Conventional human activity recognition (HAR) relies on classifiers trained to predict discrete activity classes, inherently limiting recognition to activities explicitly present in the training set. Such classifiers would invariably fail, putting zero likelihood, when encountering unseen activities. We propose Open Vocabulary HAR (OV-HAR), a framework that overcomes this limitation by first converting each activity into natural language and breaking it into a sequence of elementary motions. This descriptive text is then encoded into a fixed-size embedding. The model is trained to regress this embedding, which is subsequently decoded back into natural language using a pre-trained embedding inversion model. Unlike other works that rely on auto-regressive large language models (LLMs) at their core, OV-HAR achieves open vocabulary recognition without the computational overhead of such models. The generated text can be transformed into a single activity class using LLM prompt engineering. We have evaluated our approach on different modalities, including vision (pose), IMU, and pressure sensors, demonstrating robust generalization across unseen activities and modalities, offering a fundamentally different paradigm from contemporary classifiers.
The aim of this study is to assess the impact of information technology (IT) on university graduates in terms of employment development, which will aid in economic issues. This study uses a descriptive research methodology and a quantitative approach to understand variables. The focus of this study is to ascertain how graduates of Kurdistan regional universities might use IT to secure employment and significantly contribute to the nation's economic revival. The sample size was established by the use of judgmental sampling procedure and consisted of 314 people. The researcher prepared the questionnaire to collect data, and then SPSS statistical software, version 22, and Excel 2010 were used to modify, compile, and tabulate the results. The study's outcome showed that information technology is incredibly inventive, has a promising future, and makes life much easier for everyone. It also proved that a deep academic understanding of information technology and its constituent parts helps graduates of Kurdistan Regional University find suitable careers. More importantly, though, anyone looking for work or a means of support will find great benefit from possessing credentials and understanding of IT. The study's final finding was that information technology has actively advanced the country's economy. Not only is IT helping to boost youth employment, but it is also turning into a worthwhile investment for economic growth.
Vision-Language Models (VLMs) have shown strong performance in understanding single images, aided by numerous high-quality instruction datasets. However, multi-image reasoning tasks are still under-explored in the open-source community due to two main challenges: (1) scaling datasets with multiple correlated images and complex reasoning instructions is resource-intensive and maintaining quality is difficult, and (2) there is a lack of robust evaluation benchmarks for multi-image tasks. To address these issues, we introduce SMIR, an efficient synthetic data-generation pipeline for multi-image reasoning, and a high-quality dataset generated using this pipeline. Our pipeline efficiently extracts highly correlated images using multimodal embeddings, combining visual and descriptive information and leverages open-source LLMs to generate quality instructions. Using this pipeline, we generated 160K synthetic training samples, offering a cost-effective alternative to expensive closed-source solutions. Additionally, we present SMIR-BENCH, a novel multi-image reasoning evaluation benchmark comprising 200 diverse examples across 7 complex multi-image reasoning tasks. SMIR-BENCH is multi-turn and utilizes a VLM judge to evaluate free-form responses, providing a comprehensive assessment of model expressiveness and reasoning capability across modalities. We demonstrate the effectiveness of SMIR dataset by fine-tuning several open-source VLMs and evaluating their performance on SMIR-BENCH. Our results show that models trained on our dataset outperform baseline models in multi-image reasoning tasks up to 8% with a much more scalable data pipeline.
Visual Question Answering (VQA) is an evolving research field aimed at enabling machines to answer questions about visual content by integrating image and language processing techniques such as feature extraction, object detection, text embedding, natural language understanding, and language generation. With the growth of multimodal data research, VQA has gained significant attention due to its broad applications, including interactive educational tools, medical image diagnosis, customer service, entertainment, and social media captioning. Additionally, VQA plays a vital role in assisting visually impaired individuals by generating descriptive content from images. This survey introduces a taxonomy of VQA architectures, categorizing them based on design choices and key components to facilitate comparative analysis and evaluation. We review major VQA approaches, focusing on deep learning-based methods, and explore the emerging field of Large Visual Language Models (LVLMs) that have demonstrated success in multimodal tasks like VQA. The paper further examines available datasets and evaluation metrics essential for measuring VQA system performance, followed by an exploration of real-world VQA applications. Finally, we highlight ongoing challenges and future directions in VQA research, presenting open questions and potential areas for further development. This survey serves as a comprehensive resource for researchers and practitioners interested in the latest advancements and future
Having a sufficient quantity of quality data is a critical enabler of training effective machine learning models. Being able to effectively determine the adequacy of a dataset prior to training and evaluating a model's performance would be an essential tool for anyone engaged in experimental design or data collection. However, despite the need for it, the ability to prospectively assess data sufficiency remains an elusive capability. We report here on two experiments undertaken in an attempt to better ascertain whether or not basic descriptive statistical measures can be indicative of how effective a dataset will be at training a resulting model. Leveraging the effect size of our features, this work first explores whether or not a correlation exists between effect size, and resulting model performance (theorizing that the magnitude of the distinction between classes could correlate to a classifier's resulting success). We then explore whether or not the magnitude of the effect size will impact the rate of convergence of our learning rate, (theorizing again that a greater effect size may indicate that the model will converge more rapidly, and with a smaller sample size needed). Our results appear to indicate that this is not an effective heuristic for determining adequate sample size or projecting model performance, and therefore that additional work is still needed to better prospectively assess adequacy of data.
The automatic generation of representative natural language descriptions for observable patterns in time series data enhances interpretability, simplifies analysis and increases cross-domain utility of temporal data. While pre-trained foundation models have made considerable progress in natural language processing (NLP) and computer vision (CV), their application to time series analysis has been hindered by data scarcity. Although several large language model (LLM)-based methods have been proposed for time series forecasting, time series captioning is under-explored in the context of LLMs. In this paper, we introduce TSLM, a novel time series language model designed specifically for time series captioning. TSLM operates as an encoder-decoder model, leveraging both text prompts and time series data representations to capture subtle temporal patterns across multiple phases and generate precise textual descriptions of time series inputs. TSLM addresses the data scarcity problem in time series captioning by first leveraging an in-context prompting synthetic data generation, and second denoising the generated data via a novel cross-modal dense retrieval scoring applied to time series-caption pairs. Experimental findings on various time series captioning datasets demonstrate that TSLM outperforms existing state-of-the-art approaches from multiple data modalities by a significant margin.
Objetive: In the care of renal patients, prioritising their quality of life and nursing care is essential. Research links patients' perceptions of care quality to improved outcomes such as safety, clinical efficacy, treatment adherence, and preventive practices. This study aimed to evaluate the quality of life and care perception in these patients and explore potential associations between these dimensions. Material and methods: A cross-sectional descriptive study was conducted with 43 patients attending an advanced CKD clinic. Quality of life was assessed using the KDQOL-36 questionnaire, while the IECPAX questionnaire measured perceived care quality. Sociodemographic and clinical data were collected from patient records. Participants completed the questionnaires during routine visits, with scores analysed to identify associations between variables. Results: The study included 60% men (n=28) and 32% women (n=15), with a mean age of 78 years . Among participants, 45% were diabetic, 79% hypertensive, and 58% took more than five medications daily. Mean scores were 78.76 for KDQOL-36 and 5.54 for IECPAX. Significant differences were found in the physical role domain between men and women (p=0.01) and for individuals over 65 years (p=0.04). Higher IECPAX scores were associated with taking more than five medications (p=0.05). However, no correlation was observed between KDQOL-36 and IECPAX scores. Conclusions: The findings suggest that quality of life and perceived care quality are independent in advanced CKD patients. While this study provides insights, larger multicentre studies are needed to validate these results. These findings highlight the importance of addressing both aspects separately to improve outcomes in this population.
The exponential growth of data and advancements in big data technologies have created a demand for more efficient and automated approaches to data analysis and storytelling. However, automated data analysis systems still face challenges in leveraging large language models (LLMs) for data insight discovery, augmented analysis, and data storytelling. This paper introduces the Multidimensional Data Storytelling Framework (MDSF) based on large language models for automated insight generation and context-aware storytelling. The framework incorporates advanced preprocessing techniques, augmented analysis algorithms, and a unique scoring mechanism to identify and prioritize actionable insights. The use of fine-tuned LLMs enhances contextual understanding and generates narratives with minimal manual intervention. The architecture also includes an agent-based mechanism for real-time storytelling continuation control. Key findings reveal that MDSF outperforms existing methods across various datasets in terms of insight ranking accuracy, descriptive quality, and narrative coherence. The experimental evaluation demonstrates MDSF's ability to automate complex analytical tasks, reduce interpretive biases, and improve user satisfaction. User studies further underscore its practical utility in enhancing content structure, conclusion extraction, and richness of detail.
Digital accessibility is a cornerstone of inclusive content delivery, yet many EPUB files fail to meet fundamental accessibility standards, particularly in providing descriptive alt text for images. Alt text plays a critical role in enabling visually impaired users to understand visual content through assistive technologies. However, generating high-quality alt text at scale is a resource-intensive process, creating significant challenges for organizations aiming to ensure accessibility compliance. This paper introduces AltGen, a novel AI-driven pipeline designed to automate the generation of alt text for images in EPUB files. By integrating state-of-the-art generative models, including advanced transformer-based architectures, AltGen achieves contextually relevant and linguistically coherent alt text descriptions. The pipeline encompasses multiple stages, starting with data preprocessing to extract and prepare relevant content, followed by visual analysis using computer vision models such as CLIP and ViT. The extracted visual features are enriched with contextual information from surrounding text, enabling the fine-tuned language models to generate descriptive and accurate alt text. Validation of the generated output employs both quantitative metrics, such as cosine similarity and BLEU scores, and qualitative feedback from visually impaired users. Experimental results demonstrate the efficacy of AltGen across diverse datasets, achieving a 97.5% reduction in accessibility errors and high scores in similarity and linguistic fidelity metrics. User studies highlight the practical impact of AltGen, with participants reporting significant improvements in document usability and comprehension. Furthermore, comparative analyses reveal that AltGen outperforms existing approaches in terms of accuracy, relevance, and scalability.
Many studies have revealed that sentence comprehension relies more on semantic processing than on syntactic processing. However, previous studies have predominantly emphasized the preference for semantic processing, focusing on the semantic perspective. In contrast, this current study highlights the under-utilization of syntactic processing, from a syntactic perspective. Based on the traditional garden-path experiment, which involves locally ambiguous but globally unambiguous sentences, this study's empirical experiment innovatively crafted an adapted version featuring semantically ambiguous but syntactically unambiguous sentences to meet its specific research objective. This experiment, involving 140 subjects, demonstrates through descriptive and inferential statistical analyses using SPSS, Graph Pad Prism, and Cursor that Chinese learners of English tend to under-utilize syntactic processing when comprehending English sentences. The study identifies two types of parsing under-utilization: partial and complete. Further exploration reveals that trial and error in syntactic processing contributes to both. Consequently, this study lays a foundation for the development of a novel parsing method designed to fully integrate syntactic processing into sentence comprehension, thereby enhancing the level of English sentence comprehension for Chinese learners of English.
Deep learning models (DLMs) achieve increasingly high performance both on structured and unstructured data. They significantly extended applicability of machine learning to various domains. Their success in making predictions, detecting patterns and generating new data made significant impact on science and industry. Despite these accomplishments, DLMs are difficult to explain because of their enormous size. In this work, we propose a novel framework for post-hoc explaining and relating DLMs using redescriptions. The framework allows cohort analysis of arbitrary DLMs by identifying statistically significant redescriptions of neuron activations. It allows coupling neurons to a set of target labels or sets of descriptive attributes, relating layers within a single DLM or associating different DLMs. The proposed framework is independent of the artificial neural network architecture and can work with more complex target labels (e.g. multi-label or multi-target scenario). Additionally, it can emulate both pedagogical and decompositional approach to rule extraction. The aforementioned properties of the proposed framework can increase explainability and interpretability of arbitrary DLMs by providing different information compared to existing explainable-AI approaches.
Audio-language models (ALMs) excel in zero-shot audio classification, a task where models classify previously unseen audio clips at test time by leveraging descriptive natural language prompts. We introduce TSPE (Task-Specific Prompt Ensemble), a simple, training-free hard prompting method that boosts ALEs' zero-shot performance by customizing prompts for diverse audio classification tasks. Rather than using generic template-based prompts like "Sound of a car" we generate context-rich prompts, such as "Sound of a car coming from a tunnel". Specifically, we leverage label information to identify suitable sound attributes, such as "loud" and "feeble", and appropriate sound sources, such as "tunnel" and "street" and incorporate this information into the prompts used by Audio-Language Models (ALMs) for audio classification. Further, to enhance audio-text alignment, we perform prompt ensemble across TSPE-generated task-specific prompts. When evaluated on 12 diverse audio classification datasets, TSPE improves performance across ALMs by showing an absolute improvement of 1.23-16.36% over vanilla zero-shot evaluation.
In text-to-image (T2I) generation, a prevalent training technique involves utilizing Vision Language Models (VLMs) for image re-captioning. Even though VLMs are known to exhibit hallucination, generating descriptive content that deviates from the visual reality, the ramifications of such caption hallucinations on T2I generation performance remain under-explored. Through our empirical investigation, we first establish a comprehensive dataset comprising VLM-generated captions, and then systematically analyze how caption hallucination influences generation outcomes. Our findings reveal that (1) the disparities in caption quality persistently impact model outputs during fine-tuning. (2) VLMs confidence scores serve as reliable indicators for detecting and characterizing noise-related patterns in the data distribution. (3) even subtle variations in caption fidelity have significant effects on the quality of learned representations. These findings collectively emphasize the profound impact of caption quality on model performance and highlight the need for more sophisticated robust training algorithm in T2I. In response to these observations, we propose a approach leveraging VLM confidence score to mitigate caption noise, thereby enhancing the robustness of T2I models against hallucination in caption.
This paper presents a Multi-Agent Norm Perception and Induction Learning Model aimed at facilitating the integration of autonomous agent systems into distributed healthcare environments through dynamic interaction processes. The nature of the medical norm system and its sharing channels necessitates distinct approaches for Multi-Agent Systems to learn two types of norms. Building on this foundation, the model enables agents to simultaneously learn descriptive norms, which capture collective tendencies, and prescriptive norms, which dictate ideal behaviors. Through parameterized mixed probability density models and practice-enhanced Markov games, the multi-agent system perceives descriptive norms in dynamic interactions and captures emergent prescriptive norms. We conducted experiments using a dataset from a neurological medical center spanning from 2016 to 2020.
TalkWithMachines aims to enhance human-robot interaction by contributing to interpretable industrial robotic systems, especially for safety-critical applications. The presented paper investigates recent advancements in Large Language Models (LLMs) and Vision Language Models (VLMs), in combination with robotic perception and control. This integration allows robots to understand and execute commands given in natural language and to perceive their environment through visual and/or descriptive inputs. Moreover, translating the LLM's internal states and reasoning into text that humans can easily understand ensures that operators gain a clearer insight into the robot's current state and intentions, which is essential for effective and safe operation. Our paper outlines four LLM-assisted simulated robotic control workflows, which explore (i) low-level control, (ii) the generation of language-based feedback that describes the robot's internal states, (iii) the use of visual information as additional input, and (iv) the use of robot structure information for generating task plans and feedback, taking the robot's physical capabilities and limitations into account. The proposed concepts are presented in a set of experiments, along with a brief discussion. Project description, videos, and supplementary materials will be available on the project website: https://talk-machines.github.io.
This paper provides a comprehensive, descriptive overview of the current state of digital transformation in the Swiss economy and delineates areas that businesses should keep an eye on. Key findings illustrate that even established technologies are not universally adopted, that companies tend to overestimate their technological status compared to their competitors, and that it is important to have the appropriate technological know-how when introducing new technologies. In addition, companies expect changes in their work processes and employment conditions in connection with the digital transformation. Specifically, work tasks are expected to become more complex, diverse and varied. Employees' knowledge acquisition will gain in importance, especially in the form of formal further training and self-learning. Employees will also be more autonomous in making decisions about their jobs and working hours.
Training Large Multimodality Models (LMMs) relies on descriptive image caption that connects image and language. Existing methods either distill the caption from the LMM models or construct the captions from the internet images or by human. We propose to leverage off-the-shelf visual specialists, which were trained from annotated images initially not for image captioning, for enhancing the image caption. Our approach, named DCE, explores object low-level and fine-grained attributes (e.g., depth, emotion and fine-grained categories) and object relations (e.g., relative location and human-object-interaction (HOI)), and combine the attributes into the descriptive caption. Experiments demonstrate that such visual specialists are able to improve the performance for visual understanding tasks as well as reasoning that benefits from more accurate visual understanding. We will release the source code and the pipeline so that other visual specialists are easily combined into the pipeline. The complete source code of DCE pipeline and datasets will be available at \url{https://github.com/syp2ysy/DCE}.
Using novel establishment-level observational data from Switzerland, we empirically examine whether the usage of key technologies of Industry 4.0 distinguishes across firms with different types of organizational culture. Based on the Technology-Organization-Environment and the Competing Values framework, we hypothesize that the developmental culture has the greatest potential to promote the usage of Industry 4.0 technologies. We also hypothesize that companies with a hierarchical or rational culture are especially likely to make use of automation technologies, such as AI and robotics. By means of descriptive statistics and multiple regression analysis, we find empirical support for our first hypothesis, while we cannot con-firm our second hypothesis. Our empirical results provide important implications for managerial decision-makers. Specifically, the link between organizational culture and the implementation of Industry 4.0 technologies is relevant for managers, as this knowledge helps them to cope with digital transformation in turbulent times and keep their businesses competitive.
In this study, we define and tackle zero shot "real" classification by description, a novel task that evaluates the ability of Vision-Language Models (VLMs) like CLIP to classify objects based solely on descriptive attributes, excluding object class names. This approach highlights the current limitations of VLMs in understanding intricate object descriptions, pushing these models beyond mere object recognition. To facilitate this exploration, we introduce a new challenge and release description data for six popular fine-grained benchmarks, which omit object names to encourage genuine zero-shot learning within the research community. Additionally, we propose a method to enhance CLIP's attribute detection capabilities through targeted training using ImageNet21k's diverse object categories, paired with rich attribute descriptions generated by large language models. Furthermore, we introduce a modified CLIP architecture that leverages multiple resolutions to improve the detection of fine-grained part attributes. Through these efforts, we broaden the understanding of part-attribute recognition in CLIP, improving its performance in fine-grained classification tasks across six popular benchmarks, as well as in the PACO dataset, a widely used benchmark for object-attribute recognition. Code is available at: https://github.com/ethanbar11/grounding_ge_public.
Video Action Detection (VAD) entails localizing and categorizing action instances within videos, which inherently consist of diverse information sources such as audio, visual cues, and surrounding scene contexts. Leveraging this multi-modal information effectively for VAD poses a significant challenge, as the model must identify action-relevant cues with precision. In this study, we introduce a novel multi-modal VAD architecture, referred to as the Joint Actor-centric Visual, Audio, Language Encoder (JoVALE). JoVALE is the first VAD method to integrate audio and visual features with scene descriptive context sourced from large-capacity image captioning models. At the heart of JoVALE is the actor-centric aggregation of audio, visual, and scene descriptive information, enabling adaptive integration of crucial features for recognizing each actor's actions. We have developed a Transformer-based architecture, the Actor-centric Multi-modal Fusion Network, specifically designed to capture the dynamic interactions among actors and their multi-modal contexts. Our evaluation on three prominent VAD benchmarks, including AVA, UCF101-24, and JHMDB51-21, demonstrates that incorporating multi-modal information significantly enhances performance, setting new state-of-the-art performances in the field.