We introduce a novel anchor-free contrastive learning (AFCL) method leveraging our proposed Similarity-Orthogonality (SimO) loss. The AFCL method, powered by SimO loss, creates a fiber bundle topological structure in the embedding space, forming class-specific, internally cohesive yet orthogonal neighborhoods. We validate the efficacy of our method on the CIFAR-10 dataset, providing visualizations that demonstrate the impact of SimO loss on the embedding space. Our results illustrate the formation of distinct, orthogonal class neighborhoods, showcasing the method's ability to create well-structured embeddings that balance class separation with intra-class variability. This work opens new avenues for understanding and leveraging the geometric properties of learned representations in various machine learning tasks. The pursuit of effective representation learning (Gidaris et al. (2018); Wu et al. (2018); Oord et al. (2019)) has been a cornerstone of modern machine learning, with contrastive methods emerging as particularly powerful tools in recent years. Despite significant advancements, the field of supervised contrastive learning (Khosla et al. (2021); Balestriero et al. (2023)) continues to grapple with fundamental challenges that impede the development of truly robust and interpretable models.

Mamba is emerging as a novel approach to overcome the challenges faced by Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) in computer vision. While CNNs excel at extracting local features, they often struggle to capture long-range dependencies without complex architectural modifications. In contrast, ViTs effectively model global relationships but suffer from high computational costs due to the quadratic complexity of their self-attention mechanisms. Mamba addresses these limitations by leveraging Selective Structured State Space Models to effectively capture long-range dependencies with linear computational complexity. This survey analyzes the unique contributions, computational benefits, and applications of Mamba models while also identifying challenges and potential future research directions. We provide a foundational resource for advancing the understanding and growth of Mamba models in computer vision. An overview of this work is available at https://github.com/maklachur/Mamba-in-Computer-Vision.

On-demand Food Delivery (OFD) services have become very common around the world. For example, on the Ele.me platform, users place more than 15 million food orders every day. Predicting the Real-time Pressure Signal (RPS) is crucial for OFD services, as it is primarily used to measure the current status of pressure on the logistics system. When RPS rises, the pressure increases, and the platform needs to quickly take measures to prevent the logistics system from being overloaded. Usually, the average delivery time for all orders within a business district is used to represent RPS. Existing research on OFD services primarily focuses on predicting the delivery time of orders, while relatively less attention has been given to the study of the RPS. Previous research directly applies general models such as DeepFM, RNN, and GNN for prediction, but fails to adequately utilize the unique temporal and spatial characteristics of OFD services, and faces issues with insufficient sensitivity during sudden severe weather conditions or peak periods. To address these problems, this paper proposes a new method based on Spatio-Temporal Transformer and Memory Network (STTM). Specifically, we use a novel Spatio-Temporal Transformer structure to learn logistics features across temporal and spatial dimensions and encode the historical information of a business district and its neighbors, thereby learning both temporal and spatial information. Additionally, a Memory Network is employed to increase sensitivity to abnormal events. Experimental results on the real-world dataset show that STTM significantly outperforms previous methods in both offline experiments and the online A/B test, demonstrating the effectiveness of this method.

Spatiotemporal forecasting has emerged as an indispensable building block of diverse smart city applications, such as intelligent transportation and smart energy management. Recent advancements have uncovered that the performance of spatiotemporal forecasting can be significantly improved by integrating knowledge in geo-distributed time series data from different domains, \eg enhancing real-estate appraisal with human mobility data; joint taxi and bike demand predictions. While effective, existing approaches assume a centralized data collection and exploitation environment, overlooking the privacy and commercial interest concerns associated with data owned by different parties. In this paper, we investigate multi-party collaborative spatiotemporal forecasting without direct access to multi-source private data. However, this task is challenging due to 1) cross-domain feature heterogeneity and 2) cross-client geographical heterogeneity, where standard horizontal or vertical federated learning is inapplicable. To this end, we propose a Heterogeneous SpatioTemporal Federated Learning (HSTFL) framework to enable multiple clients to collaboratively harness geo-distributed time series data from different domains while preserving privacy. Specifically, we first devise vertical federated spatiotemporal representation learning to locally preserve spatiotemporal dependencies among individual participants and generate effective representations for heterogeneous data. Then we propose a cross-client virtual node alignment block to incorporate cross-client spatiotemporal dependencies via a multi-level knowledge fusion scheme. Extensive privacy analysis and experimental evaluations demonstrate that HSTFL not only effectively resists inference attacks but also provides a significant improvement against various baselines.

Positional Encoder Graph Neural Networks (PE-GNNs) are a leading approach for modeling continuous spatial data. However, they often fail to produce calibrated predictive distributions, limiting their effectiveness for uncertainty quantification. We introduce the Positional Encoder Graph Quantile Neural Network (PE-GQNN), a novel method that integrates PE-GNNs, Quantile Neural Networks, and recalibration techniques in a fully nonparametric framework, requiring minimal assumptions about the predictive distributions. We propose a new network architecture that, when combined with a quantile-based loss function, yields accurate and reliable probabilistic models without increasing computational complexity. Our approach provides a flexible, robust framework for conditional density estimation, applicable beyond spatial data contexts. We further introduce a structured method for incorporating a KNN predictor into the model while avoiding data leakage through the GNN layer operation. Experiments on benchmark datasets demonstrate that PE-GQNN significantly outperforms existing state-of-the-art methods in both predictive accuracy and uncertainty quantification.

Abstract-- Active perception enables robots to dynamically gather information by adjusting their viewpoints, a crucial capability for interacting with complex, partially observable environments. In this paper, we present AP-VLM, a novel framework that combines active perception with a Vision-Language Model (VLM) to guide robotic exploration and answer semantic queries. Using a 3D virtual grid overlaid on the scene and orientation adjustments, AP-VLM allows a robotic manipulator to intelligently select optimal viewpoints and orientations to resolve challenging tasks, such as identifying objects in occluded or inclined positions. We evaluate our system on two robotic platforms: a 7-DOF Franka Panda and a 6-DOF UR5, across various scenes with differing object configurations. Our results demonstrate that AP-VLM significantly outperforms passive perception methods and baseline models, including Toward Grounded Common Sense Reasoning (TGCSR), particularly in scenarios where fixed camera views are inadequate. The adaptability of AP-VLM in real-world settings shows promise for enhancing robotic systems' understanding of complex environments, bridging the gap between high-level semantic reasoning and low-level control.

Large vision-language models (VLMs) have become state-of-the-art for many computer vision tasks, with in-context learning (ICL) as a popular adaptation strategy for new ones. But can VLMs learn novel concepts purely from visual demonstrations, or are they limited to adapting to the output format of ICL examples? We propose a new benchmark we call Spatial Visual Ambiguity Tasks (SVAT) that challenges state-of-the-art VLMs to learn new visuospatial tasks in-context. We find that VLMs fail to do this zero-shot, and sometimes continue to fail after finetuning. However, adding simpler data to the training by curriculum learning leads to improved ICL performance.

Volunteer Geographic Information (VGI), with its rich variety, large volume, rapid updates, and diverse sources, has become a critical source of geospatial data. However, VGI data from platforms like OSM exhibit significant quality heterogeneity across different data types, particularly with urban building data. To address this, we propose a multi-source geographic data transformation solution, utilizing accessible and complete VGI data to assist in generating urban building footprint data. We also employ a multimodal data generation framework to improve accuracy. First, we introduce a pipeline for constructing an 'image-text-metadata-building footprint' dataset, primarily based on road network data and supplemented by other multimodal data. We then present ControlCity, a geographic data transformation method based on a multimodal diffusion model. This method first uses a pre-trained text-to-image model to align text, metadata, and building footprint data. An improved ControlNet further integrates road network and land-use imagery, producing refined building footprint data. Experiments across 22 global cities demonstrate that ControlCity successfully simulates real urban building patterns, achieving state-of-the-art performance. Specifically, our method achieves an average FID score of 50.94, reducing error by 71.01% compared to leading methods, and a MIoU score of 0.36, an improvement of 38.46%. Additionally, our model excels in tasks like urban morphology transfer, zero-shot city generation, and spatial data completeness assessment. In the zero-shot city task, our method accurately predicts and generates similar urban structures, demonstrating strong generalization. This study confirms the effectiveness of our approach in generating urban building footprint data and capturing complex city characteristics.

As various types of crime continue to threaten public safety and economic development, predicting the occurrence of multiple types of crimes becomes increasingly vital for effective prevention measures. Although extensive efforts have been made, most of them overlook the heterogeneity of different crime categories and fail to address the issue of imbalanced spatial distribution. In this work, we propose a Spatial-Temporal Mixture-of-Graph-Experts (ST-MoGE) framework for collective multiple-type crime prediction. To enhance the model's ability to identify diverse spatial-temporal dependencies and mitigate potential conflicts caused by spatial-temporal heterogeneity of different crime categories, we introduce an attentive-gated Mixture-of-Graph-Experts (MGEs) module to capture the distinctive and shared crime patterns of each crime category. Then, we propose Cross-Expert Contrastive Learning(CECL) to update the MGEs and force each expert to focus on specific pattern modeling, thereby reducing blending and redundancy. Furthermore, to address the issue of imbalanced spatial distribution, we propose a Hierarchical Adaptive Loss Re-weighting (HALR) approach to eliminate biases and insufficient learning of data-scarce regions. To evaluate the effectiveness of our methods, we conduct comprehensive experiments on two real-world crime datasets and compare our results with twelve advanced baselines. The experimental results demonstrate the superiority of our methods.

Accurately detecting objects at long distances remains a critical challenge in 3D object detection when relying solely on LiDAR sensors due to the inherent limitations of data sparsity. To address this issue, we propose the LiDAR-Camera Augmentation Network (LCANet), a novel framework that reconstructs LiDAR point cloud data by fusing 2D image features, which contain rich semantic information, generating additional points to improve detection accuracy. LCANet fuses data from LiDAR sensors and cameras by projecting image features into the 3D space, integrating semantic information into the point cloud data. This fused data is then encoded to produce 3D features that contain both semantic and spatial information, which are further refined to reconstruct final points before bounding box prediction. This fusion effectively compensates for LiDAR's weakness in detecting objects at long distances, which are often represented by sparse points. Additionally, due to the sparsity of many objects in the original dataset, which makes effective supervision for point generation challenging, we employ a point cloud completion network to create a complete point cloud dataset that supervises the generation of dense point clouds in our network. Extensive experiments on the KITTI and Waymo datasets demonstrate that LCANet significantly outperforms existing models, particularly in detecting sparse and distant objects.