Search

Recent advancements in connected autonomous vehicle (CAV) technology have sparked growing research interest in lane-free traffic (LFT). LFT envisions a scenario where all vehicles are CAVs, coordinating their movements without lanes to achieve smoother traffic flow and higher road capacity. This potentially reduces congestion without building new infrastructure. However, the transition phase will likely involve non-connected actors such as human-driven vehicles (HDVs) or independent AVs sharing the roads. This raises the question of how LFT performance is impacted when not all vehicles are CAVs, as these non-connected vehicles may prioritize their own benefits over system-wide improvements. This paper addresses this question through microscopic simulation on a ring road, where CAVs follow the potential lines (PL) controller for LFT, while HDVs adhere to a strip-based car-following model. The PL controller is also modified for safe velocities to prevent collisions. The results reveal that even a small percentage of HDVs can significantly disrupt LFT flow: 5% HDVs can reduce LFT's maximum road capacity by 16%, and a 20% HDVs nearly halves it. The study also develops an adaptive potential (APL) controller that forms APL corridors with modified PLs in the surroundings of HDVs. APL shows a peak traffic flow improvement of 23.6% over the PL controller. The study indicates that a penetration rate of approximately 60% CAVs in LFT is required before significant benefits of LFT start appearing compared to a scenario with all HDVs. These findings open a new research direction on minimizing the adverse effects of non-connected vehicles on LFT.

Colorectal polyps are structural abnormalities of the gastrointestinal tract that can potentially become cancerous in some cases. The study introduces a novel framework for colorectal polyp segmentation named the Multi-Scale and Multi-Path Cascaded Convolution Network (MMCC-Net), aimed at addressing the limitations of existing models, such as inadequate spatial dependence representation and the absence of multi-level feature integration during the decoding stage by integrating multi-scale and multi-path cascaded convolutional techniques and enhances feature aggregation through dual attention modules, skip connections, and a feature enhancer. MMCC-Net achieves superior performance in identifying polyp areas at the pixel level. The Proposed MMCC-Net was tested across six public datasets and compared against eight SOTA models to demonstrate its efficiency in polyp segmentation. The MMCC-Net's performance shows Dice scores with confidence intervals ranging between (77.08, 77.56) and (94.19, 94.71) and Mean Intersection over Union (MIoU) scores with confidence intervals ranging from (72.20, 73.00) to (89.69, 90.53) on the six databases. These results highlight the model's potential as a powerful tool for accurate and efficient polyp segmentation, contributing to early detection and prevention strategies in colorectal cancer.

While numerous recent benchmarks focus on evaluating generic Vision-Language Models (VLMs), they fall short in addressing the unique demands of geospatial applications. Generic VLM benchmarks are not designed to handle the complexities of geospatial data, which is critical for applications such as environmental monitoring, urban planning, and disaster management. Some of the unique challenges in geospatial domain include temporal analysis for changes, counting objects in large quantities, detecting tiny objects, and understanding relationships between entities occurring in Remote Sensing imagery. To address this gap in the geospatial domain, we present GEOBench-VLM, a comprehensive benchmark specifically designed to evaluate VLMs on geospatial tasks, including scene understanding, object counting, localization, fine-grained categorization, and temporal analysis. Our benchmark features over 10,000 manually verified instructions and covers a diverse set of variations in visual conditions, object type, and scale. We evaluate several state-of-the-art VLMs to assess their accuracy within the geospatial context. The results indicate that although existing VLMs demonstrate potential, they face challenges when dealing with geospatial-specific examples, highlighting the room for further improvements. Specifically, the best-performing GPT4o achieves only 40\% accuracy on MCQs, which is only double the random guess performance. Our benchmark is publicly available at https://github.com/The-AI-Alliance/GEO-Bench-VLM .

This study explores the effectiveness of multi-temporal satellite imagery for better functional field boundary delineation using deep learning semantic segmentation architecture on two distinct geographical and multi-scale farming systems of Netherlands and Pakistan. Multidate images of April, August and October 2022 were acquired for PlanetScope and Sentinel-2 in sub regions of Netherlands and November 2022, February and March 2023 for selected area of Dunyapur in Pakistan. For Netherlands, Basic registration crop parcels (BRP) vector layer was used as labeled training data. while self-crafted field boundary vector data were utilized for Pakistan. Four deep learning models with UNET architecture were evaluated using different combinations of multi-date images and NDVI stacks in the Netherlands subregions. A comparative analysis of IoU scores assessed the effectiveness of the proposed multi-date NDVI stack approach. These findings were then applied for transfer learning, using pre-trained models from the Netherlands on the selected area in Pakistan. Additionally, separate models were trained using self-crafted field boundary data for Pakistan, and combined models were developed using data from both the Netherlands and Pakistan. Results indicate that multi-date NDVI stacks provide additional temporal context, reflecting crop growth over different times of the season. The study underscores the critical role of multi-scale ground information from diverse geographical areas in developing robust and universally applicable models for field boundary delineation. The results also highlight the importance of fine spatial resolution for extraction of field boundaries in regions with small scale framing. The findings can be extended to multi-scale implementations for improved automatic field boundary delineation in heterogeneous agricultural environments., Comment: 09 pages, To be published

The manner in which different racial and gender groups are portrayed in news coverage plays a large role in shaping public opinion. As such, understanding how such groups are portrayed in news media is of notable societal value, and has thus been a significant endeavour in both the computer and social sciences. Yet, the literature still lacks a longitudinal study examining both the frequency of appearance of different racial and gender groups in online news articles, as well as the context in which such groups are discussed. To fill this gap, we propose two machine learning classifiers to detect the race and age of a given subject. Next, we compile a dataset of 123,337 images and 441,321 online news articles from New York Times (NYT) and Fox News (Fox), and examine representation through two computational approaches. Firstly, we examine the frequency and prominence of appearance of racial and gender groups in images embedded in news articles, revealing that racial and gender minorities are largely under-represented, and when they do appear, they are featured less prominently compared to majority groups. Furthermore, we find that NYT largely features more images of racial minority groups compared to Fox. Secondly, we examine both the frequency and context with which racial minority groups are presented in article text. This reveals the narrow scope in which certain racial groups are covered and the frequency with which different groups are presented as victims and/or perpetrators in a given conflict. Taken together, our analysis contributes to the literature by providing two novel open-source classifiers to detect race and age from images, and shedding light on the racial and gender biases in news articles from venues on opposite ends of the American political spectrum., Comment: 13 pages, and 11 figures

Federated Learning (FL) is a technique that allows multiple parties to train a shared model collaboratively without disclosing their private data. It has become increasingly popular due to its distinct privacy advantages. However, FL models can suffer from biases against certain demographic groups (e.g., racial and gender groups) due to the heterogeneity of data and party selection. Researchers have proposed various strategies for characterizing the group fairness of FL algorithms to address this issue. However, the effectiveness of these strategies in the face of deliberate adversarial attacks has not been fully explored. Although existing studies have revealed various threats (e.g., model poisoning attacks) against FL systems caused by malicious participants, their primary aim is to decrease model accuracy, while the potential of leveraging poisonous model updates to exacerbate model unfairness remains unexplored. In this paper, we propose a new type of model poisoning attack, EAB-FL, with a focus on exacerbating group unfairness while maintaining a good level of model utility. Extensive experiments on three datasets demonstrate the effectiveness and efficiency of our attack, even with state-of-the-art fairness optimization algorithms and secure aggregation rules employed.

We establish abstract horizontal norm relations involving the unramified Hecke-Frobenius polynomials that correspond under the Satake isomorhpism to the degree eight spinor $L$-factors of $ \mathrm{GSp}_{6} $. These relations apply to classes in the degree seven motivic cohomology of the Siegel modular sixfold obtained via Gysin pushforwards of Beilinson's Eisenstein symbol pulled back on one copy in a triple product of modular curves. The proof is based on a novel approach that circumvents the failure of the so-called multiplicity one hypothesis in our setting, which precludes the applicability of an existing technique. In a sequel, we combine our result with the previously established vertical norm relations for these classes to obtain new Euler systems for the eight dimensional Galois representations associated with certain non-endoscopic cohomological cuspidal automorphic representations of $ \mathrm{GSp}_{6} $., Comment: 52 pages. Comments welcome

We present a novel axiomatic framework for establishing horizontal norm relations in Euler systems that are built from pushforwards of classes in the motivic cohomology of Shimura varieties. This framework is uniformly applicable to the Euler systems of both algebraic cycles and Eisenstein classes. It also applies to non-spherical pairs of groups that fail to satisfy a local multiplicity one hypothesis, and thus lie beyond the reach of existing methods. A key application of this work is the construction of an Euler system for the spinor Galois representations arising in the cohomology of Siegel modular varieties of genus three, which is undertaken in two companion articles., Comment: 79 pages. Comments welcome

The fifth generation of mobile networks (5G) represents the latest development in mobile communications. It has been designed to support several types of data traffic and to meet more performance requirements than ever before. These characteristics make 5G very attractive for current but also novel public and private industries and services. However, because of coverage, regulatory, business, and security reasons, many of these novel applications can only be deployed as part of a private network. The cost of licensed frequencies makes such approach prohibitive for many stakeholders, and therefore unlicensed frequency bands represent a more affordable option. Even so, private 5G networks for use in globally unlicensed frequency bands do not yet exist. In this paper we present the first end-to-end private 5G network operating in a globally unlicensed frequency band, using general purpose computers, open-source software and software-defined radio. We evidence its working and show that the choice of the hardware can significantly affect the performance of the network., Comment: arXiv admin note: This version has been removed by arXiv administrators as the submitter did not have the right to agree to the license at the time of submission

In this paper, a Hamiltonian lattice formulation for 2+1D compact Maxwell-Chern-Simons theory is derived. We analytically solve this theory and demonstrate that the mass gap in the continuum limit matches the well-known continuum formula. Our formulation preserves topological features such as the quantization of the Chern-Simons level, the degeneracy of energy eigenstates, the non-trivial properties of Wilson loops, and the mutual and self statistics of anyons. This work lays the groundwork for future Hamiltonian-based simulations of Maxwell-Chern-Simons theory on classical and quantum computers.

Neuromorphic sensors, specifically event cameras, revolutionize visual data acquisition by capturing pixel intensity changes with exceptional dynamic range, minimal latency, and energy efficiency, setting them apart from conventional frame-based cameras. The distinctive capabilities of event cameras have ignited significant interest in the domain of event-based action recognition, recognizing their vast potential for advancement. However, the development in this field is currently slowed by the lack of comprehensive, large-scale datasets, which are critical for developing robust recognition frameworks. To bridge this gap, we introduces DailyDVS-200, a meticulously curated benchmark dataset tailored for the event-based action recognition community. DailyDVS-200 is extensive, covering 200 action categories across real-world scenarios, recorded by 47 participants, and comprises more than 22,000 event sequences. This dataset is designed to reflect a broad spectrum of action types, scene complexities, and data acquisition diversity. Each sequence in the dataset is annotated with 14 attributes, ensuring a detailed characterization of the recorded actions. Moreover, DailyDVS-200 is structured to facilitate a wide range of research paths, offering a solid foundation for both validating existing approaches and inspiring novel methodologies. By setting a new benchmark in the field, we challenge the current limitations of neuromorphic data processing and invite a surge of new approaches in event-based action recognition techniques, which paves the way for future explorations in neuromorphic computing and beyond. The dataset and source code are available at https://github.com/QiWang233/DailyDVS-200., Comment: Accepted to ECCV 2024

The so-called fast polar decoding schedules are meant to improve the decoding speed of the sequential-natured successive cancellation list decoders. The decoding speedup is achieved by replacing various parts of the serial decoding process with efficient special-purpose decoder nodes. This work incorporates the fast decoding schedules for polar codes into their quantized finite alphabet decoding. In a finite alphabet successive cancellation list decoder, the log-likelihood ratio computations are replaced with lookup operations on low-resolution integer messages. The lookup tables are designed using the information bottleneck method. It is shown that the finite alphabet decoders can also leverage the special decoder nodes found in the literature. Besides their inherent decoding speed improvement, the use of these special decoder nodes drastically reduces the number of lookup tables required to perform the finite alphabet decoding. In order to perform quantized decoding using lookup operations, the proposed decoders require up to 93% less unique lookup tables as compared to the ones that use the conventional successive cancellation schedule. Moreover, the proposed decoders exhibit negligible loss in error correction performance without necessitating alterations to the lookup table design process., Comment: 6 pages, 7 figures, submitted to IEEE GLOBECOM 2024

While neural networks have excelled in video action recognition tasks, their black-box nature often obscures the understanding of their decision-making processes. Recent approaches used inherently interpretable models to analyze video actions in a manner akin to human reasoning. These models, however, usually fall short in performance compared to their black-box counterparts. In this work, we present a new framework named Language-guided Interpretable Action Recognition framework (LaIAR). LaIAR leverages knowledge from language models to enhance both the recognition capabilities and the interpretability of video models. In essence, we redefine the problem of understanding video model decisions as a task of aligning video and language models. Using the logical reasoning captured by the language model, we steer the training of the video model. This integrated approach not only improves the video model's adaptability to different domains but also boosts its overall performance. Extensive experiments on two complex video action datasets, Charades & CAD-120, validates the improved performance and interpretability of our LaIAR framework. The code of LaIAR is available at https://github.com/NingWang2049/LaIAR., Comment: Accepted by CVPR 2024