132 datasets found

The dataset used in the paper is the 50 Salads dataset, which contains 50 videos showing people preparing salads. The dataset is used for dense action forecasting, and the...

The Breakfast dataset is another dataset used in the paper, which contains 712 videos of people performing various activities, such as making coffee or scrambling eggs. The...

The dataset used in the paper is a video-based activity recognition dataset, consisting of 90 video sequences spanning three scenarios: SHORT MEAL, HAVE SNACK and NORMAL MEAL.

A dataset for detecting advertisement billboards in soccer video scenes.

A composite dataset consisting of positive- and negative- examples of billboard detection.

AViD is a new public video dataset for action recognition, containing action videos from diverse countries.

CityCam dataset contains recordings from 212 traffic cameras in the United States, with a resolution of 352x240 and a frame rate of 1 frame/per second.

A dataset of videos of human activities captured by calibrated cameras.

A large-scale database for partial copy detection in videos.

The dataset is a collection of YouTube trending videos with their thumbnails, metadata, and object labels.

The Collective Activities dataset consists of 44 videos taken in unconstrained real-world scenarios of people performing 6 individual actions across 5 group activities.

The THUMOS'13 dataset contains 24 classes and 3,207 videos.

The JHMDB dataset contains a varying number of actions (21 in JHMDB) across different domains (sports and daily activities).

The UCF Sports dataset contains a varying number of actions (10 in UCF Sports, 21 in JHMDB, and 24 in THUMOS’13) across different domains (sports and daily activities).

TVQA is a video question answering dataset collected from 6 long-running TV shows from 3 genres. There are 21,793 video clips in total for QA collection, accompanied with...

This paper proposes a video question answering model that effectively integrates multi-modal input sources and finds the temporally relevant information to answer questions.

Temporal action detection in untrimmed videos via multi-stage cnns, Cdc: convolutional-de-convolutional networks for precise temporal action localization, Temporal action...

Tinyvideos dataset

The STV-IDL dataset is a collection of videos with referring expressions that describe spatio-temporal events.

The VisDrone2019 dataset contains 288 video clips made up of 261,908 frames and 10,209 images