With the rise of marine exploration, underwater imaging has gained significant attention as a research topic. Underwater video enhancement has become crucial for real-time computer vision tasks in marine exploration. However, most existing methods focus on enhancing individual frames and neglect video temporal dynamics, leading to visually poor enhancements. Furthermore, the lack of ground-truth references limits the use of abundant available underwater video data in many applications. To address these issues, we propose a two-stage framework for enhancing underwater videos. The first stage uses a denoising diffusion probabilistic model to learn a generative prior from unlabeled data, capturing robust and descriptive feature representations. In the second stage, this prior is incorporated into a physics-based image formulation for spatial enhancement, while also enforcing temporal consistency between video frames. Our method enables real-time and computationally-efficient processing of high-resolution underwater videos at lower resolutions, and offers efficient enhancement in the presence of diverse water-types. Extensive experiments on four datasets show that our approach generalizes well and outperforms existing enhancement methods. Our code is available at github.com/suhas-srinath/undive.
As we move towards a mixed-traffic scenario of Autonomous vehicles (AVs) and Human-driven vehicles (HDVs), understanding the car-following behaviour is important to improve traffic efficiency and road safety. Using a real-world trajectory dataset, this study uses descriptive and statistical analysis to investigate the car-following behaviours of three vehicle pairs: HDV-AV, AV-HDV and HDV-HDV in mixed traffic. The ANOVA test showed that car-following behaviours across different vehicle pairs are statistically significant (p-value < 0.05). We also introduce a data-driven Knowledge Distillation Neural Network (KDNN) model for predicting car-following behaviour in terms of speed. The KDNN model demonstrates comparable predictive accuracy to its teacher network, a Long Short-Term Memory (LSTM) network, and outperforms both the standalone student network, a Multilayer Perceptron (MLP), and traditional physics-based models like the Gipps model. Notably, the KDNN model better prevents collisions, measured by minimum Time-to-Collision (TTC), and operates with lower computational power, making it ideal for AVs or driving simulators requiring efficient computing.
High-quality training triplets (instruction, original image, edited image) are essential for instruction-based image editing. Predominant training datasets (e.g., InsPix2Pix) are created using text-to-image generative models (e.g., Stable Diffusion, DALL-E) which are not trained for image editing. Accordingly, these datasets suffer from inaccurate instruction following, poor detail preserving, and generation artifacts. In this paper, we propose to address the training data quality issue with multi-perspective reward data instead of refining the ground-truth image quality. 1) we first design a quantitative metric system based on best-in-class LVLM (Large Vision Language Model), i.e., GPT-4o in our case, to evaluate the generation quality from 3 perspectives, namely, instruction following, detail preserving, and generation quality. For each perspective, we collected quantitative score in $0\sim 5$ and text descriptive feedback on the specific failure points in ground-truth edited images, resulting in a high-quality editing reward dataset, i.e., RewardEdit20K. 2) We further proposed a novel training framework to seamlessly integrate the metric output, regarded as multi-reward, into editing models to learn from the imperfect training triplets. During training, the reward scores and text descriptions are encoded as embeddings and fed into both the latent space and the U-Net of the editing models as auxiliary conditions. During inference, we set these additional conditions to the highest score with no text description for failure points, to aim at the best generation outcome. Experiments indicate that our multi-reward conditioned model outperforms its no-reward counterpart on two popular editing pipelines, i.e., InsPix2Pix and SmartEdit. The code and dataset will be released.
Autonomous surface vessels (ASVs) are becoming increasingly significant in enhancing the safety and sustainability of maritime operations. To ensure the reliability of modern control algorithms utilized in these vessels, digital twins (DTs) provide a robust framework for conducting safe and effective simulations within a virtual environment. Digital twins are generally classified on a scale from 0 to 5, with each level representing a progression in complexity and functionality: Level 0 (Standalone) employs offline modeling techniques; Level 1 (Descriptive) integrates sensors and online modeling to enhance situational awareness; Level 2 (Diagnostic) focuses on condition monitoring and cybersecurity; Level 3 (Predictive) incorporates predictive analytics; Level 4 (Prescriptive) embeds decision-support systems; and Level 5 (Autonomous) enables advanced functionalities such as collision avoidance and path following. These digital representations not only provide insights into the vessel's current state and operational efficiency but also predict future scenarios and assess life endurance. By continuously updating with real-time sensor data, the digital twin effectively corrects modeling errors and enhances decision-making processes. Since DTs are key enablers for complex autonomous systems, this paper introduces a comprehensive methodology for establishing a digital twin framework specifically tailored for ASVs. Through a detailed literature survey, we explore existing state-of-the-art enablers across the defined levels, offering valuable recommendations for future research and development in this rapidly evolving field.
Discrete Choice Modelling serves as a robust framework for modelling human choice behaviour across various disciplines. Building a choice model is a semi structured research process that involves a combination of a priori assumptions, behavioural theories, and statistical methods. This complex set of decisions, coupled with diverse workflows, can lead to substantial variability in model outcomes. To better understand these dynamics, we developed the Serious Choice Modelling Game, which simulates the real world modelling process and tracks modellers' decisions in real time using a stated preference dataset. Participants were asked to develop choice models to estimate Willingness to Pay values to inform policymakers about strategies for reducing noise pollution. The game recorded actions across multiple phases, including descriptive analysis, model specification, and outcome interpretation, allowing us to analyse both individual decisions and differences in modelling approaches. While our findings reveal a strong preference for using data visualisation tools in descriptive analysis, it also identifies gaps in missing values handling before model specification. We also found significant variation in the modelling approach, even when modellers were working with the same choice dataset. Despite the availability of more complex models, simpler models such as Multinomial Logit were often preferred, suggesting that modellers tend to avoid complexity when time and resources are limited. Participants who engaged in more comprehensive data exploration and iterative model comparison tended to achieve better model fit and parsimony, which demonstrate that the methodological choices made throughout the workflow have significant implications, particularly when modelling outcomes are used for policy formulation.
Graph Neural Networks (GNNs) are a powerful technique for machine learning on graph-structured data, yet they pose interpretability challenges, especially for non-expert users. Existing GNN explanation methods often yield technical outputs such as subgraphs and feature importance scores, which are not easily understood. Building on recent insights from social science and other Explainable AI (XAI) methods, we propose GraphXAIN, a natural language narrative that explains individual predictions made by GNNs. We present a model-agnostic and explainer-agnostic XAI approach that complements graph explainers by generating GraphXAINs, using Large Language Models (LLMs) and integrating graph data, individual predictions from GNNs, explanatory subgraphs, and feature importances. We define XAI Narratives and XAI Descriptions, highlighting their distinctions and emphasizing the importance of narrative principles in effective explanations. By incorporating natural language narratives, our approach supports graph practitioners and non-expert users, aligning with social science research on explainability and enhancing user understanding and trust in complex GNN models. We demonstrate GraphXAIN's capabilities on a real-world graph dataset, illustrating how its generated narratives can aid understanding compared to traditional graph explainer outputs or other descriptive explanation methods.
Capturing a video's meaning and critical concepts by analyzing the subtle details is a fundamental yet challenging task in video captioning. Identifying the dominant emotional tone in a video significantly enhances the perception of its context. Despite a strong emphasis on video captioning, existing models often need to adequately address emotional themes, resulting in suboptimal captioning results. To address these limitations, this paper proposes a novel Semantic Processing and Emotion-informed video-Captioning Through Retrieval and Understanding Modalities (SPECTRUM) framework to empower the generation of emotionally and semantically credible captions. Leveraging our pioneering structure, SPECTRUM discerns multimodal semantics and emotional themes using Visual Text Attribute Investigation (VTAI) and determines the orientation of descriptive captions through a Holistic Concept-Oriented Theme (HCOT), expressing emotionally-informed and field-acquainted references. They exploit video-to-text retrieval capabilities and the multifaceted nature of video content to estimate the emotional probabilities of candidate captions. Then, the dominant theme of the video is determined by appropriately weighting embedded attribute vectors and applying coarse- and fine-grained emotional concepts, which define the video's contextual alignment. Furthermore, using two loss functions, SPECTRUM is optimized to integrate emotional information and minimize prediction errors. Extensive experiments on the EmVidCap, MSVD, and MSRVTT video captioning datasets demonstrate that our model significantly surpasses state-of-the-art methods. Quantitative and qualitative evaluations highlight the model's ability to accurately capture and convey video emotions and multimodal attributes.
Remote Sensing Image Captioning (RSIC) presents unique challenges and plays a critical role in applications. Traditional RSIC methods often struggle to produce rich and diverse descriptions. Recently, with advancements in VLMs, efforts have emerged to integrate these models into the remote sensing domain and to introduce descriptive datasets specifically designed to enhance VLM training. This paper proposes RS-MoE, a first Mixture of Expert based VLM specifically customized for remote sensing domain. Unlike traditional MoE models, the core of RS-MoE is the MoE Block, which incorporates a novel Instruction Router and multiple lightweight Large Language Models (LLMs) as expert models. The Instruction Router is designed to generate specific prompts tailored for each corresponding LLM, guiding them to focus on distinct aspects of the RSIC task. This design not only allows each expert LLM to concentrate on a specific subset of the task, thereby enhancing the specificity and accuracy of the generated captions, but also improves the scalability of the model by facilitating parallel processing of sub-tasks. Additionally, we present a two-stage training strategy for tuning our RS-MoE model to prevent performance degradation due to sparsity. We fine-tuned our model on the RSICap dataset using our proposed training strategy. Experimental results on the RSICap dataset, along with evaluations on other traditional datasets where no additional fine-tuning was applied, demonstrate that our model achieves state-of-the-art performance in generating precise and contextually relevant captions. Notably, our RS-MoE-1B variant achieves performance comparable to 13B VLMs, demonstrating the efficiency of our model design. Moreover, our model demonstrates promising generalization capabilities by consistently achieving state-of-the-art performance on the Remote Sensing Visual Question Answering (RSVQA) task.
There is an urgent need to identify both short and long-term risks from newly emerging types of Artificial Intelligence (AI), as well as available risk management measures. In response, and to support global efforts in regulating AI and writing safety standards, we compile an extensive catalog of risk sources and risk management measures for general-purpose AI (GPAI) systems, complete with descriptions and supporting examples where relevant. This work involves identifying technical, operational, and societal risks across model development, training, and deployment stages, as well as surveying established and experimental methods for managing these risks. To the best of our knowledge, this paper is the first of its kind to provide extensive documentation of both GPAI risk sources and risk management measures that are descriptive, self-contained and neutral with respect to any existing regulatory framework. This work intends to help AI providers, standards experts, researchers, policymakers, and regulators in identifying and mitigating systemic risks from GPAI systems. For this reason, the catalog is released under a public domain license for ease of direct use by stakeholders in AI governance and standards.
Video crime detection is a significant application of computer vision and artificial intelligence. However, existing datasets primarily focus on detecting severe crimes by analyzing entire video clips, often neglecting the precursor activities (i.e., privacy violations) that could potentially prevent these crimes. To address this limitation, we present PV-VTT (Privacy Violation Video To Text), a unique multimodal dataset aimed at identifying privacy violations. PV-VTT provides detailed annotations for both video and text in scenarios. To ensure the privacy of individuals in the videos, we only provide video feature vectors, avoiding the release of any raw video data. This privacy-focused approach allows researchers to use the dataset while protecting participant confidentiality. Recognizing that privacy violations are often ambiguous and context-dependent, we propose a Graph Neural Network (GNN)-based video description model. Our model generates a GNN-based prompt with image for Large Language Model (LLM), which deliver cost-effective and high-quality video descriptions. By leveraging a single video frame along with relevant text, our method reduces the number of input tokens required, maintaining descriptive quality while optimizing LLM API-usage. Extensive experiments validate the effectiveness and interpretability of our approach in video description tasks and flexibility of our PV-VTT dataset.
Generating lifelike human motions from descriptive texts has experienced remarkable research focus in the recent years, propelled by the emerging requirements of digital humans.Despite impressive advances, existing approaches are often constrained by limited control modalities, task specificity, and focus solely on body motion representations.In this paper, we present MotionGPT-2, a unified Large Motion-Language Model (LMLM) that addresses these limitations. MotionGPT-2 accommodates multiple motion-relevant tasks and supporting multimodal control conditions through pre-trained Large Language Models (LLMs). It quantizes multimodal inputs-such as text and single-frame poses-into discrete, LLM-interpretable tokens, seamlessly integrating them into the LLM's vocabulary. These tokens are then organized into unified prompts, guiding the LLM to generate motion outputs through a pretraining-then-finetuning paradigm. We also show that the proposed MotionGPT-2 is highly adaptable to the challenging 3D holistic motion generation task, enabled by the innovative motion discretization framework, Part-Aware VQVAE, which ensures fine-grained representations of body and hand movements. Extensive experiments and visualizations validate the effectiveness of our method, demonstrating the adaptability of MotionGPT-2 across motion generation, motion captioning, and generalized motion completion tasks.
The tendency of repeating past choices more often than expected from the history of outcomes has been repeatedly empirically observed in reinforcement learning experiments. It can be explained by at least two computational processes: asymmetric update and (gradual) choice perseveration. A recent meta-analysis showed that both mechanisms are detectable in human reinforcement learning. However, while their descriptive value seems to be well established, they have not been compared regarding their possible adaptive value. In this study, we address this gap by simulating reinforcement learning agents in a variety of environments with a new variant of an evolutionary algorithm. Our results show that positivity bias (in the form of asymmetric update) is evolutionary stable in many situations, while the emergence of gradual perseveration is less systematic and robust. Overall, our results illustrate that biases can be adaptive and selected by evolution, in an environment-specific manner.
Indoor navigation is challenging due to the absence of satellite positioning. This challenge is manifold greater for Visually Impaired People (VIPs) who lack the ability to get information from wayfinding signage. Other sensor signals (e.g., Bluetooth and LiDAR) can be used to create turn-by-turn navigation solutions with position updates for users. Unfortunately, these solutions require tags to be installed all around the environment or the use of fairly expensive hardware. Moreover, these solutions require a high degree of manual involvement that raises costs, thus hampering scalability. We propose an image dataset and associated image-centric solution called NaVIP towards visual intelligence that is infrastructure-free and task-scalable, and can assist VIPs in understanding their surroundings. Specifically, we start by curating large-scale phone camera data in a four-floor research building, with 300K images, to lay the foundation for creating an image-centric indoor navigation and exploration solution for inclusiveness. Every image is labelled with precise 6DoF camera poses, details of indoor PoIs, and descriptive captions to assist VIPs. We benchmark on two main aspects: 1) positioning system and 2) exploration support, prioritizing training scalability and real-time inference, to validate the prospect of image-based solution towards indoor navigation. The dataset, code, and model checkpoints are made publicly available at https://github.com/junfish/VIP_Navi.
The application of natural language processing on political texts as well as speeches has become increasingly relevant in political sciences due to the ability to analyze large text corpora which cannot be read by a single person. But such text corpora often lack critical meta information, detailing for instance the party, age or constituency of the speaker, that can be used to provide an analysis tailored to more fine-grained research questions. To enable researchers to answer such questions with quantitative approaches such as natural language processing, we provide the SpeakGer data set, consisting of German parliament debates from all 16 federal states of Germany as well as the German Bundestag from 1947-2023, split into a total of 10,806,105 speeches. This data set includes rich meta data in form of information on both reactions from the audience towards the speech as well as information about the speaker's party, their age, their constituency and their party's political alignment, which enables a deeper analysis. We further provide three exploratory analyses, detailing topic shares of different parties throughout time, a descriptive analysis of the development of the age of an average speaker as well as a sentiment analysis of speeches of different parties with regards to the COVID-19 pandemic.
We introduce ImmerseDiffusion, an end-to-end generative audio model that produces 3D immersive soundscapes conditioned on the spatial, temporal, and environmental conditions of sound objects. ImmerseDiffusion is trained to generate first-order ambisonics (FOA) audio, which is a conventional spatial audio format comprising four channels that can be rendered to multichannel spatial output. The proposed generative system is composed of a spatial audio codec that maps FOA audio to latent components, a latent diffusion model trained based on various user input types, namely, text prompts, spatial, temporal and environmental acoustic parameters, and optionally a spatial audio and text encoder trained in a Contrastive Language and Audio Pretraining (CLAP) style. We propose metrics to evaluate the quality and spatial adherence of the generated spatial audio. Finally, we assess the model performance in terms of generation quality and spatial conformance, comparing the two proposed modes: ``descriptive", which uses spatial text prompts) and ``parametric", which uses non-spatial text prompts and spatial parameters. Our evaluations demonstrate promising results that are consistent with the user conditions and reflect reliable spatial fidelity.
Current approaches for open-vocabulary scene graph generation (OVSGG) use vision-language models such as CLIP and follow a standard zero-shot pipeline -- computing similarity between the query image and the text embeddings for each category (i.e., text classifiers). In this work, we argue that the text classifiers adopted by existing OVSGG methods, i.e., category-/part-level prompts, are scene-agnostic as they remain unchanged across contexts. Using such fixed text classifiers not only struggles to model visual relations with high variance, but also falls short in adapting to distinct contexts. To plug these intrinsic shortcomings, we devise SDSGG, a scene-specific description based OVSGG framework where the weights of text classifiers are adaptively adjusted according to the visual content. In particular, to generate comprehensive and diverse descriptions oriented to the scene, an LLM is asked to play different roles (e.g., biologist and engineer) to analyze and discuss the descriptive features of a given scene from different views. Unlike previous efforts simply treating the generated descriptions as mutually equivalent text classifiers, SDSGG is equipped with an advanced renormalization mechanism to adjust the influence of each text classifier based on its relevance to the presented scene (this is what the term "specific" means). Furthermore, to capture the complicated interplay between subjects and objects, we propose a new lightweight module called mutual visual adapter. It refines CLIP's ability to recognize relations by learning an interaction-aware semantic space. Extensive experiments on prevalent benchmarks show that SDSGG outperforms top-leading methods by a clear margin.
The adoption of artificial intelligence (AI) in retail has significantly transformed the industry, enabling more personalized services and efficient operations. However, the rapid implementation of AI technologies raises ethical concerns, particularly regarding consumer privacy and fairness. This study aims to analyze the ethical challenges of AI applications in retail, explore ways retailers can implement AI technologies ethically while remaining competitive, and provide recommendations on ethical AI practices. A descriptive survey design was used to collect data from 300 respondents across major e-commerce platforms. Data were analyzed using descriptive statistics, including percentages and mean scores. Findings shows a high level of concerns among consumers regarding the amount of personal data collected by AI-driven retail applications, with many expressing a lack of trust in how their data is managed. Also, fairness is another major issue, as a majority believe AI systems do not treat consumers equally, raising concerns about algorithmic bias. It was also found that AI can enhance business competitiveness and efficiency without compromising ethical principles, such as data privacy and fairness. Data privacy and transparency were highlighted as critical areas where retailers need to focus their efforts, indicating a strong demand for stricter data protection protocols and ongoing scrutiny of AI systems. The study concludes that retailers must prioritize transparency, fairness, and data protection when deploying AI systems. The study recommends ensuring transparency in AI processes, conducting regular audits to address biases, incorporating consumer feedback in AI development, and emphasizing consumer data privacy.
Accurate short-term forecasts of passenger flow in metro systems under delay conditions are crucial for emergency response and service recovery, which pose significant challenges and are currently under-researched. Due to the rare occurrence of delay events, the limited sample size under delay condictions make it difficult for conventional models to effectively capture the complex impacts of delays on passenger flow, resulting in low forecasting accuracy. Recognizing the strengths of large language models (LLMs) in few-shot learning due to their powerful pre-training, contextual understanding, ability to perform zero-shot and few-shot reasoning, to address the issues that effectively generalize and adapt with minimal data, we propose a passenger flow forecasting framework under delay conditions that synthesizes an LLM with carefully designed prompt engineering. By Refining prompt design, we enable the LLM to understand delay event information and the pattern from historical passenger flow data, thus overcoming the challenges of passenger flow forecasting under delay conditions. The propmpt engineering in the framework consists of two main stages: systematic prompt generation and prompt refinement. In the prompt generation stage, multi-source data is transformed into descriptive texts understandable by the LLM and stored. In the prompt refinement stage, we employ the multidimensional Chain of Thought (CoT) method to refine the prompts. We verify the proposed framework by conducting experiments using real-world datasets specifically targeting passenger flow forecasting under delay conditions of Shenzhen metro in China. The experimental results demonstrate that the proposed model performs particularly well in forecasting passenger flow under delay conditions.
End-Stage Liver Disease (ESLD), a complex condition, has high rates of co-occurring comorbidities affecting multiple organ systems. There is no clear evidence-based practice (EBP) guidelines addressing the progression of comorbidities in ESLD patients awaiting liver transplantation (LT) and their impact on survival, both pre- and post-transplant. This study aimed to identify and quantify the trajectory of the most common and deteriorating comorbidities in ESLD patients awaiting LT and to analyze their effect on patient outcomes. An initial exploratory phase to identify frequent comorbidities in ESLD patients. Relevant EBP-driven data for diagnosing and measuring the progression of these conditions were collected and organized into five research matrices. In the quantitative phase, a retrospective analysis was conducted using longitudinal de-identified data from electronic health records (EHR) for patients who underwent LT between 2011-2021. Data included demographics, labs, procedures, and medications. Descriptive statistics and survival analysis assessed the association of comorbidities with post-transplant survival. The five most frequent comorbidities identified were Diabetes Mellitus (DM), Chronic Kidney Disease (CKD), Malnutrition, Portal Hypertension (PH), and Ascites. Of the 722 patients analyzed, 68.2% were male, mean age of 54.81 (SD = 11.24), and 19.8% died post-LT. Survival analysis showed a gradual decline over time, with the most significant drop at five years post-LT. Significant predictors of post-LT survival were age at transplant (p=0.01), waitlist time (p=0.004), DM at listing (p=0.02), low albumin (p=0.03), and CKD stage 5 development after listing (p=0.04). This study highlights the variability in diagnosing and measuring comorbidities in ESLD patients and provides insights into their progression and impact on post-LT survival.
This study introduces a prescriptive annotation benchmark grounded in humanities research to ensure consistent, unbiased labeling of offensive language, particularly for casual and non-mainstream language uses. We contribute two newly annotated datasets that achieve higher inter-annotator agreement between human and language model (LLM) annotations compared to original datasets based on descriptive instructions. Our experiments show that LLMs can serve as effective alternatives when professional annotators are unavailable. Moreover, smaller models fine-tuned on multi-source LLM-annotated data outperform models trained on larger, single-source human-annotated datasets. These findings highlight the value of structured guidelines in reducing subjective variability, maintaining performance with limited data, and embracing language diversity. Content Warning: This article only analyzes offensive language for academic purposes. Discretion is advised.