Zhenghao Zhang

Zuozhuo Dai, Zhenghao Zhang, Yao Yao et al.

Image animation is a key task in computer vision which aims to generate dynamic visual content from static image. Recent image animation methods employ neural based rendering technique to generate realistic animations. Despite these advancements, achieving fine-grained and controllable image animation guided by text remains challenging, particularly for open-domain images captured in diverse real environments. In this paper, we introduce an open domain image animation method that leverages the motion prior of video diffusion model. Our approach introduces targeted motion area guidance and motion strength guidance, enabling precise control the movable area and its motion speed. This results in enhanced alignment between the animated visual elements and the prompting text, thereby facilitating a fine-grained and interactive animation generation process for intricate motion sequences. We validate the effectiveness of our method through rigorous experiments on an open-domain dataset, with the results showcasing its superior performance. Project page can be found at https://animationai.github.io/AnimateAnything.

Hang Wu, Zhenghao Zhang, Siyuan Lin et al.

Robust localization is the cornerstone of autonomous driving, especially in challenging urban environments where GPS signals suffer from multipath errors. Traditional localization approaches rely on high-definition (HD) maps, which consist of precisely annotated landmarks. However, building HD map is expensive and challenging to scale up. Given these limitations, leveraging navigation maps has emerged as a promising low-cost alternative for localization. Current approaches based on navigation maps can achieve highly accurate localization, but their complex matching strategies lead to unacceptable inference latency that fails to meet the real-time demands. To address these limitations, we propose a novel transformer-based neural re-localization method. Inspired by image registration, our approach performs a coarse-to-fine neural feature registration between navigation map and visual bird's-eye view features. Our method significantly outperforms the current state-of-the-art OrienterNet on both the nuScenes and Argoverse datasets, which is nearly 10%/20% localization accuracy and 30/16 FPS improvement on single-view and surround-view input settings, separately. We highlight that our research presents an HD-map-free localization method for autonomous driving, offering cost-effective, reliable, and scalable performance in challenging driving environments.

Zhenghao Zhang, Jun Xie, Xingchen Chen et al.

The prevalence of real-world multi-view data makes incomplete multi-view clustering (IMVC) a crucial research. The rapid development of Graph Neural Networks (GNNs) has established them as one of the mainstream approaches for multi-view clustering. Despite significant progress in GNNs-based IMVC, some challenges remain: (1) Most methods rely on the K-Nearest Neighbors (KNN) algorithm to construct static graphs from raw data, which introduces noise and diminishes the robustness of the graph topology. (2) Existing methods typically utilize the Mean Squared Error (MSE) loss between the reconstructed graph and the sparse adjacency graph directly as the graph reconstruction loss, leading to substantial gradient noise during optimization. To address these issues, we propose a novel \textbf{D}ynamic Deep \textbf{G}raph Learning for \textbf{I}ncomplete \textbf{M}ulti-\textbf{V}iew \textbf{C}lustering with \textbf{M}asked Graph Reconstruction Loss (DGIMVCM). Firstly, we construct a missing-robust global graph from the raw data. A graph convolutional embedding layer is then designed to extract primary features and refined dynamic view-specific graph structures, leveraging the global graph for imputation of missing views. This process is complemented by graph structure contrastive learning, which identifies consistency among view-specific graph structures. Secondly, a graph self-attention encoder is introduced to extract high-level representations based on the imputed primary features and view-specific graphs, and is optimized with a masked graph reconstruction loss to mitigate gradient noise during optimization. Finally, a clustering module is constructed and optimized through a pseudo-label self-supervised training mechanism. Extensive experiments on multiple datasets validate the effectiveness and superiority of DGIMVCM.

Zhenghao Zhang, Matthew Trinkle, Aleksandar D. Dimitrovski et al.

A novel time synchronization attack (TSA) on wide area monitoring systems in smart grid has been identified in the first part of this paper. A cross layer detection mechanism is proposed to combat TSA in part II of this paper. In the physical layer, we propose a GPS carrier signal noise ratio (C/No) based spoofing detection technique. In addition, a patch-monopole hybrid antenna is applied to receive GPS signal. By computing the standard deviation of the C/No difference from two GPS receivers, a priori probability of spoofing detection is fed to the upper layer, where power system state is estimated and controlled. A trustworthiness based evaluation method is applied to identify the PMU being under TSA. Both the physical layer and upper layer algorithms are integrated to detect the TSA, thus forming a cross layer mechanism. Experiment is carried out to verify the effectiveness of the proposed TSA detection algorithm.

Zhenghao Zhang, Shuping Gong, Aleksandar D. Dimitrovski et al.

Many operations in power grids, such as fault detection and event location estimation, depend on precise timing information. In this paper, a novel Time Synchronization Attack (TSA) is proposed to attack the timing information in smart grid. Since many applications in smart grid utilize synchronous measurements and most of the measurement devices are equipped with global positioning system (GPS) for precise timing, it is highly probable to attack the measurement system by spoofing the GPS. The effectiveness of TSA is demonstrated for three applications of phasor measurement unit (PMU) in smart grid, namely transmission line fault detection, voltage stability monitoring and event locationing. The validity of TSA is demonstrated by numerical simulations.

Shuping Gong, Zhenghao Zhang, Husheng Li et al.

Many operations in power grids, such as fault detection and event location estimation, depend on precise timing information. In this paper, a novel time stamp attack (TSA) is proposed to attack the timing information in smart grid. Since many applications in smart grid utilize synchronous measurements and most of the measurement devices are equipped with global positioning system (GPS) for precise timing, it is highly probable to attack the measurement system by spoofing the GPS. The effectiveness of TSA is demonstrated for three applications of phasor measurement unit (PMU) in smart grid, namely transmission line fault detection, voltage stability monitoring and event locationing.