Visual Place Recognition (VPR) aims to match query images against a database using visual cues. State-of-the-art methods aggregate features from deep backbones to form global descriptors. Optimal transport-based aggregation methods reformulate feature-to-cluster assignment as a transport problem, but the standard Sinkhorn algorithm symmetrically treats source and target marginals, limiting effectiveness when image features and cluster centers exhibit substantially different distributions. We propose an asymmetric aggregation VPR method with geometric constraints for locally aggregated descriptors, called A^2GC-VPR. Our method employs row-column normalization averaging with separate marginal calibration, enabling asymmetric matching that adapts to distributional discrepancies in visual place recognition. Geometric constraints are incorporated through learnable coordinate embeddings, computing compatibility scores fused with feature similarities, thereby promoting spatially proximal features to the same cluster and enhancing spatial awareness. Experimental results on MSLS, NordLand, and Pittsburgh datasets demonstrate superior performance, validating the effectiveness of our approach in improving matching accuracy and robustness.
Room temperature phosphorescence (RTP) materials, featuring large Stokes shifts, high exciton utilization, long lifetime, and multicolor emission, have consequently attracted widespread attention across various fields. Carbon dots (CDs) have rapidly emerged as a burgeoning research hotspot in materials science, owing to their ease of synthesis, low toxicity, excellent biocompatibility, and outstanding optical properties. Recent studies have highlighted the crucial role of host–guest strategies in both enhancing and precisely modulating the RTP performance of CDs, thereby expanding their potential applications across a wide range of fields. Despite significant progress, there remains a lack of comprehensive reviews that systematically elucidate the design strategies of CDs‐based host–guest materials and their correlation with RTP property modulation. This review addresses this gap by summarizing the latest advancements in CDs‐based host–guest RTP materials, with a particular focus on fundamental design strategies and mechanisms for performance modulation. On this basis, the potential applications of these materials in information security, intelligent optical devices, bioimaging, and optical sensing are discussed. Finally, in light of the current research landscape, the opportunities and future prospects for CDs‐based host–guest RTP materials are outlined, aiming to offer new insights for the advancement of this emerging field.
Cross-modal localization using text and point clouds enables robots to localize themselves via natural language descriptions, with applications in autonomous navigation and interaction between humans and robots. In this task, objects often recur across text and point clouds, making spatial relationships the most discriminative cues for localization. Given this characteristic, we present SpatiaLoc, a framework utilizing a coarse-to-fine strategy that emphasizes spatial relationships at both the instance and global levels. In the coarse stage, we introduce a Bezier Enhanced Object Spatial Encoder (BEOSE) that models spatial relationships at the instance level using quadratic Bezier curves. Additionally, a Frequency Aware Encoder (FAE) generates spatial representations in the frequency domain at the global level. In the fine stage, an Uncertainty Aware Gaussian Fine Localizer (UGFL) regresses 2D positions by modeling predictions as Gaussian distributions with a loss function aware of uncertainty. Extensive experiments on KITTI360Pose demonstrate that SpatiaLoc significantly outperforms existing state-of-the-art (SOTA) methods.
Ice accretion induced by extreme weather conditions poses a serious threat to the safe operation of infrastructure. Although superhydrophobic coatings exhibit excellent passive anti-icing performance, they generally lack active deicing capabilities. In this study, a novel photothermal superhydrophobic coating (PM-CPPS) is developed by integrating hydrangea-like hollow carbon nanospheres (CPPS) with a water-soluble fluorine-free polysiloxane (PMATE), enabling a synergistic effect of passive anti-icing and active deicing. The hierarchical micro/nanostructure and low surface energy of the PM-CPPS coating significantly enhanced its hydrophobicity (WCA > 157 degrees), and the photothermal effect enabled complete melting of surface ice within 93 s. Experimental results showed that at -15 degrees C, the coating extended the freezing time of water droplets by approximately 20-fold. Additionally, interfacial adhesion is improved via an epoxy-amine ring-opening reaction between epoxy groups and polydopamine (PDA), allowing the coating to maintain superhydrophobicity after 200 sandpaper abrasion cycles and 160 tape-peeling tests. PM-CPPS exhibited an ultra-low initial ice adhesion strength (5.25 kPa) and a stable photothermal conversion efficiency of 83.24%. This study offers an efficient and durable coating design strategy for long-term anti-icing and deicing applications in infrastructure under extreme environmental conditions.
Sea surface temperature (SST) is a critical indicator of global climate change, yet satellite-derived SST imagery often suffers from coarse spatial resolution, limiting the ability to capture fine-scale thermal structures such as ocean fronts. To address this, we propose a Dual-Branch State-Displacement Network (DBSD-Net) for SST super-resolution. DBSD-Net adopts a dual-branch architecture: a wavelet frequency branch that explicitly separates low and high-frequency components via discrete wavelet transform for targeted processing, and a VGGUNet branch that extracts multi-scale semantic features from a frozen pre-trained VGG backbone. Within the wavelet branch, we introduce a Structural State Space Module (SSSM) with a Gated Structure Refinement (GSR) unit to efficiently capture long-range dependencies and enhance structural integrity, and a Displacement Gate Module (DGM) that learns a displacement field for geometry-aware modulation of high-frequency details, thereby mitigating spatially varying degradation. Experiments on multiple public SST datasets demonstrate that DBSD-Net outperforms existing state-of-the-art methods.
