24 datasets found

The Penn Action dataset is a real video dataset of people performing various indoor and outdoor sports with annotations of human joint locations.

Long form video understanding (LVU) is a sub-domain of video recognition concerned with understanding contextual information across contiguous shots which can contain multiple...

LocalStyleFool: Regional Video Style Transfer Attack Using Segment Anything

The Diving48 dataset is a fine-grained video dataset of competitive diving. It has ∼18k trimmed video clips of 48 unambiguous dive sequences standardized by the professional....

The Mini-Kinetics dataset is a mini version of the Kinetics-400 dataset, containing 240k training samples and 20k validation samples in 400 human action classes.

The HMDB51 dataset is a video dataset for human action recognition. It contains 6,767 videos annotated with 51 categories of human actions.

The Kinetics-700 dataset is a large-scale video dataset for human action recognition. It contains 555,774 videos annotated with 700 categories of human actions.

The KTH dataset consists of videos of 25 people performing different activities.

The dataset used in the LORD framework for autonomous driving, consisting of images, videos, and text-based observations.

The Moments in Time dataset is a large-scale video action recognition dataset.

Mobile Video Networks (MoViNets) is a family of computation and memory efficient video networks that can operate on streaming video for online inference.

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

Video classification is a fundamental problem in many video-based tasks. Applications such as autonomous driving technology, controlling drones and robots are driving the demand...

The Kinetics-600 dataset consists of 392k training videos and 30k validation videos in 600 human action categories.

Motion has shown to be useful for video understanding, where motion is typically represented by optical flow. However, computing flow from video frames is very time-consuming....

Motion has shown to be useful for video understanding, where motion is typically represented by optical flow. However, computing flow from video frames is very time-consuming....

The Something-Something V1 & V2 dataset is a large-scale video dataset created by crowdsourcing. It contains about 100k videos over 174 categories, and the number of videos...

Video classification is a fundamental problem in many video-based tasks. Applications such as autonomous driving technology, controlling drones and robots are driving the demand...

The dataset used for video action classification, consisting of 9.8k training videos, 1.8k validation videos, and 157 classes.

The dataset used in this paper is a Flickr image dataset, which is used to evaluate the proposed deep aesthetic feature learning framework.