The ability to read, understand and find important information from written text is a critical skill in our daily lives for our independence, comfort and safety. However, a significant part of our society is affected by partial vision impairment, which leads to discomfort and dependency in daily activities. To address the limitations of this part of society, we propose an intelligent reading assistant based on smart glasses with embedded RGB cameras and a Large Language Model (LLM), whose functionality goes beyond corrective lenses. The video recorded from the egocentric perspective of a person wearing the glasses is processed to localise text information using object detection and optical character recognition methods. The LLM processes the data and allows the user to interact with the text and responds to a given query, thus extending the functionality of corrective lenses with the ability to find and summarize knowledge from the text. To evaluate our method, we create a chat-based application that allows the user to interact with the system. The evaluation is conducted in a real-world setting, such as reading menus in a restaurant, and involves four participants. The results show robust accuracy in text retrieval. The system not only provides accurate meal suggestions but also achieves high user satisfaction, highlighting the potential of smart glasses and LLMs in assisting people with special needs.
A comprehensive understanding of surgical scenes allows for monitoring of the surgical process, reducing the occurrence of accidents and enhancing efficiency for medical professionals. Semantic modeling within operating rooms, as a scene graph generation (SGG) task, is challenging since it involves consecutive recognition of subtle surgical actions over prolonged periods. To address this challenge, we propose a Tri-modal (i.e., images, point clouds, and language) confluence with Temporal dynamics framework, termed TriTemp-OR. Diverging from previous approaches that integrated temporal information via memory graphs, our method embraces two advantages: 1) we directly exploit bi-modal temporal information from the video streaming for hierarchical feature interaction, and 2) the prior knowledge from Large Language Models (LLMs) is embedded to alleviate the class-imbalance problem in the operating theatre. Specifically, our model performs temporal interactions across 2D frames and 3D point clouds, including a scale-adaptive multi-view temporal interaction (ViewTemp) and a geometric-temporal point aggregation (PointTemp). Furthermore, we transfer knowledge from the biomedical LLM, LLaVA-Med, to deepen the comprehension of intraoperative relations. The proposed TriTemp-OR enables the aggregation of tri-modal features through relation-aware unification to predict relations so as to generate scene graphs. Experimental results on the 4D-OR benchmark demonstrate the superior performance of our model for long-term OR streaming.
Iterative learning control (ILC) is a method for reducing system tracking or estimation errors over multiple iterations by using information from past iterations. The disturbance observer (DOB) is used to estimate and mitigate disturbances within the system, while the system is being affected by them. ILC enhances system performance by introducing a feedforward signal in each iteration. However, its effectiveness may diminish if the conditions change during the iterations. On the other hand, although DOB effectively mitigates the effects of new disturbances, it cannot entirely eliminate them as it operates reactively. Therefore, neither ILC nor DOB alone can ensure sufficient robustness in challenging scenarios. This study focuses on the simultaneous utilization of ILC and DOB to enhance system robustness. The proposed methodology specifically targets dynamically different linearized systems performing repetitive tasks. The systems share similar forms but differ in dynamics (e.g. sizes, masses, and controllers). Consequently, the design of learning filters must account for these differences in dynamics. To validate the approach, the study establishes a theoretical framework for designing learning filters in conjunction with DOB. The validity of the framework is then confirmed through numerical studies and experimental tests conducted on unmanned aerial vehicles (UAVs). Although UAVs are nonlinear systems, the study employs a linearized controller as they operate in proximity to the hover condition. A video introduction of this paper is available via this link: https://zh.engr.tamu.edu/wp-content/uploads/sites/310/2024/02/ILCDOB_v3f.mp4.
Finding an available on-street parking spot is a relevant problem of day-to-day life. In recent years, cities such as Melbourne and San Francisco deployed sensors that provide real-time information about the occupation of parking spots. Finding a free parking spot in such a smart environment can be modeled and solved as a Markov decision process (MDP). The problem has to consider uncertainty as available parking spots might not remain available until arrival due to other vehicles also claiming spots in the meantime. Knowing the parking intention of every vehicle in the environment would eliminate this uncertainty. Unfortunately, it does currently not seem realistic to have such data from all vehicles. In contrast, acquiring data from a subset of vehicles or a vehicle fleet appears feasible and has the potential to reduce uncertainty. In this paper, we examine the question of how useful sharing data within a vehicle fleet might be for the search times of particular drivers. We use fleet data to better estimate the availability of parking spots at arrival. Since optimal solutions for large scenarios are infeasible, we base our method on approximate solutions, which have been shown to perform well in single-agent settings. Our experiments are conducted on a simulation using real-world and synthetic data from the city of Melbourne. The results indicate that fleet data can significantly reduce search times for an available parking spot.
Chain of thought finetuning aims to endow small student models with reasoning capacity to improve their performance towards a specific task by allowing them to imitate the reasoning procedure of large language models (LLMs) beyond simply predicting the answer to the question. However, the existing methods 1) generate rationale before the answer, making their answer correctness sensitive to the hallucination in the rationale;2) force the student model to repeat the exact LLMs rationale expression word-after-word, which could have the model biased towards learning the expression in rationale but count against the model from understanding the core logic behind it. Therefore, we propose a robust Post-Semantic-Thinking (PST) strategy to generate answers before rationale. Thanks to this answer-first setting, 1) the answering procedure can escape from the adverse effects caused by hallucinations in the rationale; 2) the complex reasoning procedure is tightly bound with the relatively concise answer, making the reasoning for questions easier with the prior information in the answer; 3) the efficiency of the method can also benefit from the setting since users can stop the generation right after answers are outputted when inference is conducted. Furthermore, the PST strategy loose the constraint against the generated rationale to be close to the LLMs gold standard in the hidden semantic space instead of the vocabulary space, thus making the small student model better comprehend the semantic reasoning logic in rationale. Extensive experiments conducted across 12 reasoning tasks demonstrate the effectiveness of PST.
In this paper, we study the embedded feature selection problem in linear Support Vector Machines (SVMs), in which a cardinality constraint is employed, leading to a fully explainable selection model. The problem is NP-hard due to the presence of the cardinality constraint, even though the original linear SVM amounts to a problem solvable in polynomial time. To handle the hard problem, we first introduce two mixed-integer formulations for which novel SDP relaxations are proposed. Exploiting the sparsity pattern of the relaxations, we decompose the problems and obtain equivalent relaxations in a much smaller cone, making the conic approaches scalable. To make the best usage of the decomposed relaxations, we propose heuristics using the information of its optimal solution. Moreover, an exact procedure is proposed by solving a sequence of mixed-integer decomposed SDPs. Numerical results on classical benchmarking datasets are reported, showing the efficiency and effectiveness of our approach.
The interest in federated learning has surged in recent research due to its unique ability to train a global model using privacy-secured information held locally on each client. This paper pays particular attention to the issue of client-side model heterogeneity, a pervasive challenge in the practical implementation of FL that escalates its complexity. Assuming a scenario where each client possesses varied memory storage, processing capabilities and network bandwidth - a phenomenon referred to as system heterogeneity - there is a pressing need to customize a unique model for each client. In response to this, we present an effective and adaptable federated framework FedP3, representing Federated Personalized and Privacy-friendly network Pruning, tailored for model heterogeneity scenarios. Our proposed methodology can incorporate and adapt well-established techniques to its specific instances. We offer a theoretical interpretation of FedP3 and its locally differential-private variant, DP-FedP3, and theoretically validate their efficiencies.
Harmonic instability occurs frequently in the power electronic converter system. This paper leverages multi-resolution dynamic mode decomposition (MR-DMD) as a data-driven diagnostic tool for the system stability of power electronic converters, not requiring complex modeling and detailed control information. By combining dynamic mode decomposition (DMD) with the multi-resolution analysis used in wavelet theory, dynamic modes and eigenvalues can be identified at different decomposition levels and time scales with the MR-DMD algorithm, thereby allowing for handling datasets with transient time behaviors, which is not achievable using conventional DMD. Further, the selection criteria for important parameters in MR-DMD are clearly defined through derivation, elucidating the reason for enabling it to extract eigenvalues within different frequency ranges. Finally, the analysis results are verified using the dataset collected from the experimental platform of a low-frequency oscillation scenario in electrified railways featuring a single-phase converter.
Accurate prediction of drivers' gaze is an important component of vision-based driver monitoring and assistive systems. Of particular interest are safety-critical episodes, such as performing maneuvers or crossing intersections. In such scenarios, drivers' gaze distribution changes significantly and becomes difficult to predict, especially if the task and context information is represented implicitly, as is common in many state-of-the-art models. However, explicit modeling of top-down factors affecting drivers' attention often requires additional information and annotations that may not be readily available. In this paper, we address the challenge of effective modeling of task and context with common sources of data for use in practical systems. To this end, we introduce SCOUT+, a task- and context-aware model for drivers' gaze prediction, which leverages route and map information inferred from commonly available GPS data. We evaluate our model on two datasets, DR(eye)VE and BDD-A, and demonstrate that using maps improves results compared to bottom-up models and reaches performance comparable to the top-down model SCOUT which relies on privileged ground truth information. Code is available at https://github.com/ykotseruba/SCOUT.
In the Massive Open Online Courses (MOOC) learning scenario, the semantic information of instructional videos has a crucial impact on learners' emotional state. Learners mainly acquire knowledge by watching instructional videos, and the semantic information in the videos directly affects learners' emotional states. However, few studies have paid attention to the potential influence of the semantic information of instructional videos on learners' emotional states. To deeply explore the impact of video semantic information on learners' emotions, this paper innovatively proposes a multimodal emotion recognition method by fusing video semantic information and physiological signals. We generate video descriptions through a pre-trained large language model (LLM) to obtain high-level semantic information about instructional videos. Using the cross-attention mechanism for modal interaction, the semantic information is fused with the eye movement and PhotoPlethysmoGraphy (PPG) signals to obtain the features containing the critical information of the three modes. The accurate recognition of learners' emotional states is realized through the emotion classifier. The experimental results show that our method has significantly improved emotion recognition performance, providing a new perspective and efficient method for emotion recognition research in MOOC learning scenarios. The method proposed in this paper not only contributes to a deeper understanding of the impact of instructional videos on learners' emotional states but also provides a beneficial reference for future research on emotion recognition in MOOC learning scenarios.