Action Detection aims to find both where and when an action occurs within a video clip and classify what the action is taking place. Typically results are given in the form of action tublets, which are action bounding boxes linked across time in the video. This is related to temporal localization, which seeks to identify the start and end frame of an action, and action recognition, which seeks only to classify which action is taking place and typically assumes a trimmed video.
데이터셋
출처에 같은 태스크 이름으로 연결된 데이터셋입니다. 동명 태스크가 포함될 수 있으므로, 비교할 때는 평가 결과의 조건도 확인하세요.
HASCD (Human Activity Segmentation Challenge Dataset) contains 250 annotated multivariate time series capturing 10.7 h of real-world human motion smartphone sensor data from 15 bachelor computer science students. The recordings capture 6 distinct human motion sequences designed to represent pervasive behaviour in realistic indoor and outdoor settings. The data set serves as a benchmark for evaluating machine learning workflows.
IM-SportingBehaviors Dataset ## Dataset Overview The IM-SportingBehaviors dataset, developed by researchers at Air University Pakistan, provides detailed motion data from participants engaged in various sports activities. This dataset captures human movement through triaxial accelerometers attached to multiple parts of the body, specifically the knee, wrist, and below-neck areas. The dataset includes motion data from six sports: cycling, badminton, skipping, basketball, football, and table tennis, with participants comprising both professional and amateur athletes aged between 20 and 30 years, weighing between 60 and 100 kilograms. ## Dataset Characteristics - Total Samples: 62,500 - Sports Activities: Cycling, badminton, skipping, basketball, football, and table tennis - Data Imbalance: The dataset is imbalanced, with the ‘Skipping’ class as the most represented (22.4%) and ‘Football’ as the least represented (12.3%). - Sensors Used: Triaxial accelerometers providing 9-dimensional data from three sensor placements; however, only 6-dimensional data is utilized in analyses, corresponding to two accelerometers. - Data Distribution: - Skipping: 22.4% - Cycling: 19% - Table Tennis: 16.8% - Badminton: 16% - Basketball: 13.4% - Football: 12.3% ## Motivation and Summary of Content The IM-SportingBehaviors dataset aims to enhance the understanding of human mobility patterns and biomechanics across a range of sports. By collecting and analyzing motion data through wearable accelerometers, researchers can gain insights into activity-specific movement dynamics and variability in performance between professional and amateur athletes. This dataset's detailed sensor data captures essential aspects of motion and posture, which are crucial for applications in sports science, human-computer interaction, and motion analysis. ## Potential Use Cases The IM-SportingBehaviors dataset is valuable for: 1. Activity Recognition: Developing and validating algorithms to classify sports activities based on sensor data. 2. Performance Analysis: Analyzing movement efficiency and style differences between professional and amateur athletes. 3. Biomechanics Research: Studying human movement patterns, energy expenditure, and motion efficiency in various sports. 4. Wearable Device Optimization: Improving the accuracy of wearable fitness trackers in recognizing and categorizing sports-specific movements. 5. Injury Prevention: Identifying movement patterns or deviations that could contribute to sports-related injuries. This dataset provides a robust foundation for advancing both theoretical and applied research in fields that depend on accurate motion and activity classification.
The LIRIS human activities dataset contains (gray/rgb/depth) videos showing people performing various activities taken from daily life (discussing, telphone calls, giving an item etc.). The dataset is fully annotated, where the annotation not only contains information on the action class but also its spatial and temporal positions in the video. It was originally shot for the ICPR-HARL 2012 competition. The dataset has been shot with two different cameras: Subset D1 has been shot with a MS Kinect module mounted on a remotely controlled Wany robotics Pekee II mobile robot which is part of the LIRIS-VOIR platform. Subset D2 has been shot with a sony consumer camcorder
Metaphorics is a newly introduced non-contextual skeleton action dataset. All the datasets introduced so far in the skeleton human action recognition have categories based only on verb-based actions. Source: Metaphorics
MOSAD (Mobile Sensing Human Activity Data Set) is a multi-modal, annotated time series (TS) data set that contains 14 recordings of 9 triaxial smartphone sensor measurements (126 TS) from 6 human subjects performing (in part) 3 motion sequences in different locations. The aim of the data set is to facilitate the study of human behaviour and the design of TS data mining technology to separate individual activities using low-cost sensors in wearable devices.
This dataset was generated to characterize mouse grooming behavior. Mouse grooming serves many adaptive functions such as coat and body care, stress reduction, de-arousal, social functions, thermoregulation, nociception, as well as other functions. Alteration of this behavior is measured and used for mouse pre-clinical models of human psychiatric illnesses. Grooming behavior in mice contains a variety of visually diverse syntaxes including but not limited to paw licking, face washing, and flank licking. Additionally, this dataset includes visually diverse mice including 157 individual mice spanning 60 different inbred and F1 hybrid mouse strains. This feature is a stark difference to most other mouse behavior datasets, which typically only include 1-2 inbred strains. This dataset includes 1,253 video clips of mice behaving in an open field imaged from top-down perspective. Each video clip contains a 112x112 video tubelet cropped around the center of mass of the mouse as it walks around the open field arena. Video clips are of variable length totaling 2,637,363 frames. Annotators were required to provide a "Grooming" or "Not Grooming" annotation for each frame. Frames where annotators disagree is also provided.
The MPII Human Pose Descriptions dataset extends the widely-used MPII Human Pose Dataset with rich textual annotations. These annotations are generated by various state-of-the-art language models (LLMs) and include detailed descriptions of the activities being performed, the count of people present, and their specific poses. The dataset consists of the same image splits as provided in MMPose, with 14644 training samples and 2723 validation samples. Each image is accompanied by one or more pose descriptions generated by different LLMs. The descriptions are also accompanied by additional annotation information, including the activity type, people count, and pose keypoints, which are derived from the original MPII Human Pose Dataset annotations. By adding textual annotations to the existing human pose dataset, this extended version supports novel research in multi-modal learning, where both visual and textual cues can be explored.
MuscleMap136 is a dataset for video-based Activated Muscle Group Estimation (AMGE) aiming at identifying currently activated muscular regions of humans performing a specific activity. Video-based AMGE is an important yet overlooked problem. To this intent, the MuscleMap136 dataset features 15K video clips with 136 different activities and 20 labeled muscle groups. Source: MuscleMap: Towards Video-based Activated Muscle Group Estimation Image Source: https://arxiv.org/pdf/2303.00952v1.pdf
InfiniteRep is a synthetic, open-source dataset for fitness and physical therapy (PT) applications. It includes 1k videos of diverse avatars performing multiple repetitions of common exercises. It includes significant variation in the environment, lighting conditions, avatar demographics, and movement trajectories. From cadence to kinematic trajectory, each rep is done slightly differently -- just like real humans. InfiniteRep videos are accompanied by a rich set of pixel-perfect labels and annotations, including frame-specific repetition counts. The dataset features: + 100 videos per exercise, spanning 5 to 10 repetitions each (1,000 videos total) + 7 unique indoor scenes + Realistic environmental occlusion (+ corresponding labels) + Diverse lighting conditions + Varied body shape, skin tones, and clothing + Rich annotations for 2D and 3D supervision ## Exercises The dataset currently includes the following exercises: + Pushups + Alternating Bicep Curls (with dumbbells) + Delt Flys (with dumbbells) + Squats + Bird Dogs + Supermans + Bicycle Crunches + Leg Raises + Front Raises (with dumbbells) + Overhead Press (with dumbbells) ## Annotations The dataset includes the following annotations: + Bounding boxes + Segmentation masks + Keypoints + Joint angles (quaternions) + Percent occlusion + Avatar characteristics + Camera position + and more Want depth labels? They are not included in the dataset but we can send them to you. Email us at info@toinfinity.ai. ## Download Download the dataset: toinfinity.ai/infiniterep Github repo with additional documentation: https://github.com/toinfinityai/InfiniteRep ## Need more data? Infinity AI specializes in generating custom synthetic data. If you need more (or different data), drop us a line at info@toinfinity.ai (we read every email).