Reconstructing controllable Gaussian splats for articulated objects from monocular video is especially challenging due to its inherently insufficient constraints. Existing methods address this by relying on dense masks and manually defined control signals, limiting their real-world applications. In this paper, we propose an annotation-free method, FreeGaussian, which mathematically disentangles camera egomotion and articulated movements via flow derivatives. By establishing a connection between 2D flows and 3D Gaussian dynamic flow, our method enables optimization and continuity of dynamic Gaussian motions from flow priors without any control signals. Furthermore, we introduce a 3D spherical vector controlling scheme, which represents the state as a 3D Gaussian trajectory, thereby eliminating the need for complex 1D control signal calculations and simplifying controllable Gaussian modeling. Extensive experiments on articulated objects demonstrate the state-of-the-art visual performance and precise, part-aware controllability of our method.

Visual grounding (VG) aims to localize target objects in an image based on natural language descriptions. In this paper, we propose AerialVG, a new task focusing on visual grounding from aerial views. Compared to traditional VG, AerialVG poses new challenges, \emph{e.g.}, appearance-based grounding is insufficient to distinguish among multiple visually similar objects, and positional relations should be emphasized. Besides, existing VG models struggle when applied to aerial imagery, where high-resolution images cause significant difficulties. To address these challenges, we introduce the first AerialVG dataset, consisting of 5K real-world aerial images, 50K manually annotated descriptions, and 103K objects. Particularly, each annotation in AerialVG dataset contains multiple target objects annotated with relative spatial relations, requiring models to perform comprehensive spatial reasoning. Furthermore, we propose an innovative model especially for the AerialVG task, where a Hierarchical Cross-Attention is devised to focus on target regions, and a Relation-Aware Grounding module is designed to infer positional relations. Experimental results validate the effectiveness of our dataset and method, highlighting the importance of spatial reasoning in aerial visual grounding. The code and dataset will be released.

Time geography is an elegant framework for analyzing human activity–travel behaviors across temporal and spatial dimensions. At the core of this framework are the concepts of space–time paths, which represent historical trajectories, and space–time prisms, which define potential future activity spaces. However, most studies examine space–time paths and prisms in isolation, overlooking the integrative nature of time geography as a theoretical framework that incorporates the past, present, and future within a continuous temporal dimension. This study addresses this gap by developing novel methods for measuring and querying the spatiotemporal proximity of these heterogeneous and heterochronous time-geographic entities. To operationalize these methods, a GIS tool was implemented to support the local density analysis of time-geographic entities. Comprehensive computational experiments were conducted to validate the developed methods using large-scale, network-constrained, and time-geographic datasets. The developed methods exhibited high computational efficiency (approximately 2 s) in computing the local density for each path within extensive prism collections. The experimental results demonstrate the effectiveness of the developed methods in analyzing and visualizing the local density of historical paths in the near future. The methods offer new insights into space–time interactions, advancing research in human mobility forecasting and spatial decision-making.

In the modern era, the optimization of energy utilization in both industrial production and everyday life represents a critical challenge. This challenge underscores the imperative for innovative technological solutions, with artificial intelligence (AI) standing at the forefront of this transformative wave. Among the myriad advancements, high-performance deep learning frameworks have notably advanced, propelling the widespread adoption of computer vision technologies. Despite these advancements, the quest for enhanced interpretability of deep learning networks remains a concern, as it holds the key to unlocking more transparent AI systems. To address this issue, our study proposed an innovative method called information activation mapping (IAM), aimed at enhancing the interpretability of deep learning classification networks through the advanced gradient-weighted class activation mapping-based approach. By refining and extending existing methods, our technique produces highly detailed highlight maps that illuminate critical areas influencing decision-making processes within the network. This breakthrough not only elevates the network’s interpretability but also serves as a cornerstone for development of more efficient and targeted datasets. Our comprehensive analysis encompassed both the qualitative and quantitative evaluation of data quality, alongside a thorough efficiency analysis of the networks and datasets involved. By doing so, we demonstrate that our proposed IAM method significantly improves the interpretability of deep learning networks, thereby promoting more accurate and effective data processing strategies. This research has profound implications for future of AI, particularly in the realms of sustainable and low-carbon AI of Things (AIoT) systems, by promoting more energy-efficient data processing and contributing to the advancement of eco-friendly technological solutions.

Agent-based models have gained traction in exploring the intricate processes governing the spread of infectious diseases, particularly due to their proficiency in capturing nonlinear interaction dynamics. The fidelity of agent-based models in replicating real-world epidemic scenarios hinges on the accurate portrayal of both population-wide and individual-level interactions. In situations where comprehensive population data are lacking, synthetic populations serve as a vital input to agent-based models, approximating real-world demographic structures. While some current population synthesizers consider the structural relationships among agents from the same household, there remains room for refinement in this domain, which could potentially introduce biases in subsequent disease transmission simulations. In response, this study unveils a novel methodology for generating synthetic populations tailored for infectious disease transmission simulations. By integrating insights from microsample-derived household structures, we employ a heuristic combinatorial optimizer to recalibrate these structures, subsequently yielding synthetic populations that faithfully represent agent structural relationships. Implementing this technique, we successfully generated a spatially-explicit synthetic population encompassing over 17 million agents for Shenzhen, China. The findings affirm the method's efficacy in delineating the inherent statistical structural relationship patterns, aligning well with demographic benchmarks at both city and subzone tiers. Moreover, when assessed against a stochastic agent-based Susceptible-Exposed-Infectious-Recovered model, our results pinpointed that variations in population synthesizers can notably alter epidemic projections, influencing both the peak incidence rate and its onset.

Covert communication in this regard has been widely used for protecting the secrecy of communication. Voice over Long Term Evolution (VoLTE) is a packet-switched core network solution for high-speed and high-quality end-to-end services which usually applied to the communication between intelligent systems. However, covert channels using inter-packet delays and packet order in VoLTE services are limited by specific rules. Since minor modifications to overt traffic can be detected, existing covert channel solutions cannot be directly applied to VoLTE. Therefore, this study presents a robust packet loss covert timing channel by cascade hash coding with intelligent system. To ensure robustness and undetectability, we design hash-based inter-codeword verification, codeword self-verification based on cyclic redundancy check, and adaptive mapping matrix. The sender modulates the covert messages according to the sequence number of the actively dropped packets, and the receiver can retrieve the covert messages using a specialized verification method. To evaluate undetectability, robustness, throughput, and construction costs, a large number of experiments in mobile intelligent terminals have been conducted. The experimental results prove that the proposed scheme is feasible for VoLTE communication, as the covert message is shown to be transmitted secretly, and the bit error and throughput are within acceptable ranges.