Stripe-like space target detection (SSTD) plays a key role in enhancing space situational awareness, but it faces three challenges: the lack of public datasets, interference from space noise, and the variability of stripe-like targets, making manual labeling both inaccurate and labor-intensive. In response, we introduce ‘AstroStripeSet’, a pioneering dataset for SSTD, aiming to bridge the gap in academic resources. Furthermore, we propose a novel teacher-student label evolution framework with single-point weak supervision, providing a new solution to the challenges of manual labeling. It starts with generating initial pseudo-labels using the zero-shot capabilities of the Segment Anything Model (SAM) in a single-point setting. Then, the fine-tuned StripeSAM serves as the teacher and the newly developed StripeNet as the student, improving segmentation performance through label evolution, which iteratively refines these labels. We also introduce ‘GeoDice’, a new loss function tailored for the linear characteristics of stripe-like targets. Extensive experiments show that our method matches fully supervised approaches, exhibits strong zero-shot generalization for diverse real-world images, and sets a new state-of-the-art benchmark. Our dataset and code are available at https://github.com/BenZae/SSTD.

Crop biomass offers crucial insights into plant health and yield, making it essential for crop science, farming systems, and agricultural research. However, current measurement methods, which are labor-intensive, destructive, and imprecise, hinder large-scale quantification of this trait. To address this limitation, we present a biomass prediction network (BioNet), designed for adaptation across different data modalities, including point clouds and drone imagery. Our BioNet, utilizing a sparse 3D convolutional neural network (CNN) and a transformer-based prediction module, processes point clouds and other 3D data representations to predict biomass. To further extend BioNet for drone imagery, we integrate a neural feature field (NeFF) module, enabling 3D structure reconstruction and the transformation of 2D semantic features from vision foundation models into the corresponding 3D surfaces. For the point cloud modality, BioNet demonstrates superior performance on two public datasets, with an approximate 6.1% relative improvement (RI) over the state-of-the-art. In the RGB image modality, the combination of BioNet and NeFF achieves a 7.9% RI. Additionally, the NeFF-based approach utilizes inexpensive, portable drone-mounted cameras, providing a scalable solution for large field applications.

• Introduce CBCB with sequential (CBCB-S) and revert (CBCB-R) behaviours. • Leverage watch-time duration with user history for short-term prediction. • Outperform VideoReach and UVCAN on Precision, Recall, F1, and Accuracy. • CBCB-R achieves Recall 1.000 and F1-Score 0.990 on JAWWY logs. • Decision Tree is the strongest conventional baseline across datasets. Predicting future user actions is essential for enhancing video recommendation systems. Machine learning-based recommendation models analyze user behavior on video streaming platforms to deliver personalized content suggestions. However, existing approaches often rely solely on user-item interaction history or optimize video-level watch-time, overlooking key implicit factors such as watch-time duration and video intrinsic characteristics, which significantly influence user engagement and content preference. To address these gaps, this study introduces the Content-Based Captivation Behavior (CBCB) framework, a novel two-step approach that enhances short-term behavior prediction in video streaming platforms. First, the User Sequential Captivation Behavior (CBCB-S) component analyzes historical viewing patterns to track engagement trends. Next, the User Revert Captivation Behavior (CBCB-R) component identifies instances where users return to previously viewed content, refining personalized recommendations. By integrating watch-time duration and historical behavioral patterns, CBCB provides a more nuanced understanding of user engagement and captures sequential and revert behaviors at the user level—enabling more precise personalized recommendations than video-level watch-time-based approaches. The proposed method is implemented using machine learning algorithms and evaluated on a real-world JAWWY (Saudi Telecom Company) dataset. Experimental results demonstrate that CBCB achieves high precision, recall, F1-score, and overall accuracy for personalized recommendations. These findings highlight the importance of modeling sequential and revert user behaviors to enhance content personalization, recommendation relevance, and user satisfaction.

We introduce TopoX, a Python software suite that provides reliable and user-friendly building blocks for computing and machine learning on topological domains that extend graphs: hypergraphs, simplicial, cellular, path and combinatorial complexes. TopoX consists of three packages: TopoNetX facilitates constructing and computing on these domains, including working with nodes, edges and higher-order cells; TopoEmbedX provides methods to embed topological domains into vector spaces, akin to popular graph-based embedding algorithms such as node2vec; TopoModelX is built on top of PyTorch and offers a comprehensive toolbox of higher-order message passing functions for neural networks on topological domains. The extensively documented and unit-tested source code of TopoX is available under MIT license at https://pyt-team.github.io.

Extracting and aggregating multiple feature representations from various scales have become the key to point cloud classification tasks. Vision Transformer (ViT) is a representative solution along this line, but it lacks the capability to model detailed multi-scale features and their interactions. In addition, learning efficient and effective representation from the point cloud is challenging due to its irregular, unordered, and sparse nature. To tackle these problems, we propose a novel multi-scale representation learning transformer framework, employing various geometric features beyond common Cartesian coordinates. Our approach enriches the description of point clouds by local geometric relationships and group them at multiple scales. This scale information is aggregated and then new patches can be extracted to minimize feature overlay. The bottleneck projection head is then adopted to enhance the information and feed all patches to the multi-head attention to capture the deep dependencies among representations across patches. Evaluation on public benchmark datasets shows the competitive performance of our framework on point cloud classification.

This article investigates spectral chromatic and spatial defocus aberration in a monocular hyperspectral image (HSI) and proposes methods on how these cues can be utilized for relative depth estimation. The main aim of this work is to develop a framework by exploring intrinsic and extrinsic reflectance properties in HSI that can be useful for depth estimation. Depth estimation from a monocular image is a challenging task. An additional level of difficulty is added due to low resolution and noises in hyperspectral data. Our contribution to handling depth estimation in HSI is threefold. Firstly, we propose that change in focus across band images of HSI due to chromatic aberration and band-wise defocus blur can be integrated for depth estimation. Novel methods are developed to estimate sparse depth maps based on different integration models. Secondly, by adopting manifold learning, an effective objective function is developed to combine all sparse depth maps into a final optimized sparse depth map. Lastly, a new dense depth map generation approach is proposed, which extrapolate sparse depth cues by using material-based properties on graph Laplacian. Experimental results show that our methods successfully exploit HSI properties to generate depth cues. We also compare our method with state-of-the-art RGB image-based approaches, which shows that our methods produce better sparse and dense depth maps than those from the benchmark methods.

Spectral-spatial feature extraction is an important task in hyperspectral image processing. In this paper we propose a novel method to extract distinctive invariant features from hyperspectral images for registration of hyperspectral images with different spectral conditions. Spectral condition means images are captured with different incident lights, viewing angles, or using different hyperspectral cameras. In addition, spectral condition includes images of objects with the same shape but different materials. This method, which is named spectral-spatial scale invariant feature transform (SS-SIFT), explores both spectral and spatial dimensions simultaneously to extract spectral and geometric transformation invariant features. Similar to the classic SIFT algorithm, SS-SIFT consists of keypoint detection and descriptor construction steps. Keypoints are extracted from spectral-spatial scale space and are detected from extrema after 3D difference of Gaussian is applied to the data cube. Two descriptors are proposed for each keypoint by exploring the distribution of spectral-spatial gradient magnitude in its local 3D neighborhood. The effectiveness of the SS-SIFT approach is validated on images collected in different light conditions, different geometric projections, and using two hyperspectral cameras with different spectral wavelength ranges and resolutions. The experimental results show that our method generates robust invariant features for spectral-spatial image matching.

3D reconstruction from hyper spectral images has seldom been addressed in the literature. This is a challenging problem because 3D models reconstructed from different spectral bands demonstrate different properties. If we use a single band or covert the hyper spectral image to gray scale image for the reconstruction, fine structural information may be lost. In this paper, we present a novel method to reconstruct a 3D model from hyper spectral images. Our proposed method first generates 3D point sets from images at each wavelength using the typical structure from motion approach. A structural descriptor is developed to characterize the spatial relationship between the points, which allows robust point matching between two 3D models at different wavelength. Then a 3D registration method is introduced to combine all band-level models into a single and complete hyper spectral 3D model. As far as we know, this is the first attempt in reconstructing a complete 3D model from hyper spectral images. This work allows fine structural-spectral information of an object be captured and integrated into the 3D model, which can be used to support further research and applications.

This paper addresses the problem of avoiding dynamic obstacles while following the learned trajectory through non-point based maps directly through laser data. The geometric representation of free configuration area changes while a moving obstacle enters into the safety region of autonomous mobile robot. We have applied the Bézier curve properties to the free configuration eigenspaces to satisfy the dynamic obstacle avoidance path constraints. The algorithm is designed to accurately represent the mobile robot's characteristics while avoiding obstacle such as minimum turning radius. Moreover, we also discuss the obstacle avoided path feasibility as a vectorial combination of free configuration eigen-vectors at discrete time scan-frames to manifest a trajectory, which once followed and mapped onto the two control signals of mobile robot will enable it to build an efficient and accurate online environment map. Preliminary results in Matlab have been shown to validate the idea, while the same has been implemented in Player/stage (robotics real-time software) to analyze the performance of the proposed system.

This paper addresses the problem of moving obstacle detection for autonomous mobile robots in unknown urban environments through the fusion of (vehicle-mounted) forward looking laser and vision sensors. In this approach we reparameterize the 2D gaussian distribution of the laser free-configuration eigenspaces by vision saliency gaussian kernel function. The approach uses bi-sensor paradigm to achieve greater effective mapping of the environment and improved accuracy in obstacle position estimation. Where the laser lower dimensional manifolds provide an eigenvector which corresponds to the free configuration space of the high order geometric representation of the environment and vision based edge detection followed by the saliency mapping provides the road detection and existance of dynamic obstacles on the road. We have shown that while the vectorial combination of eigenvectors at discrete time scan-frames of laser data manifest a trajectory, and once followed and fused with the vision sensor data, enables mobile robot to build an efficient and accurate online environment map free of obstacles. We demonstrated this process using real-time NAVLAB CMU (Autonomous Jeep's) data-set which is a good representation of autonomous mobile robot's navigation in an urban environment.