This data set belongs to the paper "Video-to-Model: Unsupervised Trace Extraction from Videos for Process Discovery and Conformance Checking in Manual Assembly", submitted on March 24, 2020, to the 18th International Conference on Business Process Management (BPM).
Abstract: Manual activities are often hidden deep down in discrete manufacturing processes. For the elicitation and optimization of process behavior, complete information about the execution of Manual activities are required. Thus, an approach is presented on how execution level information can be extracted from videos in manual assembly. The goal is the generation of a log that can be used in state-of-the-art process mining tools. The test bed for the system was lightweight and scalable consisting of an assembly workstation equipped with a single RGB camera recording only the hand movements of the worker from top. A neural network based real-time object classifier was trained to detect the worker’s hands. The hand detector delivers the input for an algorithm, which generates trajectories reflecting the movement paths of the hands. Those trajectories are automatically assigned to work steps using the position of material boxes on the assembly shelf as reference points and hierarchical clustering of similar behaviors with dynamic time warping. The system has been evaluated in a task-based study with ten participants in a laboratory, but under realistic conditions. The generated logs have been loaded into the process mining toolkit ProM to discover the underlying process model and to detect deviations from both, instructions and ground truth, using conformance checking. The results show that process mining delivers insights about the assembly process and the system’s precision.
The data set contains the generated and the annotated logs based on the video material gathered during the user study. In addition, the petri nets from the process discovery and conformance checking conducted with ProM (http://www.promtools.org) and the reference nets modeled with Yasper (http://www.yasper.org/) are provided.

Please cite the following paper when using this dataset: N. Thakur, V. Su, M. Shao, K. Patel, H. Jeong, V. Knieling, and A.Bian “A labelled dataset for sentiment analysis of videos on YouTube, TikTok, and other sources about the 2024 outbreak of measles,” arXiv [cs.CY], 2024. Available: http://arxiv.org/abs/2406.07693 Abstract This dataset contains the data of 4011 videos about the ongoing outbreak of measles published on 264 websites on the internet between January 1, 2024, and May 31, 2024. These websites primarily include YouTube and TikTok, which account for 48.6% and 15.2% of the videos, respectively. The remainder of the websites include Instagram and Facebook as well as the websites of various global and local news organizations. For each of these videos, the URL of the video, title of the post, description of the post, and the date of publication of the video are presented as separate attributes in the dataset. After developing this dataset, sentiment analysis (using VADER), subjectivity analysis (using TextBlob), and fine-grain sentiment analysis (using DistilRoBERTa-base) of the video titles and video descriptions were performed. This included classifying each video title and video description into (i) one of the sentiment classes i.e. positive, negative, or neutral, (ii) one of the subjectivity classes i.e. highly opinionated, neutral opinionated, or least opinionated, and (iii) one of the fine-grain sentiment classes i.e. fear, surprise, joy, sadness, anger, disgust, or neutral. These results are presented as separate attributes in the dataset for the training and testing of machine learning algorithms for performing sentiment analysis or subjectivity analysis in this field as well as for other applications. The paper associated with this dataset (please see the above-mentioned citation) also presents a list of open research questions that may be investigated using this dataset.

This data zip file consists of three different data sets using SAS format 1) Data of 105+ thousand adopters - 2 million and 795 thousand records 2) Data of 7+ thousand video game profiles 3) Data of 93+ thousand posts about video games Please unzip the file before using data. The data sets require at least 4 GB.

Video Lecture of Course Data Mining & Machine Learning by Prof Pedro Domingos, University of Washington USA.

The Media Memorability 2020 dataset contains a subset of short videos selected from the TRECVid 2019 Video-to-Text dataset. The dataset contains links to, as well as features describing and annotations on, 590videos as part of the training set and 410 videos as part of development set. It also contains links to, and features describing, 500 videos used as test videos for the MediaEval Video Memorability benchmark in 2020.

A dataset containing learning analytics data for the playback of learning materials in video format in different college courses in the STEM field, across a period of ten years. It can be used to test hypothesis and tools regarding the use of video in different learning environments, and should be of interest to the learning analytics and educational data mining communities. It can also be of help to teachers and other stakeholders in the educational process to take decisions based on learners actions when playing videos. It consists of data for 35 different videos, with a total of 40,453 sessions, and 313,724 records. The videos are accompanied by their timestamped transcription, both in the original language and their translation into English

The deep learning market, valued at $4.97 billion in 2025, is experiencing rapid expansion, projected to grow at a compound annual growth rate (CAGR) of 26.06% from 2025 to 2033. This robust growth is fueled by several key drivers. The increasing availability of large datasets and powerful computing resources, including specialized hardware like GPUs and TPUs, are enabling the development and deployment of increasingly sophisticated deep learning models. Furthermore, the rising adoption of deep learning across diverse applications, such as image and voice recognition, video surveillance and diagnostics, and data mining, is significantly contributing to market expansion. The demand for automation, improved accuracy in various tasks, and the ability to extract valuable insights from complex data are driving businesses across sectors to integrate deep learning solutions. Significant advancements in algorithmic efficiency and the emergence of novel architectures, such as transformer networks, are further accelerating market growth. Competition is intense, with major technology companies like Google, Amazon, Microsoft, and NVIDIA leading the charge, alongside specialized deep learning startups. However, challenges remain, including the need for skilled professionals to develop and maintain these systems, ethical concerns surrounding algorithmic bias, and the high computational costs associated with training complex models. The market segmentation reveals significant opportunities. The software segment currently dominates, driven by the development of user-friendly frameworks and libraries. However, the hardware segment is anticipated to witness significant growth, fueled by advancements in specialized processors and memory technologies designed to accelerate deep learning computations. Geographically, North America and Europe currently hold the largest market share due to established technological infrastructure and high adoption rates. However, the Asia-Pacific region is expected to experience substantial growth in the coming years, driven by increasing digitalization and government investments in AI technologies. The competitive landscape is characterized by a mix of established technology giants and innovative startups, leading to ongoing innovation and competitive pricing. This dynamic environment necessitates continuous adaptation and innovation to maintain market leadership. The forecast period (2025-2033) promises further consolidation and the emergence of new applications, driving the continued expansion of the deep learning market.

This video shows the community water pollution from mining exploration. The video is produced by indigenous people youths through the Civil Society Support Activity: cluster Anchor Grants funded by USAID through FHI360-CSS. The views expressed in this video are the indigenous youths’ alone and are not necessarily the views of the USAID, FHI360-CSS, ODC, and CIPL.

This repository contains all the data available for the publication:

Alex Falcon, Giuseppe Serra, and Oswald Lanz. Improving semantic video retrieval models by training with a relevance-aware online mining strategy. Computer Vision and Image Understanding. 2024.

Code is available at: https://github.com/aranciokov/ranp/

The data includes:

• pre-extracted features (ordered_feature_*.zip files)
• annotations, such as pre-extracted semantic graphs, glove checkpoints, class annotations, etc (annotations_*.zip files)
• train/val/test, when available, split information (public_split_*.zip) files
• pretrained models for HGR and EAO (details in the github repo)

Listing of specific actions recorded and qualified by video analysis.

This data was taken directly in the Toraja area using a digital camera, a minimum shooting distance of 3 m in video form, the results of the shooting are divided into frames

Sports Analytics Market size was valued at USD 1.15 Billion in 2024 and is projected to reach USD 8.23 Billion by 2031, growing at a CAGR of 30.70% from 2024 to 2031.

Sports Analytics Market: Definition/ Overview

Sports analytics involves the collection, analysis, and interpretation of data related to athletic performance, game strategies, and operational aspects of sports organizations. By utilizing statistical models and data mining techniques, sports analytics aims to enhance decision-making processes in various sports contexts.

Sports analytics involves the collection, analysis, and interpretation of data related to athletic performance, game strategies, and operational aspects of sports organizations. By utilizing statistical models and data mining techniques, sports analytics aims to enhance decision-making processes in various sports contexts.

In addition to this, the future of sports analytics is poised for significant growth with advancements in AI and machine learning. Enhanced predictive analytics will provide deeper insights into player health and performance. Additionally, the integration of wearable technology and real-time data analysis will revolutionize training and in-game strategy adjustments.

Frequent subgraph mining, i.e., the identification of relevant patterns in graph databases, is a well-known data mining problem with high practical relevance, since next to summarizing the data, the resulting patterns can also be used to define powerful domain-specific similarity functions for prediction. In recent years, significant progress has been made towards subgraph mining algorithms that scale to complex graphs by focusing on tree patterns and probabilistically allowing a small amount of incompleteness in the result. Nonetheless, the complexity of the pattern matching component used for deciding subtree isomorphism on arbitrary graphs has significantly limited the scalability of existing approaches. In this paper, we adapt sampling techniques from mathematical combinatorics to the problem of probabilistic subtree mining in arbitrary databases of many small to medium-size graphs or a single large graph. By restricting on tree patterns, we provide an algorithm that approximately counts or decides subtree isomorphism for arbitrary transaction graphs in sub-linear time with one-sided error. Our empirical evaluation on a range of benchmark graph datasets shows that the novel algorithm substantially outperforms state-of-the-art approaches both in the task of approximate counting of embeddings in single large graphs and in probabilistic frequent subtree mining in large databases of small to medium sized graphs.

Snapshot img

US Deep Learning Market Size 2025-2029

The deep learning market size in US is forecast to increase by USD 5.02 billion at a CAGR of 30.1% between 2024 and 2029.

The deep learning market is experiencing robust growth, driven by the increasing adoption of artificial intelligence (AI) in various industries for advanced solutioning. This trend is fueled by the availability of vast amounts of data, which is a key requirement for deep learning algorithms to function effectively. Industry-specific solutions are gaining traction, as businesses seek to leverage deep learning for specific use cases such as image and speech recognition, fraud detection, and predictive maintenance. Alongside, intuitive data visualization tools are simplifying complex neural network outputs, helping stakeholders understand and validate insights. 


However, challenges remain, including the need for powerful computing resources, data privacy concerns, and the high cost of implementing and maintaining deep learning systems. Despite these hurdles, the market's potential for innovation and disruption is immense, making it an exciting space for businesses to explore further. Semi-supervised learning, data labeling, and data cleaning facilitate efficient training of deep learning models. Cloud analytics is another significant trend, as companies seek to leverage cloud computing for cost savings and scalability. 

What will be the Size of the market During the Forecast Period?

Request Free Sample

Deep learning, a subset of machine learning, continues to shape industries by enabling advanced applications such as image and speech recognition, text generation, and pattern recognition. Reinforcement learning, a type of deep learning, gains traction, with deep reinforcement learning leading the charge. Anomaly detection, a crucial application of unsupervised learning, safeguards systems against security vulnerabilities. Ethical implications and fairness considerations are increasingly important in deep learning, with emphasis on explainable AI and model interpretability. Graph neural networks and attention mechanisms enhance data preprocessing for sequential data modeling and object detection. Time series forecasting and dataset creation further expand deep learning's reach, while privacy preservation and bias mitigation ensure responsible use.

In summary, deep learning's market dynamics reflect a constant pursuit of innovation, efficiency, and ethical considerations. The Deep Learning Market in the US is flourishing as organizations embrace intelligent systems powered by supervised learning and emerging self-supervised learning techniques. These methods refine predictive capabilities and reduce reliance on labeled data, boosting scalability. BFSI firms utilize AI image recognition for various applications, including personalizing customer communication, maintaining a competitive edge, and automating repetitive tasks to boost productivity. Sophisticated feature extraction algorithms now enable models to isolate patterns with high precision, particularly in applications such as image classification for healthcare, security, and retail.

How is this market segmented and which is the largest segment?

The market research report provides comprehensive data (region-wise segment analysis), with forecasts and estimates in 'USD million' for the period 2025-2029, as well as historical data from 2019-2023 for the following segments.

Application

  Image recognition
  Voice recognition
  Video surveillance and diagnostics
  Data mining


Type

  Software
  Services
  Hardware


End-user

  Security
  Automotive
  Healthcare
  Retail and commerce
  Others


Geography

  North America

    US

By Application Insights

The Image recognition segment is estimated to witness significant growth during the forecast period. In the realm of artificial intelligence (AI) and machine learning, image recognition, a subset of computer vision, is gaining significant traction. This technology utilizes neural networks, deep learning models, and various machine learning algorithms to decipher visual data from images and videos. Image recognition is instrumental in numerous applications, including visual search, product recommendations, and inventory management. Consumers can take photographs of products to discover similar items, enhancing the online shopping experience. In the automotive sector, image recognition is indispensable for advanced driver assistance systems (ADAS) and autonomous vehicles, enabling the identification of pedestrians, other vehicles, road signs, and lane markings.

Furthermore, image recognition plays a pivotal role in augmented reality (AR) and virtual reality (VR) applications, where it tracks physical objects and overlays digital content onto real-world scenarios. The model training process involves the backpropagation algorithm, which calculates

Volunteered geographic information and citizen science have advanced academic and public understanding of geographical and ecological processes. Videos hosted online represent a large data source that could potentially provide meaningful results for studies in physical geography—a concept we term volunteered geographic videos (VGV). Technological advances in image-capturing devices, computing, and image processing have resulted in increasingly sophisticated methods that treat imagery as raw data, such as resolving high-resolution topography with structure from motion or the calculation of surface flow velocity in rivers with particle image velocimetry. The ubiquitous nature of recording devices and citizens who share imagery online have resulted in a vast archive of potentially useful online videos. This article analyzes the potential for using YouTube videos for research in physical geography. We discuss the combination of suitability and availability that has made this possible and emphasize the distinction between moderately suitable imagery that can directly answer research questions and lower suitability imagery that can indirectly support a study. We present example case studies that address (1) initial considerations of using VGV, (2) topographic data extraction from a video taken after a landslide, and (3) data extraction from a video of a flash flood that could support a study of extreme floods and wood transport. Finally, we discuss both the benefits and complicating factors associated with VGV. The results indicate that VGV could be used to support certain studies in physical geography and that this large repository of raw data has been underutilized.

Social media in general provide great opportunities for mining massive amounts of text, image, and video-based data. However, what questions can be addressed from analyzing such data? In this review, we are focusing on microblogging services and discuss applications of streaming data from the scientific literature. We will focus on text-based approaches because they represent by far the largest cohort of studies and we present a taxonomy of studied problems.

Borehole Video Camera Market Outlook

The global borehole video camera market size was valued at USD 450 million in 2023 and is projected to reach USD 720 million by 2032, exhibiting a CAGR of 5.5% during the forecast period. The market growth is primarily driven by the increasing demand for groundwater and oil exploration, coupled with advancements in camera technology that offer enhanced resolution and durability.

One of the significant growth factors in the borehole video camera market is the rising necessity for efficient groundwater management. The escalating global population and the consequent increase in water consumption have put enormous pressure on existing water resources. Borehole video cameras enable precise monitoring and assessment of water wells, ensuring sustainable groundwater management. Moreover, governmental regulations mandating the periodic inspection of water wells to ensure water safety and quality are further propelling market growth.

The oil and gas industry presents another substantial growth driver for the borehole video camera market. Enhanced oil recovery techniques and the need for detailed subsurface data have necessitated the adoption of advanced borehole video cameras. These cameras provide critical visual insights that aid in the identification of potential issues within boreholes, leading to improved maintenance and operational efficiency. As oil and gas exploration activities continue to surge globally, the demand for high-quality borehole video cameras is expected to rise correspondingly.

In the mining industry, borehole video cameras are increasingly being utilized for ore body characterization and mine safety inspections. These cameras offer valuable visual data that helps in making informed decisions regarding mining operations. The growing emphasis on worker safety and stringent mining regulations are compelling mining companies to adopt borehole video cameras for regular inspections and monitoring. This trend is anticipated to contribute significantly to the market's expansion over the forecast period.

The integration of specialized equipment such as the Push Rod Camera has revolutionized the inspection process in borehole video camera applications. These cameras are particularly advantageous in scenarios where maneuverability and access to confined spaces are critical. The compact and flexible design of Push Rod Cameras allows for detailed inspections in challenging environments, providing clear and precise visual data. This capability is essential for identifying potential issues and ensuring the integrity of boreholes, especially in industries like oil and gas where precision is paramount. As the demand for efficient and reliable inspection tools grows, the role of Push Rod Cameras in enhancing operational efficiency and safety continues to expand.

Regionally, North America is expected to dominate the borehole video camera market owing to the presence of extensive groundwater extraction activities, particularly in the United States and Canada. Additionally, the substantial investments in oil and gas exploration in this region are likely to drive market growth. On the other hand, the Asia Pacific region is projected to exhibit the highest growth rate due to the increasing demand for water resources and rapid industrialization in countries like China and India.

Product Type Analysis

The borehole video camera market is segmented by product type into portable and non-portable borehole video cameras. Portable borehole video cameras are compact, lightweight devices designed for ease of transport and operation. They are particularly favored in remote and difficult-to-access locations, making them ideal for field inspections and temporary monitoring projects. The rising adoption of portable devices in various industries, including environmental studies and residential applications, is expected to drive the growth of this segment.

Non-portable borehole video cameras, meanwhile, are typically more robust and offer higher resolution and durability. These cameras are often used in more permanent installations where detailed, long-term monitoring is required. Industries such as oil and gas and mining, which demand high precision and reliability, are the primary users of non-portable borehole video cameras. The advanced technological features and higher investment in infrastructure in these sectors are anticipated to propel the market for non-portable cameras.</p

The challenges in investigating the situational clutter are sourced from its complicated constitution of different contributors (e.g., vehicle, other road users, the road infrastructures, etc.) and its dynamically changing manner (e.g., dashboard display, traffic conditions and outlooks of the vehicles, dynamic road, and roadside landscapes, etc.). Although the psychology and cognitive science communities have investigated the situational visual clutter, there lacks effort in studying it in the driving context. The proposed study aims to bridge such a gap. The objective of this study is threefold: 1) to develop a new video analysis model that can quantify the complex and dynamic driving scene; 2) to employ the developed model to quantify the impact of the situational visual clutter on driving performance, and 3) to demonstrate the potential of employing the driving scene quantification to support other retrospective studies and data mining using the existing driving simulation data.

The global borehole video camera market is experiencing robust growth, driven by increasing demand across diverse sectors like engineering geology, hydrogeology, and mining. The market size in 2025 is estimated at $150 million, exhibiting a Compound Annual Growth Rate (CAGR) of 7% from 2025 to 2033. This growth is fueled by several key factors. Firstly, advancements in camera technology, including higher resolution imaging and improved durability, are enhancing the efficiency and reliability of subsurface inspections. Secondly, the rising need for precise geological data in infrastructure projects, coupled with stringent safety regulations, is driving the adoption of borehole video cameras for comprehensive site assessments. Finally, the exploration and expansion of mining operations globally are significantly contributing to the market's expansion, as these activities necessitate detailed subsurface imaging for resource identification and safety monitoring. The dual-camera segment currently holds a significant market share due to its ability to provide broader visual coverage and enhanced data acquisition capabilities. Looking ahead, several trends are expected to shape the market's trajectory. The integration of advanced analytics and AI capabilities in borehole video camera systems will enable automated data interpretation and enhanced efficiency. Furthermore, the growing adoption of remotely operated vehicles (ROVs) and drones for subsurface inspections will create new opportunities for specialized borehole camera systems. However, potential restraints include the high initial investment costs associated with acquiring sophisticated equipment and the need for specialized personnel to operate and interpret the data. Geographic expansion, particularly in emerging economies with significant infrastructure development projects, presents significant growth opportunities. North America and Europe are currently the largest markets, but Asia-Pacific is projected to witness the fastest growth in the coming years due to robust infrastructure investments and mining activities. This report provides a detailed analysis of the global borehole video camera market, projected to be worth over $2.5 billion by 2030. We delve into market concentration, key trends, dominant segments, and future growth catalysts, offering valuable insights for industry stakeholders. This in-depth study covers crucial aspects of the borehole video camera market, including production, application, and technological advancements, empowering businesses to make informed strategic decisions.

Graphics Card (Video Card) Market Outlook

The global graphics card (video card) market size was valued at approximately USD 25 billion in 2023 and is projected to reach around USD 50 billion by 2032, growing at a compound annual growth rate (CAGR) of 8.1% during the forecast period. This substantial growth is primarily driven by increasing demand in gaming, rising adoption in data centers, and the growing influence of cryptocurrency mining activities.

The escalating demand for immersive gaming experiences is one of the primary factors fueling the expansion of the graphics card market. Gamers are continuously seeking high-performance video cards to achieve superior graphics and smoother gameplay. The rapid advancements in gaming technologies, such as virtual reality (VR) and augmented reality (AR), are also propelling market growth. As VR and AR applications become more mainstream, the need for advanced graphics cards capable of rendering high-quality visuals in real-time is surging. Furthermore, the rise of esports and the growing popularity of live streaming platforms are contributing to the heightened demand for high-end gaming graphics cards.

Another significant growth factor is the increasing utilization of graphics cards in professional visualization and data centers. Industries such as media and entertainment, architecture, engineering, and construction are leveraging graphics cards for tasks that require high computational power, including 3D rendering, video editing, and complex simulations. Moreover, data centers are adopting powerful graphics processing units (GPUs) to accelerate performance in applications such as artificial intelligence (AI), machine learning (ML), and big data analytics. The ability of GPUs to handle parallel processing tasks more efficiently than traditional central processing units (CPUs) makes them indispensable in modern data-driven operations.

Cryptocurrency mining has emerged as a pivotal driver for the graphics card market. Mining cryptocurrencies like Bitcoin and Ethereum requires extensive computational power, leading miners to invest heavily in high-performance GPUs. Despite regulatory uncertainties and market volatility, the profitability of cryptocurrency mining continues to attract investments in advanced graphics cards. This trend is likely to sustain as blockchain technology evolves and new digital currencies are introduced, driving further demand for robust GPU solutions.

In the realm of high-performance computing, the introduction of Multi Fan Graphics Card technology has marked a significant advancement. These graphics cards are designed with multiple fans to enhance cooling efficiency, which is crucial for maintaining optimal performance during intensive tasks such as gaming, professional visualization, and cryptocurrency mining. The multi-fan setup not only helps in dissipating heat more effectively but also allows the graphics card to operate at higher clock speeds without the risk of overheating. This innovation is particularly beneficial for gamers and professionals who demand sustained performance over extended periods. As the demand for high-end graphics solutions continues to rise, Multi Fan Graphics Cards are becoming increasingly popular among users who seek both performance and reliability.

From a regional perspective, the Asia Pacific is expected to dominate the graphics card market during the forecast period. This region's growth can be attributed to the presence of key manufacturers, the burgeoning gaming industry, and the increasing adoption of advanced technologies across various sectors. North America follows closely, driven by technological advancements, high disposable incomes, and a robust gaming community. Europe is also witnessing growth, supported by the proliferation of data centers and increasing investments in AI and ML technologies. Latin America and the Middle East & Africa are anticipated to experience moderate growth, propelled by expanding digital infrastructure and rising interest in gaming and professional applications.

Product Type Analysis

The graphics card market is broadly segmented into discrete graphics cards and integrated graphics cards. Discrete graphics cards are standalone units that provide superior performance compared to integrated graphics solutions. These cards are predominantly used by gamers, professional content creators, and cryptocurrency miners who require high computational power. The increasing demand for high-definition games and