In the digital media era, video blogs (vlogs) have become a crucial news platform, gaining attention for their personalized and interactive features. However, research has yet to fully explore the factors influencing sustained audience engagement with vlog news. Grounded in Media-system Dependency (MSD) Theory and Parasocial Interaction (PSI) Theory, this study examines key drivers of continuous user engagement, including vlogger attributes, content quality, and platform technicalities. A survey of 553 users, analyzed with Partial Least Squares Structural Equation Modeling (PLS-SEM) and Fuzzy-set Qualitative Comparative Analysis (fsQCA), reveals significant effects of vlogger attractiveness and expertise, content’s entertainment and information quality, and the platform’s interactivity and fluency on PSI and ongoing viewing intentions. Additionally, the emotional bond between users and vlog news moderates the PSI and sustained viewing relationship. These findings enrich the media consumption framework and offer practical insights. Notably, the role of algorithmic content curation, enhancing media dependency and PSI through personalized content recommendations, is acknowledged.

Off-road semantic segmentation with fine-grained labels is necessary for autonomous vehicles to understand driving scenes, as the coarse-grained road detection cannot satisfy off-road vehicles with various mechanical properties. Pixel-wise annotation of fine-grained labels in off-road scenes is very hard because a large part of the pixels could suffer from severe semantic ambiguity. Furthermore, semantic properties of off-road scenes can be very changeable due to various precipitations, temperature, defoliation, etc. To address these challenges, this research proposes an active and contrastive learning-based method. A few image patches are annotated mainly to distinguish semantic differences rather than semantic categories, which can greatly reduce the burden of manual annotation. A feature representation is learnt using the contrastive pairs of image patches, and semantic categories are adaptively modeled from the data. To actively adapt to new scenes, a risk evaluation method is developed to discover and select hard frames with high-risk predictions for supplementary labeling, to update the model efficiently. Extensive experiments and analyses are conducted on self-developed and public datasets. Experimental results demonstrate that fine-grained semantic segmentation can be learned with only dozens of weakly labeled frames, and the model can efficiently adapt across scenes by weak supervision, while achieving competitive performance with the typical fully supervised ones.

Whether it’s a driver warning or an autonomous driving system, ADAS needs to decide when to alert the driver of danger or take over control. This research formulates the problem as an alert-scene categorization one and proposes a method using contrastive learning. Given a front-view video of a driving scene, a set of anchor points is marked by a human driver, where an anchor point indicates that the semantic attribute of the current scene is different from that of the previous one. The anchor frames are then used to generate contrastive image pairs to train a feature encoder and obtain a scene similarity measure, so as to expand the distance of the scenes of different categories in the feature space. Each scene category is explicitly modeled to capture the meta pattern on the distribution of scene similarity values, which is then used to infer scene categories. Experiments are conducted using front-view videos that were collected during driving at a cluttered dynamic campus. The scenes are categorized into no alert, longitudinal alert, and lateral alert. The results are studied at both feature encoding, category modeling, and reasoning aspects. By comparing precision with two full supervised end-to-end baseline models, the proposed method demonstrates competitive or superior performance. However, it remains still questions: how to generate ground truth data and how to evaluate performance in ambiguous situations, which leads to future works.

3D semantic segmentation is a fundamental task for robotic and autonomous driving applications. Recent works have been focused on using deep learning techniques, whereas developing fine-annotated 3D LiDAR datasets is extremely labor intensive and requires professional skills. The performance limitation caused by insufficient datasets is called data hunger problem. This research provides a comprehensive survey on the question: are we hungry for 3D LiDAR data for semantic segmentation? The studies are conducted at three levels. First, a broad review to the main 3D LiDAR datasets is conducted, followed by a statistical analysis on three representative datasets to gain an in-depth view on the datasets’ size, diversity and quality, which are the critical factors in learning deep models. Second, an organized survey of 3D semantic segmentation methods is given with a focus on the mainstream of the latest research trend using deep learning techniques, followed by a systematic survey to the existing efforts to solve the data hunger problem. Finally, an insightful discussion of the remaining problems on both methodological and datasets’ viewpoints, and the open questions on dataset bias, domain and semantic gap are given, leading to potential topics in future works. To the best of our knowledge, this is the first work to study the data hunger problem for 3D semantic segmentation using deep learning techniques, which are addressed in both methodological and dataset review, and we share findings and discussions through a comprehensive dataset analysis.

Road detection or traversability analysis has been a key technique for a mobile robot to traverse complex off-road scenes. The problem has been mainly formulated in early works as a binary classification one, e.g. associating pixels with road or non-road labels. Whereas understanding scenes with fine-grained labels are needed for off-road robots, as scenes are very diverse, and the various mechanical performance of off-road robots may lead to different definitions of safe regions to traverse. How to define and annotate fine-grained labels to achieve meaningful scene understanding for a robot to traverse off-road is still an open question. This research proposes a contrastive learning based method. With a set of human-annotated anchor patches, a feature representation is learned to discriminate regions with different traversability, a method of fine-grained semantic segmentation and mapping is subsequently developed for off-road scene understanding. Experiments are conducted on a dataset of three driving segments that represent very diverse off-road scenes. An anchor accuracy of 89.8% is achieved by evaluating the matching with human-annotated image patches in cross-scene validation. Examined by associated 3D LiDAR data, the fine-grained segments of visual images are demonstrated to have different levels of toughness and terrain elevation, which represents their semantical meaningfulness. The resultant maps contain both fine-grained labels and confidence values, providing rich information to support a robot traversing complex off-road scenes.

3D semantic segmentation is one of the key tasks for autonomous driving system. Recently, deep learning models for 3D semantic segmentation task have been widely researched, but they usually require large amounts of training data. However, the present datasets for 3D semantic segmentation are lack of point-wise annotation, diversiform scenes and dynamic objects. In this paper1, we propose the SemanticPOSS dataset, which contains 2988 various and complicated LiDAR scans with large quantity of dynamic instances. The data is collected in Peking University and uses the same data format as SemanticKITTI. In addition, we evaluate several typical 3D semantic segmentation models on our SemanticPOSS dataset. Experimental results show that SemanticPOSS can help to improve the prediction accuracy of dynamic objects as people, car in some degree. SemanticPOSS will be published at www.poss.pku.edu.cn.

This work studies the semantic segmentation of 3D LiDAR data in dynamic scenes for autonomous driving applications. A system of semantic segmentation using 3D LiDAR data, including range image segmentation, sample generation, inter-frame data association, track-level annotation, and semi-supervised learning, is developed. To reduce the considerable requirement of fine annotations, a CNN-based classifier is trained by considering both supervised samples with manually labeled object classes and pairwise constraints, where a data sample is composed of a segment as the foreground and neighborhood points as the background. A special loss function is designed to account for both annotations and constraints, where the constraint data are encouraged to be assigned to the same semantic class. A dataset containing 1838 frames of LiDAR data, 39 934 pairwise constraints and 57 927 human annotations is developed. The performance of the method is examined extensively. The qualitative and quantitative experiments show that the combination of a few annotations and large amount of constraint data significantly enhances the effectiveness and scene adaptability, resulting in greater than 10% improvement.

Securely deleting obsolete data is of significant importance, as reserving them may not only endanger data owners' privacy, but also violate data protection regulations like GDPR, SOX and HIPPA. However, completely eliminating data is extremely challenging in modern computer systems. One reason is the past existence of the deleted data may leave artifacts in the layout of a storage system at all layers, and such structural artifacts may be utilized by the adversary to derive sensitive information about the data having been deleted. A novel security notion, history independence, can ensure that memory representation of a data structure is independent of the operation sequences leading to it. Therefore, history independence can be utilized to remove the structural artifacts created by the deleted data, making it possible to achieve secure deletion guarantee. In this work, leveraging history independence, we build history independent systems. The existing history independent file system (HIFS) suffers from a significant degradation compared to the regular file system, rendering it impractical for real-world applications. A fundamental reason for such a degradation is, HIFS simply re-locates the entire data in a history independent manner for each single write. This is unfortunately unnecessary since a multi-snapshot adversary has observed a previous snapshot, and relocating data appearing in this old snapshot is vain and incurs unnecessary overhead. This will be exacerbated when the file system load factor is large. We thus design eHIFS, the first efficient History Independent File System, in which we smartly take advantage of knowledge on the adversary's observations and eliminate those unnecessary re-locations. Security analysis and experimental evaluation show that, compared to HIFS, eHIFS can achieve a similar history independence guarantee, with a 33X write throughput improvement when the file system load factor is 90%.

We propose a method for off-road drivable area extraction using 3D LiDAR data with the goal of autonomous driving application. A specific deep learning framework is designed to deal with the ambiguous area, which is one of the main challenges in the off-road environment. To reduce the considerable demand for human-annotated data for network training, we utilize the information from vast quantities of vehicle paths and auto-generated obstacle labels. Using these auto-generated annotations, the proposed network can be trained using weakly supervised or semi-supervised methods, which can achieve better performance with fewer human annotations. The experiments on our dataset illustrate the reasonability of our framework and the validity of our weakly and semi-supervised methods.

In the multirate switching environment each (connection) request is associated with a bandwidth weight. We consider a three-stage Clos network and assume that each link has a capacity of one (after normalization). The network is rearrangeable if for all possible sets of requests such that each input and output link generates a total weight not exceeding one, there always exists a set of paths, one for each request, such that the sum of weights of all paths going through a link does not exceed the link capacity. The question is to determine the minimum number of center switches which guarantees rearrangeability. We obtain a lower bound of 11n/9 and an upper bound of 41n/16. We then extend the result for the three-stage Clos network to the multistage Clos network. Finally, we propose the weighted version of the edge-coloring problem, which somehow has escaped the literature, associated with our switching network problem.

A minimum Steiner tree for a given set X of points is a network interconnecting the points of X having minimum possible total length. The Steiner ratio for a metric space is the largest lower bound for the ratio of lengths between a minimum Steiner tree and a minimum spanning tree on the same set of points in the metric space. In this note, we show that for any Minkowski plane, the Steiner ratio is at least 2/3. This settles a conjecture of D. Cieslik, and also Du et al.