With potential applications in robotics and autonomous vehicles, LiDAR-based human action recognition (HAR) in outdoor long-range scenarios is challenging due to the degradation of point cloud density with distance and the simultaneous motion of humans and sensors. To address these issues, we propose the Pose-Enhanced Point Cloud Network (PePNet), a distance-aware framework for long-range HAR. As the core component, the Pose-Enhanced Point Cloud Block (PeP Block) integrates three modules: a Dynamic Enhancement Module that mitigates point cloud sparsity at long distances by generating supplementary points from motion cues, a Pose Prompter Module that introduces pose priors, and an Adaptive Point Selection Module that suppresses irrelevant body-part movements. We further design a Spatiotemporal Tube Embedding (ST-Tube), combined with the Mamba state space model, to capture long-range dependencies and complex motion dynamics. In addition, we construct Momo, a large-scale LiDAR-based HAR dataset that focuses on long-range (2-30 m) outdoor scenarios where sparse point clouds and simultaneous human-sensor motion pose prominent challenges, complementing existing benchmarks by providing a dedicated evaluation platform for long-range outdoor HAR. Experimental results show that PePNet achieves consistent performance gains over existing methods on Momo. Moreover, the proposed PeP Block can serve as a plug-and-play module to enhance other point cloud action recognition frameworks in long-range outdoor settings. The code is available at https://github.com/Shark0-0/PePNet.

Spiking Neural Networks (SNNs) offer a biologically plausible and energy-efficient framework for temporal information processing. However, existing studies overlook a fundamental property widely observed in biological neurons—synaptic heterogeneity, which plays a crucial role in temporal processing and cognitive capabilities. To bridge this gap, we introduce HetSyn, a generalized framework that models synaptic heterogeneity with synapse-specific time constants. This design shifts temporal integration from the membrane potential to the synaptic current, enabling versatile timescale integration and allowing the model to capture diverse synaptic dynamics. We implement HetSyn as HetSynLIF, an extended form of the leaky integrate-and-fire (LIF) model equipped with synapse-specific decay dynamics. By adjusting the parameter configuration, HetSynLIF can be specialized into vanilla LIF neurons, neurons with threshold adaptation, and neuron-level heterogeneous models. We demonstrate that HetSynLIF not only improves the performance of SNNs across a variety of tasks—including pattern generation, delayed match-to-sample, speech recognition, and visual recognition—but also exhibits strong robustness to noise, enhanced working memory performance, efficiency under limited neuron resources, and generalization across timescales. In addition, analysis of the learned synaptic time constants reveals trends consistent with empirical observations in biological synapses. These findings underscore the significance of synaptic heterogeneity in enabling efficient neural computation, offering new insights into brain-inspired temporal modeling. Code available at: https://github.com/dzcgood/HetSyn.

Understanding the real world through point cloud video is a crucial aspect of robotics and autonomous driving systems. However, prevailing methods for 4D point cloud recognition have limitations due to sensor resolution, which leads to a lack of detailed information. Recent advances have shown that Vision-Language Models (VLM) pre-trained on web-scale text-image datasets can learn fine-grained visual concepts that can be transferred to various downstream tasks. However, effectively integrating VLM into the domain of 4D point clouds remains an unresolved problem. In this work, we propose the Vision-Language Models Goes 4D (VG4D) framework to transfer VLM knowledge from visual-text pretrained models to a 4D point cloud network. Our approach involves aligning the 4D encoder’s representation with a VLM learning a shared visual and text space from training on large-scale image-text pairs. By transferring the knowledge of the VLM to the 4D encoder and combining the VLM, our VG4D achieves improved recognition performance. To enhance the 4D encoder, we modernize the classic dynamic point cloud backbone and propose an improved version of PSTNet, im-PSTNet, which can efficiently model point cloud videos. Experiments demonstrate that our method achieves state-of-the-art performance for action recognition on both NTU RGB+D 60 dataset and NTU RGB+D 120 dataset.

Interferometric Synthetic Aperture Radar (InSAR) has become a widely used and efficient tool for monitoring large-scale, long-term land subsidence. Most applications, especially those related to risky assessment, utilize only the mean deformation rate derived through a linear fit of the InSAR-derived time series deformations without considering the full-time sequence. In this way, the embedded information, such as the onset, duration, and patterns of abnormal deformations, is ignored. This information, however, should not be compromised as it is critical for assessing the risky deformations and recognizing the causal factors. Due to the large data volume, processing the full-time-series information derived by InSAR analysis can be a challenge. In this study, we propose to use the Time-series Anomaly Detection Generative Adversarial Network (TadGAN) to deal with the time series InSAR deformation and recognize the onset and duration of abnormal epochs. The proposed method has been tested with InSAR-derived results over the Hong Kong airport region. It performs better than conventional risk assessment methods, such as the one based on Mean Absolute Deviation (MAD) outlier detection.

Interferometric Synthetic Aperture Radar (InSAR) has been recognized as an effective remote sensing tool for Earth Observation (EO) thanks to its capacity to penetrate clouds and forests. In the field of InSAR deformation monitoring, coherence is used as an indicator for the stability of the interferometric phase. Actually, interferometric coherence itself contains valuable information about land surface and can be used to classify land cover types. Currently, there are few studies about the possibility of retrieving forest canopy height from interferometric coherence, especially its multitemporal variation. In this study, we emphasize the relationship between multi-temporal InSAR coherence and forest canopy height by investigating the InSAR coherence variation of multi-temporal Sentinel-1 data regarding the tree height measured by the NASA Global Ecosystem Dynamics Investigation (GEDI). Results show that forest canopy height can be estimated by using the Random Forest (RF) regression model trained by samples of GEDI height and InSAR coherence variation. InSAR coherence performs better in estimating the forest canopy height than using other remote sensing data, such as multispectral reflectance from Sentinel2 and SAR backscatter intensity.

Beauty and Personal care product retrieval has attracted more and more attention due to its wide application value. However, due to the diversity of data and the complexity of image background, this task is very challenging. In this paper, we propose a multi-feature fusion method based on salient object detection to improve retrieval performance. The key of our method is to extract the foreground objects of the query set by using the salient object detection network, so as to eliminate the background interference. Then the foreground target images and dataset are put into the multi-classification networks to extract multiple fusion features for retrieval. We use the perfect-500k dataset for experiments, and the results show that our method is effective. Our method ranked 2st in the Grand Challenge of AI Meets Beauty in ACM Multimedia 2020 with a MAP score of 0.43729. We released our code on GitHub:github.com/R-M-Yan/ACMMM2020AIMeetBeauty.

Creating a Robust Design requires that the operating conditions of each component of the design are carefully measured and compared with its Safe Operating, a task commonly referred to as stress analysis. In this paper we analyze the relationship between the component stress and the Safe Operating Area. We summarize the requirements of describing the Safe Operating Areas and propose how these requirements can be used to model the concept with two hardware description languages: MAST® and VHDL-AMS. A circuit example is given.