35 datasets found

Groups: Action Recognition

Filter Results

  • DiscrimNet: Semi-Supervised Action Recognition from Videos using Generative A...

    Propose an action recognition framework using Generative Adversarial Networks. Our model involves training a deep convolutional generative adversarial network (DCGAN) using a...

  • UCF-101 dataset

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

  • Jester

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

  • Kinetics-600

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

  • Kinetics Human Action Video Dataset

    The Kinetics dataset is a large-scale video dataset for human action recognition.

  • FineGym

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

  • Kinetics-400

    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-driven Visual Tempo Learning for Video-based Action Recognition

    The proposed Temporal Correlation Module (TCM) to deal with the variation of action visual tempo in videos, which includes a Multi-scale Temporal Dynamics Module (MTDM) and a...

  • UCF101

    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...

  • HMDB51

    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

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

  • Charades

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

  • AVA

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

  • Kinetics

    The Kinetics dataset is a large-scale human action dataset, which consists of 400 action classes where each category has more than 400 videos.

  • THUMOS

    The dataset is used for action recognition with a large number of classes.