Li Wang

Rui Fan, Sicen Guo, Li Wang et al.

Road damage is an inconvenience and a safety hazard, severely affecting vehicle condition, driving comfort, and traffic safety. The traditional manual visual road inspection process is pricey, dangerous, exhausting, and cumbersome. Also, manual road inspection results are qualitative and subjective, as they depend entirely on the inspector's personal experience. Therefore, there is an ever-increasing need for automated road inspection systems. This chapter first compares the five most common road damage types. Then, 2-D/3-D road imaging systems are discussed. Finally, state-of-the-art machine vision and intelligence-based road damage detection algorithms are introduced.

Li Wang, Wei Huang

Variational Auto-Encoders (VAEs) have emerged as powerful probabilistic models for generative tasks. However, their convergence properties have not been rigorously proven. The challenge of proving convergence is inherently difficult due to the highly non-convex nature of the training objective and the implementation of a Stochastic Neural Network (SNN) within VAE architectures. This paper addresses these challenges by characterizing the optimization trajectory of SNNs utilized in VAEs through the lens of Neural Tangent Kernel (NTK) techniques. These techniques govern the optimization and generalization behaviors of ultra-wide neural networks. We provide a mathematical proof of VAE convergence under mild assumptions, thus advancing the theoretical understanding of VAE optimization dynamics. Furthermore, we establish a novel connection between the optimization problem faced by over-parameterized SNNs and the Kernel Ridge Regression (KRR) problem. Our findings not only contribute to the theoretical foundation of VAEs but also open new avenues for investigating the optimization of generative models using advanced kernel methods. Our theoretical claims are verified by experimental simulations.

Yifeng Gao, Yifan Ding, Hongyu Su et al.

As AI-generated video becomes increasingly pervasive across media platforms, the ability to reliably distinguish synthetic content from authentic footage has become both urgent and essential. Existing approaches have primarily treated this challenge as a binary classification task, offering limited insight into where or why a model identifies a video as AI-generated. However, the core challenge extends beyond simply detecting subtle artifacts; it requires providing fine-grained, persuasive evidence that can convince auditors and end-users alike. To address this critical gap, we introduce DAVID-X, the first dataset to pair AI-generated videos with detailed defect-level, temporal-spatial annotations and written rationales. Leveraging these rich annotations, we present DAVID-XR1, a video-language model designed to deliver an interpretable chain of visual reasoning-including defect categorization, temporal-spatial localization, and natural language explanations. This approach fundamentally transforms AI-generated video detection from an opaque black-box decision into a transparent and verifiable diagnostic process. We demonstrate that a general-purpose backbone, fine-tuned on our compact dataset and enhanced with chain-of-thought distillation, achieves strong generalization across a variety of generators and generation modes. Our results highlight the promise of explainable detection methods for trustworthy identification of AI-generated video content.

Amith K. Belman, Li Wang, S. S. Iyengar et al.

Behavioral biometrics are key components in the landscape of research in continuous and active user authentication. However, there is a lack of large datasets with multiple activities, such as typing, gait and swipe performed by the same person. Furthermore, large datasets with multiple activities performed on multiple devices by the same person are non-existent. The difficulties of procuring devices, participants, designing protocol, secure storage and on-field hindrances may have contributed to this scarcity. The availability of such a dataset is crucial to forward the research in behavioral biometrics as usage of multiple devices by a person is common nowadays. Through this paper, we share our dataset, the details of its collection, features for each modality and our findings of how keystroke features vary across devices. We have collected data from 117 subjects for typing (both fixed and free text), gait (walking, upstairs and downstairs) and touch on Desktop, Tablet and Phone. The dataset consists a total of about: 3.5 million keystroke events; 57.1 million data-points for accelerometer and gyroscope each; 1.7 million data-points for swipes; and enables future research to explore previously unexplored directions in inter-device and inter-modality biometrics. Our analysis on keystrokes reveals that in most cases, keyhold times are smaller but inter-key latencies are larger, on hand-held devices when compared to desktop. We also present; detailed comparison with related datasets; possible research directions with the dataset; and lessons learnt from the data collection.

Rui Fan, Mohammud Junaid Bocus, Yilong Zhu et al.

Crack is one of the most common road distresses which may pose road safety hazards. Generally, crack detection is performed by either certified inspectors or structural engineers. This task is, however, time-consuming, subjective and labor-intensive. In this paper, we propose a novel road crack detection algorithm based on deep learning and adaptive image segmentation. Firstly, a deep convolutional neural network is trained to determine whether an image contains cracks or not. The images containing cracks are then smoothed using bilateral filtering, which greatly minimizes the number of noisy pixels. Finally, we utilize an adaptive thresholding method to extract the cracks from road surface. The experimental results illustrate that our network can classify images with an accuracy of 99.92%, and the cracks can be successfully extracted from the images using our proposed thresholding algorithm.

Hongyao Tang, Li Wang, Zan Wang et al.

Multiagent coordination in cooperative multiagent systems (MASs) has been widely studied in both fixed-agent repeated interaction setting and the static social learning framework. However, two aspects of dynamics in real-world multiagent scenarios are currently missing in existing works. First, the network topologies can be dynamic where agents may change their connections through rewiring during the course of interactions. Second, the game matrix between each pair of agents may not be static and usually not known as a prior. Both the network dynamic and game uncertainty increase the coordination difficulty among agents. In this paper, we consider a multiagent dynamic social learning environment in which each agent can choose to rewire potential partners and interact with randomly chosen neighbors in each round. We propose an optimal rewiring strategy for agents to select most beneficial peers to interact with for the purpose of maximizing the accumulated payoff in repeated interactions. We empirically demonstrate the effectiveness and robustness of our approach through comparing with benchmark strategies. The performance of three representative learning strategies under our social learning framework with our optimal rewiring is investigated as well.

Benjamin Allain, Li Wang, Jean-Sebastien Franco et al.

We present a novel volumetric animation generation framework to create new types of animations from raw 3D surface or point cloud sequence of captured real performances. The framework considers as input time incoherent 3D observations of a moving shape, and is thus particularly suitable for the output of performance capture platforms. In our system, a suitable virtual representation of the actor is built from real captures that allows seamless combination and simulation with virtual external forces and objects, in which the original captured actor can be reshaped, disassembled or reassembled from user-specified virtual physics. Instead of using the dominant surface-based geometric representation of the capture, which is less suitable for volumetric effects, our pipeline exploits Centroidal Voronoi tessellation decompositions as unified volumetric representation of the real captured actor, which we show can be used seamlessly as a building block for all processing stages, from capture and tracking to virtual physic simulation. The representation makes no human specific assumption and can be used to capture and re-simulate the actor with props or other moving scenery elements. We demonstrate the potential of this pipeline for virtual reanimation of a real captured event with various unprecedented volumetric visual effects, such as volumetric distortion, erosion, morphing, gravity pull, or collisions.