgroup can learn the effective information in the …
Combat Effectiveness Evaluation Method Of Homogeneous Cluster Equipment System Based On Rlomag+Eas,
2024
Department of Information and Communication, Academy of Army Armored Force, Beijing 100072, China
Combat Effectiveness Evaluation Method Of Homogeneous Cluster Equipment System Based On Rlomag+Eas, Guohui Zhang, Ang Gao, Ya'nan Zhang
Journal of System Simulation
Abstract: The equipment system is the reflection of the combat system from the perspective of equipment. The research on the combat effectiveness evaluation of the equipment system is of great practical significance for the optimization, construction, and development of the equipment system. Cluster equipment combat system confrontation is characterized by large-scale, highly dynamic and strong confrontation, and it is difficult to directly evaluate combat effectiveness with traditional methods. Aiming at the single task homogeneous cluster equipment system (such as UAV reconnaissance swarm and ground unmanned platform fire assault cluster), this paper regards the confrontation process of equipment system as the …
Optimization On Cold Chain Distribution Routes Considering Carbon Emissions Based On Improved Ant Colony Algorithm,
2024
School of Electrical and Photoelectric Engineering, West Anhui University, Luan 237012, China
Optimization On Cold Chain Distribution Routes Considering Carbon Emissions Based On Improved Ant Colony Algorithm, Huifang Bao, Jie Fang, Jinsi Zhang, Chuansheng Wang
Journal of System Simulation
Abstract: As the comprehensive distribution cost is not considered comprehensively in the current cold chain distribution route optimization, this paper builds a path optimization model to minimize the comprehensive distribution cost. The model combines with the characteristics of fresh distribution, and comprehensively considers the transportation cost, carbon emission, refrigeration, cargo damage and time window constraints during cold chain transportation. Then, an improved ant colony algorithm is designed to solve this model. At the initial stage, the genetic algorithm is adopted to generate the initial pheromone, and then the ant colony algorithm is applied to conduct the subsequent optimization search. The …
