12 datasets found

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...

Video-MNIST is a novel variant of the classic MNIST dataset. It contains 70000 sequences, each sequence containing 30 frames showing an affine transformation on a single...

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...

FineGym is a hierarchical video dataset for fine-grained action understanding, containing 354 action categories.

Resound is a video dataset for action recognition without representation bias.

Structural Vision Transformer (StructViT) is a vision transformer network that leverages structural self-attention (StructSA) to capture correlation structures in images and...

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...

The UCF101 dataset contains 13320 videos distributed in 101 action categories. This dataset is different from the above ones in that it contains mostly coarse sports activities...

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...

Kinetics-700 is a large-scale video dataset for human action recognition, with 700 action categories.

Youtube-8M is a large-scale video classification benchmark.