Handwritten Mathematical Expression Recognition (HMER) has wide applications in human-machine interaction scenarios, such as digitized education and automated offices. Recently, sequence-based models with encoder-decoder architectures have been commonly adopted to address this task by directly predicting LaTeX sequences of expression images. However, these methods only implicitly learn the syntax rules provided by LaTeX, which may fail to describe the position and hierarchical relationship between symbols due to complex structural relations and diverse handwriting styles. To overcome this challenge, we propose a position forest transformer (PosFormer) for HMER, which jointly optimizes two tasks: expression recognition and position recognition, to explicitly enable position-aware symbol feature representation learning. Specifically, we first design a position forest that models the mathematical expression as a forest structure and parses the relative position relationships between symbols. Without requiring extra annotations, each symbol is assigned a position identifier in the forest to denote its relative spatial position. Second, we propose an implicit attention correction module to accurately capture attention for HMER in the sequence-based decoder architecture. Extensive experiments validate the superiority of PosFormer, which consistently outperforms the state-of-the-art methods 2.03%/1.22%/2.00%, 1.83%, and 4.62% gains on the single-line CROHME 2014/2016/2019, multi-line M2E, and complex MNE datasets, respectively, with no additional latency or computational cost. Code is available at https://github.com/SJTU-DeepVisionLab/PosFormer.
Large-scale pre-training models have promoted the development of histopathology image analysis. However, existing self-supervised methods for histopathology images primarily focus on learning patch features, while there is a notable gap in the availability of pre-training models specifically designed for WSI-level feature learning. In this paper, we propose a novel self-supervised learning framework for pan-cancer WSI-level representation pre-training with the designed position-aware masked autoencoder (PAMA). Meanwhile, we propose the position-aware cross-attention (PACA) module with a kernel reorientation (KRO) strategy and an anchor dropout (AD) mechanism. The KRO strategy can capture the complete semantic structure and eliminate ambiguity in WSIs, and the AD contributes to enhancing the robustness and generalization of the model. We evaluated our method on 7 large-scale datasets from multiple organs for pan-cancer classification tasks. The results have demonstrated the effectiveness and generalization of PAMA in discriminative WSI representation learning and pan-cancer WSI pre-training. The proposed method was also compared with 8 WSI analysis methods. The experimental results have indicated that our proposed PAMA is superior to the state-of-the-art methods. The code and checkpoints are available at https://github.com/WkEEn/PAMA.
In this letter, we study the energy efficiency maximization problem for a fluid antenna system (FAS) in near field communications. Specifically, we consider a point-to-point near-field system where the base station (BS) transmitter has multiple fixed-position antennas and the user receives the signals with multiple fluid antennas. Our objective is to jointly optimize the transmit beamforming of the BS and the fluid antenna positions at the user for maximizing the energy efficiency. Our scheme is based on an alternating optimization algorithm that iteratively solves the beamforming and antenna position subproblems. Our simulation results validate the performance improvement of the proposed algorithm and confirm the effectiveness of FAS.
The calibration of weather radar for detecting meteorological phenomena has advanced rapidly, aiming to enhance accuracy. Utilizing an unmanned aerial vehicle (UAV) equipped with a suspended metal sphere introduces an efficient calibration method by allowing dynamic adjustment of the UAV's position, effectively acting as a mobile calibration platform. However, external factors such as wind can introduce bias in reflectivity measurements by causing the sphere to deviate from its intended position. This study develops a theoretical model to assess the impact of the metal sphere's one-dimensional oscillation on reflectivity. The findings offer valuable insights for UAV based radar calibration efforts.
This paper investigates an over-the-air federated learning (OTA-FL) system that employs fluid antennas (FAs) at an access point. The system enhances learning performance by leveraging the additional degrees of freedom provided by antenna mobility. We analyze the convergence of the OTA-FL system and derive the optimality gap to illustrate the influence of FAs on learning performance. With these results, we formulate a nonconvex optimization problem to minimize the optimality gap by jointly optimizing the positions of the FAs, the beamforming vector, and the transmit power allocation at each user. To address the dynamic environment, we cast this optimization problem as a Markov decision process and propose the recurrent deterministic policy gradient (RDPG) algorithm. Finally, extensive simulations show that the FA-assisted OTA-FL system outperforms systems with fixed-position antennas and that the RDPG algorithm surpasses the existing methods.
The advent of the sixth-generation (6G) networks presents another round of revolution for the mobile communication landscape, promising an immersive experience, robust reliability, minimal latency, extreme connectivity, ubiquitous coverage, and capabilities beyond communication, including intelligence and sensing. To achieve these ambitious goals, it is apparent that 6G networks need to incorporate the state-of-the-art technologies. One of the technologies that has garnered rising interest is fluid antenna system (FAS) which represents any software-controllable fluidic, conductive, or dielectric structure capable of dynamically changing its shape and position to reconfigure essential radio-frequency (RF) characteristics. Compared to traditional antenna systems (TASs) with fixed-position radiating elements, the core idea of FAS revolves around the unique flexibility of reconfiguring the radiating elements within a given space. One recent driver of FAS is the recognition of its position-flexibility as a new degree of freedom (dof) to harness diversity and multiplexing gains. In this paper, we provide a comprehensive tutorial, covering channel modeling, signal processing and estimation methods, information-theoretic insights, new multiple access techniques, and hardware designs. Moreover, we delineate the challenges of FAS and explore the potential of using FAS to improve the performance of other contemporary technologies. By providing insights and guidance, this tutorial paper serves to inspire researchers to explore new horizons and fully unleash the potential of FAS.
The objective of this paper is to determine the position of a single mobile robot in a swarm using dead reckoning techniques. We investigate the accuracy of navigation by using this process. The paper begins with the research background and social importance. Then, the specific experimental setup and analysis of experimental results are presented. Finally, the results are detailed and some potential improvements are provided.
Testing in production-like test environments is an essential part of quality assurance processes in many industries. Provisioning of such test environments, for information-intensive services, involves setting up databases that are rich-enough to enable simulating a wide variety of user scenarios. While production data is perhaps the gold-standard here, many organizations, particularly within the public sectors, are not allowed to use production data for testing purposes due to privacy concerns. The alternatives are to use anonymized data, or synthetically generated data. In this paper, we elaborate on these alternatives and compare them in an industrial context. Further we focus on synthetic data generation and investigate the use of recurrent neural networks for this purpose. In our preliminary experiments, we were able to generate representative and highly accurate data using a recurrent neural network. These results open new research questions that we discuss here, and plan to investigate in our future research.
Despite the success achieved by existing image generation and editing methods, current models still struggle with complex problems including intricate text prompts, and the absence of verification and self-correction mechanisms makes the generated images unreliable. Meanwhile, a single model tends to specialize in particular tasks and possess the corresponding capabilities, making it inadequate for fulfilling all user requirements. We propose GenArtist, a unified image generation and editing system, coordinated by a multimodal large language model (MLLM) agent. We integrate a comprehensive range of existing models into the tool library and utilize the agent for tool selection and execution. For a complex problem, the MLLM agent decomposes it into simpler sub-problems and constructs a tree structure to systematically plan the procedure of generation, editing, and self-correction with step-by-step verification. By automatically generating missing position-related inputs and incorporating position information, the appropriate tool can be effectively employed to address each sub-problem. Experiments demonstrate that GenArtist can perform various generation and editing tasks, achieving state-of-the-art performance and surpassing existing models such as SDXL and DALL-E 3, as can be seen in Fig. 1. Project page is https://zhenyuw16.github.io/GenArtist_page.
Left atrial (LA) segmentation is a crucial technique for irregular heartbeat (i.e., atrial fibrillation) diagnosis. Most current methods for LA segmentation strictly assume that the input data is acquired using object-oriented center cropping, while this assumption may not always hold in practice due to the high cost of manual object annotation. Random cropping is a straightforward data pre-processing approach. However, it 1) introduces significant irregularities and incompleteness in the input data and 2) disrupts the coherence and continuity of object boundary regions. To tackle these issues, we propose a novel Dynamic Position transformation and Boundary refinement Network (DPBNet). The core idea is to dynamically adjust the relative position of irregular targets to construct their contextual relationships and prioritize difficult boundary pixels to enhance foreground-background distinction. Specifically, we design a shuffle-then-reorder attention module to adjust the position of disrupted objects in the latent space using dynamic generation ratios, such that the vital dependencies among these random cropping targets could be well captured and preserved. Moreover, to improve the accuracy of boundary localization, we introduce a dual fine-grained boundary loss with scenario-adaptive weights to handle the ambiguity of the dual boundary at a fine-grained level, promoting the clarity and continuity of the obtained results. Extensive experimental results on benchmark dataset have demonstrated that DPBNet consistently outperforms existing state-of-the-art methods.
In the era of 6G, developing and managing software requires cutting-edge software engineering (SE) theories and practices tailored for such complexity across a vast number of connected edge devices. Our project aims to lead the development of sustainable methods and energy-efficient orchestration models specifically for edge environments, enhancing architectural support driven by AI for contemporary edge-to-cloud continuum computing. This initiative seeks to position Finland at the forefront of the 6G landscape, focusing on sophisticated edge orchestration and robust software architectures to optimize the performance and scalability of edge networks. Collaborating with leading Finnish universities and companies, the project emphasizes deep industry-academia collaboration and international expertise to address critical challenges in edge orchestration and software architecture, aiming to drive significant advancements in software productivity and market impact.
This paper studies the problem of characterizing the region of the airspace that will be occupied by a space debris during an uncontrolled reentry (footprint), with the final goal of supporting the air traffic controllers in their task of guiding aircraft safely from their origin to their destination. Given the various sources of uncertainty affecting the debris dynamics, the reentry process is characterized probabilistically and the problem of determining the footprint is formulated in terms of a chance-constrained optimization program, which is solved via a simulation-based method. When observations of the debris initial position and radar measurements of the aircraft prior to the reentry event are available, nonlinear filtering techniques can be adopted and the posterior probability distribution of the debris position as well as of the wind field affecting the reentry process can be integrated in the chance-constraint formulation so as to obtain an enhanced estimate of the footprint. Simulation results show the efficacy of the approach.
Due to their architecture and how they are trained, artificial neural networks are typically not robust toward pruning or shuffling layers at test time. However, such properties would be desirable for different applications, such as distributed neural network architectures where the order of execution cannot be guaranteed or parts of the network can fail during inference. In this work, we address these issues through a number of training approaches for vision transformers whose most important component is randomizing the execution order of attention modules at training time. With our proposed approaches, vision transformers are capable to adapt to arbitrary layer execution orders at test time assuming one tolerates a reduction (about 20\%) in accuracy at the same model size. We analyse the feature representations of our trained models as well as how each layer contributes to the models prediction based on its position during inference. Our analysis shows that layers learn to contribute differently based on their position in the network. Finally, we layer-prune our models at test time and find that their performance declines gracefully. Code available at https://github.com/matfrei/layershuffle.
Utility-scale solar arrays require specialized inspection methods for detecting faulty panels. Photovoltaic (PV) panel faults caused by weather, ground leakage, circuit issues, temperature, environment, age, and other damage can take many forms but often symptomatically exhibit temperature differences. Included is a mini survey to review these common faults and PV array fault detection approaches. Among these, infrared thermography cameras are a powerful tool for improving solar panel inspection in the field. These can be combined with other technologies, including image processing and machine learning. This position paper examines several computer vision algorithms that automate thermal anomaly detection in infrared imagery. We demonstrate our infrared thermography data collection approach, the PV thermal imagery benchmark dataset, and the measured performance of image processing transformations, including the Hough Transform for PV segmentation. The results of this implementation are presented with a discussion of future work.
Integrating cognitive ergonomics with LLMs is crucial for improving safety, reliability, and user satisfaction in human-AI interactions. Current LLM designs often lack this integration, resulting in systems that may not fully align with human cognitive capabilities and limitations. This oversight exacerbates biases in LLM outputs and leads to suboptimal user experiences due to inconsistent application of user-centered design principles. Researchers are increasingly leveraging NLP, particularly LLMs, to model and understand human behavior across social sciences, psychology, psychiatry, health, and neuroscience. Our position paper explores the need to integrate cognitive ergonomics into LLM design, providing a comprehensive framework and practical guidelines for ethical development. By addressing these challenges, we aim to advance safer, more reliable, and ethically sound human-AI interactions.
To be able to play soccer, a robot needs a good estimate of its current position on the field. Ideally, multiple features are visible that have known locations. By applying trigonometry we can estimate the viewpoint from where this observation was actually made. Given that the Nao robots of the Standard Platform League have quite a limited field of view, a given camera frame typically only allows for one or two points to be recognized. In this paper we propose a method for determining the (x, y) coordinates on the field and the height h of the camera from the geometry of a simplified tetrahedron. This configuration is formed by two observed points on the ground plane plus the gravitational direction. When the distance between the two points is known, and the directions to the points plus the gravitational direction are measured, all dimensions of the tetrahedron can be determined. By performing these calculations with rational trigonometry instead of classical trigonometry, the computations turn out to be 28.7% faster, with equal numerical accuracy. The position of the head of the Nao can also be externally measured with the OptiTrack system. The difference between externally measured and internally predicted position from sensor data gives us mean absolute errors in the 3-6 centimeters range, when we estimated the gravitational direction from the vanishing point of the outer edges of the goal posts.
In recent years, vision Transformers and MLPs have demonstrated remarkable performance in image understanding tasks. However, their inherently dense computational operators, such as self-attention and token-mixing layers, pose significant challenges when applied to spatio-temporal video data. To address this gap, we propose PosMLP-Video, a lightweight yet powerful MLP-like backbone for video recognition. Instead of dense operators, we use efficient relative positional encoding (RPE) to build pairwise token relations, leveraging small-sized parameterized relative position biases to obtain each relation score. Specifically, to enable spatio-temporal modeling, we extend the image PosMLP's positional gating unit to temporal, spatial, and spatio-temporal variants, namely PoTGU, PoSGU, and PoSTGU, respectively. These gating units can be feasibly combined into three types of spatio-temporal factorized positional MLP blocks, which not only decrease model complexity but also maintain good performance. Additionally, we enrich relative positional relationships by using channel grouping. Experimental results on three video-related tasks demonstrate that PosMLP-Video achieves competitive speed-accuracy trade-offs compared to the previous state-of-the-art models. In particular, PosMLP-Video pre-trained on ImageNet1K achieves 59.0%/70.3% top-1 accuracy on Something-Something V1/V2 and 82.1% top-1 accuracy on Kinetics-400 while requiring much fewer parameters and FLOPs than other models. The code is released at https://github.com/zhouds1918/PosMLP_Video.
For the past three years, Kaggle has been hosting the Image Matching Challenge, which focuses on solving a 3D image reconstruction problem using a collection of 2D images. Each year, this competition fosters the development of innovative and effective methodologies by its participants. In this paper, we introduce an advanced ensemble technique that we developed, achieving a score of 0.153449 on the private leaderboard and securing the 160th position out of over 1,000 participants. Additionally, we conduct a comprehensive review of existing methods and techniques employed by top-performing teams in the competition. Our solution, alongside the insights gathered from other leading approaches, contributes to the ongoing advancement in the field of 3D image reconstruction. This research provides valuable knowledge for future participants and researchers aiming to excel in similar image matching and reconstruction challenges.
Multimodal Large Language Models (MLLM) have made significant progress in the field of document analysis. Despite this, existing benchmarks typically focus only on extracting text and simple layout information, neglecting the complex interactions between elements in structured documents such as mind maps and flowcharts. To address this issue, we introduce the new benchmark named MindBench, which not only includes meticulously constructed bilingual authentic or synthetic images, detailed annotations, evaluation metrics and baseline models, but also specifically designs five types of structured understanding and parsing tasks. These tasks include full parsing, partial parsing, position-related parsing, structured Visual Question Answering (VQA), and position-related VQA, covering key areas such as text recognition, spatial awareness, relationship discernment, and structured parsing. Extensive experimental results demonstrate the substantial potential and significant room for improvement in current models' ability to handle structured document information. We anticipate that the launch of MindBench will significantly advance research and application development in structured document analysis technology. MindBench is available at: https://miasanlei.github.io/MindBench.github.io/.
Mobile robots and autonomous vehicles are often required to function in environments where critical position estimates from sensors such as GPS become uncertain or unreliable. Single image visual place recognition (VPR) provides an alternative for localization but often requires techniques such as sequence matching to improve robustness, which incurs additional computation and latency costs. Even then, the sequence length required to localize at an acceptable performance level varies widely; and simply setting overly long fixed sequence lengths creates unnecessary latency, computational overhead, and can even degrade performance. In these scenarios it is often more desirable to meet or exceed a set target performance at minimal expense. In this paper we present an approach which uses a calibration set of data to fit a model that modulates sequence length for VPR as needed to exceed a target localization performance. We make use of a coarse position prior, which could be provided by any other localization system, and capture the variation in appearance across this region. We use the correlation between appearance variation and sequence length to curate VPR features and fit a multilayer perceptron (MLP) for selecting the optimal length. We demonstrate that this method is effective at modulating sequence length to maximize the number of sections in a dataset which meet or exceed a target performance whilst minimizing the median length used. We show applicability across several datasets and reveal key phenomena like generalization capabilities, the benefits of curating features and the utility of non-state-of-the-art feature extractors with nuanced properties.