Given the scarcity of real data and the time-intensive nature of labeling, current multi-agent perception models often rely on simulated sensor data for training and validation. However, perception performance deteriorates significantly due to domain gap between simulated and real data. Existing adaptation methods focus on domain-generalized feature extraction while neglecting multi-agent shift uncertainty and relational semantic loss. To address this issue, we propose a Selective Shift Domain Adaptation method in multi-agent collaborative perception, called SSDA. SSDA incorporates two essential components: the frequency-decoupled feature shift adjustment (FSA) and the entropy-driven staged adaptive alignment (SAA). To mitigate the relational semantic loss, the FSA is proposed to simplify the representation of correlation features and remove redundant information from the source domain, thereby mitigating interference for domain adversarial scenarios. To tackle the shift uncertainty, the SAA is designed to achieve adaptive alignment from global to local guided by information entropy, which dynamically adjusts weights for samples according to their level of uncertainty. The results demonstrate that the SSDA is significantly superior to the SOTA, achieving up to 7.35% improvements on [email protected].

The development of intelligent robots seeks to seamlessly integrate them into the human world, providing assistance and companionship in daily life and work, with the ultimate goal of achieving human-robot symbiosis. This requires robots with intelligent interaction abilities to work naturally and effectively with humans. However, current robotic simulators fail to support real human participation, limiting their ability to provide authentic interaction experiences and gather valuable human feedback essential for enhancing robotic capabilities. In this paper, we introduce SymBridge, the first human-in-the-loop cyber-physical interactive system designed to enable the safe and efficient development, evaluation, and optimization of human-robot interaction methods. Specifically, we employ augmented reality technology to enable real humans to interact with virtual robots in physical environments, creating an authentic interactive experience. Building on this, we propose a novel robotic interaction model that generates responsive, precise robot actions in real time through continuous human behavior observation. The model incorporates multi-resolution human motion features and environmental affordances, ensuring contextually adaptive robotic responses. Additionally, SymBridge enables continuous robot learning by collecting human feedback and dynamically adapting the robotic interaction model. By leveraging a designed system architecture and modules, SymBridge builds a bridge between humans and robots, as well as between cyber and physical spaces, providing a natural and realistic interaction experience while facilitating the continuous evolution of robotic intelligence. Extensive experiments, user studies, and robot testing demonstrate the system’s promising performance and highlight its potential to significantly advance research on human-robot symbiosis.

With advancements in artificial intelligence, the field of power inspection faces challenges in utilizing upgraded AI technologies to improve operational efficiency. As part of the smart grid initiative, each power pole must be accurately modeled. However, manual classification of strain poles and tangent poles remains hindered by three primary limitations: low accuracy, high costs, and poor timeliness. To address these issues, this paper introduces the following contributions: (1) A computer vision model, TNet, is proposed to distinguish strain poles from tangent poles, leveraging a stable T module and ResNet to extract fine-grained features from images. This approach utilizes high-speed computing to enhance timeliness and mitigates high costs by reducing manual labor, with electricity being the only primary operational cost. (2) We introduce a newly collected power pole classification dataset, featuring images of pole heads from 6 and 10[Formula: see text]kV power lines in a specific city. This dataset includes 695 images of tangent poles and 329 images of strain poles, with a total size of 3.52[Formula: see text]GB. Finally, the model can achieve an accuracy of 93.76% and an F1-score of 0.91 on the MyGT2.0 dataset. Our work has been practically applied to the circuit maintenance work of a certain power supply company in 2024.

Human-centric Point Cloud Video Understanding (PVU) is an emerging field focused on extracting and interpreting human-related features from sequences of human point clouds, further advancing downstream human-centric tasks and applications. Previous works usually focus on tack-ling one specific task and rely on huge labeled data, which has poor generalization capability. Considering that hu-man has specific characteristics, including the structural semantics of human body and the dynamics of human motions, we propose a unified framework to make full use of the prior knowledge and explore the inherent features in the data itself for generalized human-centric point cloud video understanding. Extensive experiments demonstrate that our method achieves state-of-the-art performance on various human-related tasks, including action recognition and 3D pose estimation. All datasets and code will be re-leased soon.

Depth estimation is usually ill-posed and ambiguous for monocular camera-based 3D multi-person pose estimation. Since LiDAR can capture accurate depth information in long-range scenes, it can benefit both the global localization of individuals and the 3D pose estimation by providing rich geometry features. Motivated by this, we propose a monocular camera and single LiDAR-based method for 3D multi-person pose estimation in large-scale scenes, which is easy to deploy and insensitive to light. Specifically, we design an effective fusion strategy to take advantage of multi-modal input data, including images and point cloud, and make full use of temporal information to guide the network to learn natural and coherent human motions. Without relying on any 3D pose annotations, our method exploits the inherent geometry constraints of point cloud for self-supervision and utilizes 2D keypoints on images for weak supervision. Extensive experiments on public datasets and our newly collected dataset demonstrate the superiority and generalization capability of our proposed method. Project homepage is at \url{https://github.com/4DVLab/FusionPose.git}.

Human-centric scene understanding is significant for real-world applications, but it is extremely challenging due to the existence of diverse human poses and actions, complex human-environment interactions, severe occlusions in crowds, etc. In this paper, we present a large-scale multi-modal dataset for human-centric scene under-standing, dubbed HuCenLife, which is collected in diverse daily-life scenarios with rich and fine-grained annotations. Our HuCenLife can benefit many 3D perception tasks, such as segmentation, detection, action recognition, etc., and we also provide benchmarks for these tasks to facilitate related research. In addition, we design novel modules for LiDAR-based segmentation and action recognition, which are more applicable for large-scale human-centric scenarios and achieve state-of-the-art performance. The dataset and code can be found at https://github.com/4DVLab/HuCenLife.git.