检索结果-内蒙古大学图书馆

MI-CAPTCHA: Enhance the Security of CAPTCHA Using Mooney Images 39

学校读者我要写书评

暂无评论

MI-CAPTCHA: Enhance the Security of CAPTCHA Using Mooney Ima...

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Li, Jingmeng Fu, Lukang Yang, Surun Wei, Hui Laboratory of Algorithms for Cognitive Models Fudan University Shanghai China

ISBN: (纸本)157735897X

Completely automated public Turing test to tell humans apart (CAPTCHA) is an effective mechanism to protect websites and online applications from malicious bots programs. Image-based CAPTCHA is one of the most widely used schemes. However, deep learning techniques have significantly weakened the security of some image-based CAPTCHA schemes. Mooney images (MIs) are important research materials in the field of cognitive science. Compared to natural images, MI exhibits fewer visual cues, fragmented content, and greater ambiguity, leading to the perception of MI relying more on the iterative process between feedforward and feedback mechanisms. In this paper, we raise an intriguing problem: can MIs be used to enhance the security of CAPTCHA? Before this study, we first propose a novel framework HiMI that generates the high-quality MIs from natural images and also allows flexible adjustment of the perceived difficulty. Based on MI, we design two MI-CAPTCHA schemes related to object detection and instance segmentation tasks, respectively. We experimentally demonstrate that HiMI performs better than other baseline methods in terms of both image quality and application potential in two MI-CAPTCHA schemes. Additionally, we conduct experiments to explore the solving performance of humans and CAPTCHA solvers under different parameter settings of schemes, providing valuable reference for the practical application. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Deep learning

Why Does the Cortex Have Such a Vast Storage Capacity?

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wei, Hui Yang, Surun Li, Yangwang Laboratory of Algorithms for Cognitive Models Fudan University Shanghai200433 China

The capacity of long-term memory seems to be extremely large, capable of storing information spanning almost a lifetime. Why does it have such a vast capacity? Why are some memories so enduring? What is the actual physical form of long-term memory? In the movie Inside Out, it is depicted as individual orbs containing information. Is that really the case? Simply explaining this by saying that the cortex has many neurons, numerous neural connections, and complex electrochemical activity between them is not sufficient to answer these fundamental questions. We need to uncover the theory hidden behind these *** essence, a neural network is equivalent to a very large directed graph, with a massive number of nodes and directed connections. This paper posits that the physical form of long-term memory is a connected subgraph within this complex directed graph. This subgraph is capable of linking together the disparate fragments of the same event, spread across different sensory cortices, to form associations. This provides a physical realization of the engram theory. The robustness of the connected subgraph and the resources it consumes can explain various memory *** on anatomical, brain imaging and electrophysiological evidence, this paper constructs a probabilistic connectivity model and uses theorems from graph theory to prove the ease of constructing connected subgraphs. Finally, it explains why the potential capacity for memory is immense. © 2024, CC BY-NC-ND.

关键词： Directed graphs

Stereo Matching Algorithm for Improved Acquisition of Disparity Of Tiny Objects 14

学校读者我要写书评

暂无评论

Stereo Matching Algorithm for Improved Acquisition of Dispar...

14th International Conference on Information Technology in Medicine and Education, ITME 2024

作者： Meng, Lingjiang Wei, Hui Wang, Haoming Zhang, Qing Li, Guangrong Nanning Vocational and Technical University School of Artifical Intellgence Nanning530000 China Shanghai Key Laboratory of Data Science Fudan University Laboratory of Algorithms for Cognitive Models Shanghai200000 China Harbin Institute of Technology School of Mechatronics Engineering Harbin150000 China

ISBN: (纸本)9798350356670

Deep-learning algorithms have an excellent nonlinear fitting ability. However, tiny objects in images do not approach the general properties of the fit, which causes the algorithms to have problems acquiring disparity for tiny objects. In addition, the results suffer from problems such as disparity inflation and warping variation. To address the shortcomings of deep learning algorithms, we propose an improved deep learning algorithm based on traditional algorithms. First, the algorithm divides the image into segments based on edges. Second, the edge error disparity and disparity expansion is corrected. Third, it finds the wrong disparity in a small segment, and removes it. The adjacent pixels with disparity removed are grouped into clusters. The matching relationship is established by combining the cluster's gray, gradient, and feature-point information into matching elements. Finally, removal of disparity warping variation and post-processing is performed. The algorithm can effectively correct error disparity, detect the disparity of tiny objects, and can be applied to practical scenarios where tiny objects are detected. © 2024 IEEE.

关键词： Adversarial machine learning

Important Clues that Facilitate Visual Emergence: Three Psychological Experiments

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Li, Jingmeng Wei, Hui Laboratory of Algorithms for Cognitive Models School of Computer Science Fudan University Shanghai China

Visual emergence is the phenomenon in which the visual system obtains a holistic perception after grouping and reorganizing local signals. The picture Dalmatian dog is known for its use in explaining visual emergence. This type of image, which consists of a set of discrete black speckles (speckles), is called an emerging image. Not everyone can find the dog in Dalmatian dog, and among those who can, the time spent varies greatly. Although Gestalt theory summarizes perceptual organization into several principles, it remains ambiguous how these principles affect the perception of emerging images. This study, therefore, designed three psychological experiments to explore the factors that influence the perception of emerging images. In the first, we found that the density of speckles in the local area and the arrangements of some key speckles played a key role in the perception of an emerging case. We set parameters in the algorithm to characterize these two factors. We then automatically generated diversified emerging-test images (ETIs) through the algorithm and verified their effectiveness in two subsequent experiments. © 2023, CC BY-NC-ND.

关键词： Speckle

On Support Relations Inference and Scene Hierarchy Graph Construction from Point Cloud in Clustered Environments

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Ma, Gang Wei, Hui The Laboratory of Algorithms for Cognitive Models Shanghai Key Laboratory of Data Science School of Computer Science Fudan University Shanghai200433 China

Over the years, scene understanding has attracted a growing interest in computer vision, providing the semantic and physical scene information necessary for robots to complete some particular tasks autonomously. In 3D scenes, rich spatial geometric and topological information are often ignored by RGB-based approaches for scene understanding. In this study, we develop a bottom-up approach for scene understanding that infers support relations between objects from a point cloud. Our approach utilizes the spatial topology information of the plane pairs in the scene, consisting of three major steps. 1) Detection of pairwise spatial configuration: dividing primitive pairs into local support connection and local inner connection;2) primitive classification: a combinatorial optimization method applied to classify primitives;and 3) support relations inference and hierarchy graph construction: bottom-up support relations inference and scene hierarchy graph construction containing primitive level and object level. Through experiments, we demonstrate that the algorithm achieves excellent performance in primitive classification and support relations inference. Additionally, we show that the scene hierarchy graph contains rich geometric and topological information of objects, and it possesses great scalability for scene understanding. Copyright © 2024, The Authors. All rights reserved.

关键词： Combinatorial optimization

Modeling of Memory Mechanisms in Cerebral Cortex and Simulation of Storage Performance

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Wei, Hui Feng, Chenyue Zhang, Jianning Laboratory of Algorithms for Cognitive Models School of Computer Science Fudan University No.2005 Songhu Road Shanghai200438 China

At the intersection of computation and cognitive science, graph theory is utilized as a formalized description of complex relationships and structures. Traditional graph models are often static, lacking dynamic and autonomous behavioral patterns. They rely on algorithms with a global view, significantly differing from biological neural networks, in which, to simulate information storage and retrieval processes, the limitations of centralized algorithms must be overcome. This study introduces a directed graph model that equips each node with adaptive learning and decision-making capabilities, thereby facilitating decentralized dynamic information storage and modeling and simulation of the brain’s memory process. We abstract different storage instances as directed graph paths, transforming the storage of information into the assignment, discrimination, and extraction of different paths. To address writing and reading challenges, each node has a personalized adaptive learning ability. A storage algorithm without a "God’s eye" view is developed, where each node uses its limited neighborhood information to facilitate the extension, formation, solidification, and awakening of directed graph paths, achieving competitive, reciprocal, and sustainable utilization of limited resources. Storage behavior occurs in each node, with adaptive learning behaviors of nodes concretized in a microcircuit centered around a variable resistor, simulating the electrophysiological behavior of neurons. Based on Ohm’s and Kirchhoff’s laws, we simulated the dynamics of this directed graph network on a computer, where the network could store and retrieve uploaded instances, confirming the model’s effectiveness and exploring its storage capacity. Under the constraints of neurobiology on the anatomy and electrophysiology of biological neural networks, this model offers a plausible explanation for the mechanism of memory realization, providing a comprehensive, system-level experimental validation of

关键词： Directed graphs

Integrating One-Shot View Planning with a Single Next-Best View via Long-Tail Multiview Sampling

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Pan, Sicong Hu, Hao Wei, Hui Dengler, Nils Zaenker, Tobias Dawood, Murad Bennewitz, Maren The Laboratory of Algorithms for Cognitive Models School of Computer Science Fudan University China The Humanoid Robots Lab University of Bonn Germany

Existing view planning systems either adopt an iterative paradigm using next-best views (NBV) or a one-shot pipeline relying on the set-covering view-planning (SCVP) network. However, neither of these methods can concurrently guarantee both high-quality and high-efficiency reconstruction of 3D unknown objects. To tackle this challenge, we introduce a crucial hypothesis: with the availability of more information about the unknown object, the prediction quality of the SCVP network improves. There are two ways to provide extra information: (1) leveraging perception data obtained from NBVs, and (2) training on an expanded dataset of multiview inputs. In this work, we introduce a novel combined pipeline that incorporates a single NBV before activating the proposed multiview-activated (MA-)SCVP network. The MA-SCVP is trained on a multiview dataset generated by our long-tail sampling method, which addresses the issue of unbalanced multiview inputs and enhances the network performance. Extensive simulated experiments substantiate that our system demonstrates a significant surface coverage increase and a substantial 45% reduction in movement cost compared to state-of-the-art systems. Real-world experiments justify the capability of our system for generalization and deployment. Copyright © 2023, The Authors. All rights reserved.

关键词： Pipelines

Modeling of Memory Mechanisms in Cerebral Cortex and Simulation of Storage Performance

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wei, Hui Feng, Chenyue Zhang, Jianning Laboratory of Algorithms for Cognitive Models School of Computer Science Fudan University No.2005 Songhu Road Shanghai200438 China

关键词： Directed graphs

Stereo Matching Algorithm for Improved Acquisition of Disparity Of Tiny Objects

学校读者我要写书评

暂无评论

Stereo Matching Algorithm for Improved Acquisition of Dispar...

IEEE International Symposium on Information (IT) in Medicine and Education, ITME

作者： Lingjiang Meng Hui Wei Haoming Wang Qing Zhang Guangrong Li School of Artifical Intellgence Nanning Vocational and Technical University Nanning China Laboratory of Algorithms for Cognitive Models Shanghai Key Laboratory of Data Science Fudan University Shanghai China School of Mechatronics Engineering Harbin Institute of Technology Harbin China

ISBN: (数字)9798350356670

ISBN: (纸本)9798350356687

Deep-learning algorithms have an excellent nonlinear fitting ability. However, tiny objects in images do not approach the general properties of the fit, which causes the algorithms to have problems acquiring disparity for tiny objects. In addition, the results suffer from problems such as disparity inflation and warping variation. To address the shortcomings of deep learning algorithms, we propose an improved deep learning algorithm based on traditional algorithms. First, the algorithm divides the image into segments based on edges. Second, the edge error disparity and disparity expansion is corrected. Third, it finds the wrong disparity in a small segment, and removes it. The adjacent pixels with disparity removed are grouped into clusters. The matching relationship is established by combining the cluster’s gray, gradient, and feature-point information into matching elements. Finally, removal of disparity warping variation and post-processing is performed. The algorithm can effectively correct error disparity, detect the disparity of tiny objects, and can be applied to practical scenarios where tiny objects are detected.

关键词： Deep learning Image segmentation Image edge detection Nonlinear distortion Fitting Clustering algorithms Object detection Industrial robots Object recognition Information technology