Cross-view geo-localization (CVGL) establishes correspondences between ground-level and satellite images of the same geographic location, serving as a fundamental technology for smart city applications, including autonomous navigation, urban planning, and location-based services. Current CVGL approaches fall into two categories: feature-based methods achieve superior performance through 2D representation learning but lack interpretability. Spatial-based methods provide geometric understanding and interpretable matching but suffer from limited spatial modeling and weak cross-view alignment, leading to lower performance. We reformulate CVGL from a spatial perspective and propose an auxiliary task-enhanced network. The network captures spatial semantics and provides explicit alignment processes with visualizable results. We introduce an auxiliary spatial semantic alignment (SSA) task that learns spatial structure via vision foundation models (VFM) and BEV transformation to enhance the primary CVGL task. The primary task captures visual semantics, including texture and appearance. Within this unified framework with shared encoders, the primary task enriches the learned embeddings by fusing spatial structure with visual semantics, yielding spatially complete representations. Extensive experiments on three standard CVGL benchmarks demonstrate that our method significantly surpasses previous spatial-based approaches while maintaining competitive performance with state-of-the-art (SOTA) feature-based methods, achieving 98.48% R@1 on CVUSA and 71.05% R@1 on CVACT\_test. We provide comprehensive analyses through pixel-level activation maps and feature-space UMAP visualizations to validate both effectiveness and interpretability.

Web 3.0-enabled edge computing provides a promising foundation for decentralized application (DApp) deployment. However, optimizing execution modes for interdependent task patterns remains challenging due to high computational overhead and blockchain consensus latency. This paper proposes an elastic hybrid architecture for Web 3.0-Enabled Edge Computing Systems (EDGEWEB3.0) that integrates on-chain and off-chain execution. DApp contracts are modeled as Directed Acyclic Graphs (DAGs) and partitioned into dependent task patterns, enabling a structured decomposition of execution. We formulate a DApp task scheduling problem and introduce the Decision Transformer-based Dependent Scheduling (DTDS) algorithm. DTDS employs masked self-attention to capture DAG dependencies and incorporates regularization terms to enforce constraints on service delays, gas costs, and computing capacity. We implement a real-world Web 3.0 testbed based on Ethereum, Goerli, and zkSync. Experimental results demonstrate that DTDS consistently outperforms state-of-the-art baselines in gas costs and service delays, providing a scalable solution for DApp execution in environments.

In the evolving landscape of Web 3.0, deploying and scheduling decentralized applications (DApps) presents significant challenges due to the complexity of heterogeneous nodes, edges, and their intricate interactions. Traditional approaches, particularly graph-based reinforcement learning (RL) methods, often rely on homogeneous graphs, which fail to capture the diverse relationships inherent in heterogeneous Web 3.0 environments. This limitation results in inefficient resource allocation, suboptimal task scheduling, and unclear security requirements. To address these issues, this paper introduces the Heterogeneous Graph Deployment Scheduler (HGDS), a novel framework that leverages Heterogeneous Graph Neural Networks (HGNNs) to model users, edge servers, and DApp tasks within Web 3.0 environments, and incorporates RL to optimize DApp scheduling policies. HGDS captures heterogeneity in Web 3.0 environments by jointly modeling node–edge interactions and heterogeneous edge relationships, enabling the generation of dynamic, task-aware embeddings that integrate both node and edge features. RL is further employed to adaptively optimize scheduling and resource allocation based on real-time network feedback. Experiments on a Web 3.0 testbed show that HGDS outperforms baseline methods by 12.2% in reward, while reducing service delay and gas consumption.

Prompt learning has proven effective in adapting vision language models for downstream tasks. However, existing methods usually append learnable prompt tokens solely with the category names to obtain textual features, which fails to fully leverage the rich context indicated in the category name. To address this issue, we propose the Tree of Attributes Prompt learning (TAP), which first instructs LLMs to generate a tree of attributes with a “concept - attribute - description” structure for each category, and then learn the hierarchy with vision and text prompt tokens. Unlike existing methods that merely augment category names with a set of unstructured descriptions, our approach essentially distills structured knowledge graphs associated with class names from LLMs. Furthermore, our approach introduces text and vision prompts designed to explicitly learn the corresponding visual attributes, effectively serving as domain experts. Additionally, the general and diverse descriptions generated based on the class names may be wrong or absent in the specific given images. To address this misalignment, we further introduce a vision-conditional pooling module to extract instance-specific text features. Extensive experimental results demonstrate that our approach outperforms state-of-the-art methods on the zero-shot base-to-novel generalization, cross-dataset transfer, as well as few-shot classification across 11 diverse datasets. Code is available at https://github.com/HHenryD/TAP.

Real world data often exhibits a long-tailed and open-ended (i.e., with unseen classes) distribution. A practical recognition system must balance between majority (head) and minority (tail) classes, generalize across the distribution, and acknowledge novelty upon the instances of unseen classes (open classes). We define Open Long-Tailed Recognition++ (OLTR++) as learning from such naturally distributed data and optimizing for the classification accuracy over a balanced test set which includes both known and open classes. OLTR++ handles imbalanced classification, few-shot learning, open-set recognition, and active learning in one integrated algorithm, whereas existing classification approaches often focus only on one or two aspects and deliver poorly over the entire spectrum. The key challenges are: 1) how to share visual knowledge between head and tail classes, 2) how to reduce confusion between tail and open classes, and 3) how to actively explore open classes with learned knowledge. Our algorithm, OLTR++, maps images to a feature space such that visual concepts can relate to each other through a memory association mechanism and a learned metric (dynamic meta-embedding) that both respects the closed world classification of seen classes and acknowledges the novelty of open classes. Additionally, we propose an active learning scheme based on visual memory, which learns to recognize open classes in a data-efficient manner for future expansions. On three large-scale open long-tailed datasets we curated from ImageNet (object-centric), Places (scene-centric), and MS1M (face-centric) data, as well as three standard benchmarks (CIFAR-10-LT, CIFAR-100-LT, and iNaturalist-18), our approach, as a unified framework, consistently demonstrates competitive performance. Notably, our approach also shows strong potential for the active exploration of open classes and the fairness analysis of minority groups.

We explore the challenges of human-in-the-loop frameworks to label wildlife recognition datasets with a neural network. In wildlife imagery, the main challenges for a model to assist human annotation are two-fold: (1) the training dataset is usually imbalanced, which makes the model's suggestion biased, and (2) there are complex taxonomies in the classes. We establish a simple and efficient baseline, including the debiasing loss function and the hyperbolic network architecture, to address these issues. Moreover, we propose leveraging the semantic correlation to train the model more effectively by adding a co-occurrence layer to our model during training. We demonstrate the efficacy of our method in both a real-world wildlife areal survey recognition dataset and the public image classification dataset, CIFAR100-LT, CIFAR10-LT, and iNaturalist.

A typical domain adaptation approach is to adapt models trained on the annotated data in a source domain (e.g., sunny weather) for achieving high performance on the test data in a target domain (e.g., rainy weather). Whether the target contains a single homogeneous domain or multiple heterogeneous domains, existing works always assume that there exist clear distinctions between the domains, which is often not true in practice (e.g., changes in weather). We study an open compound domain adaptation (OCDA) problem, in which the target is a compound of multiple homogeneous domains without domain labels, reflecting realistic data collection from mixed and novel situations. We propose a new approach based on two technical insights into OCDA: 1) a curriculum domain adaptation strategy to bootstrap generalization across domains in a data-driven self-organizing fashion and 2) a memory module to increase the model's agility towards novel domains. Our experiments on digit classification, facial expression recognition, semantic segmentation, and reinforcement learning demonstrate the effectiveness of our approach.

Real world data often have a long-tailed and open-ended distribution. A practical recognition system must classify among majority and minority classes, generalize from a few known instances, and acknowledge novelty upon a never seen instance. We define Open Long-Tailed Recognition (OLTR) as learning from such naturally distributed data and optimizing the classification accuracy over a balanced test set which include head, tail, and open classes. OLTR must handle imbalanced classification, few-shot learning, and open-set recognition in one integrated algorithm, whereas existing classification approaches focus only on one aspect and deliver poorly over the entire class spectrum. The key challenges are how to share visual knowledge between head and tail classes and how to reduce confusion between tail and open classes. We develop an integrated OLTR algorithm that maps an image to a feature space such that visual concepts can easily relate to each other based on a learned metric that respects the closed-world classification while acknowledging the novelty of the open world. Our so-called dynamic meta-embedding combines a direct image feature and an associated memory feature, with the feature norm indicating the familiarity to known classes. On three large-scale OLTR datasets we curate from object-centric ImageNet, scene-centric Places, and face-centric MS1M data, our method consistently outperforms the state-of-the-art. Our code, datasets, and models enable future OLTR research and are publicly available at \url{https://liuziwei7.github.io/projects/LongTail.html}.