86 datasets found

BMLrub is a dataset of human motion and video.

The dataset used in the paper is not explicitly described, but it is mentioned that the authors tested their model on various signal reconstruction tasks: 1D sinusoidal...

The CelebV-HQ dataset contains 35,666 face videos from over 15,000 identities.

The UCF-Crime and XD-Violence datasets are used for weakly supervised video anomaly detection.

Weakly-Supervised Temporal Action Localization (WSTAL) aims to localize actions in untrimmed videos with only video-level labels.

CamVid dataset is a benchmark dataset for semantic segmentation. It consists of 700 images with 11 object classes.

BDD100K Dataset is a large-scale dataset for autonomous driving, containing 100,000 images, with 20,000 images for training and 80,000 images for testing.

The dataset used in the paper for self-supervised learning of video representations.

Four datasets are relevant for our study: HMDB51, UCF101, Kinetics-400, and IG65M.

The DAVIS dataset comprises 60, 30 and 30 video sequences for training, validation and testing, respectively. The YouTube-VOS dataset is a larger dataset with 3471 videos for...

The Every Moment Counts dataset contains 1,000 hours of video footage of various activities.

The Hollywood in Homes dataset contains 9,848 videos of daily activities across 157 classes.

The THUMOS Challenge dataset contains 413 sports videos of 65 classes.

Temporal Action Detection (TAD) aims to identify the action boundaries and the corresponding category within untrimmed videos.

The Multi Visual Modality Fall Detection Dataset (MUVIM) was used for anomaly detection of falls. It contains (6) vision-based sensors of different modalities including thermal,...

UCF-101 dataset is a large-scale action recognition dataset, containing 13,320 videos categorized into 101 human action categories.

The Jester dataset is of continuous jokes ratings from -10 to 10, containing the jokes’ texts.

The DAVIS dataset is a widely used dataset for video-related tasks, consisting of approximately 2000 frames from 26 human-centric scenarios.

The MUSES dataset is a collection of 3,697 videos, with 2,587 for training and 1,110 for testing.

Temporal action localization (TAL) is a prevailing task due to its great application potential. Existing works in this field mainly suffer from two weaknesses: (1) They often...