A Short Note on the Kinetics-700 Human Action Dataset

By João Carreira, Eric Noland, Chloe Hillier, Andrew Zisserman. 2019

559 citations recorded by the source corpus.

We describe an extension of the DeepMind Kinetics human action dataset from 600 classes to 700 classes, where for each class there are at least 600 video clips from different YouTube videos. This paper details the changes introduced for this new release of the dataset, and includes a comprehensive set of statistics as well as baseline results using the I3D neural network architecture.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Evaluation & Benchmarks

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Evaluation & Benchmarks

Citations in the corpus

Learning Video Representations from Textual Web Supervision (2020, methodology): “Kinetics-400, 600, and 700 are increasingly large versions of the dataset, containing 400, 600, and 700 action categories, respectively [7, 8].”
Self-Supervised MultiModal Versatile Networks (2020, methodology): “Finally, our approach is significantly better than pre-training in a fully supervised manner on Kinetics-700 [14].”
End-to-End Learning of Visual Representations From Uncurated Instructional Videos (2019, neutral): “Action Recognition: HMDB-51 [45], UCF-101 [69], Kinetics-700 [14].”
A Short Note on the Kinetics-700-2020 Human Action Dataset (2020, methodology): “Three editions have been released: Kinetics-400 [6], Kinetics-600 [1] and Kinetics-700 [2], with 400, 600 and 700 human action classes, respectively.”
Rescaling Egocentric Vision: Collection, Pipeline and Challenges for EPIC-KITCHENS-100 (2020, neutral): “Kinetics-700 [41,42] 2019 YouTube 1806 1 650k 10.”
Less is More: CLIPBERT for Video-and-Language Learning via Sparse Sampling (2021, methodology): “s. Speciﬁcally, for CNN, we use weights from random initialization, image classiﬁcation model pre-trained on ImageNet [10], frame-wise action recognition model TSN [66, 9] pre-trained on Kinetics-700 [57,4], or detection model grid-feat [24] pre-trained on Visual Genome [29]. For transformer and wor”
SlowFast Networks for Video Recognition (2018, background): “SlowFast results on the recent Kinetics-700 [4] are in [11].”
Action Genome: Actions As Compositions of Spatio-Temporal Scene Graphs (2019, background): “4K 200 Kinetics-700 [9] 1794 650K 700 -”
MoViNets: Mobile Video Networks for Efficient Video Recognition (2021, methodology): “We report results on all Kinetics datasets, including Kinetics 400 [9, 32], Kinetics 600 [6], and Kinetics 700 [7], which contain 10-second, 250-frame video sequences at 25 fps labeled with 400, 600, and 700 action classes, respectively.”
EVA-02: A Visual Representation for Neon Genesis (2023, methodology): “Following [95], we report top-1 accuracy for UCF-101 [111], and the mean of top-1 and top-5 accuracies for K-400 [21], K-600 [19] and K-700 [20] datasets. present CLIP model configurations and IN-1K zero-shot accuracies in Table 10.”
Intern VL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks (2023, methodology): “Following previous meth-ods [89, 99, 117], we report the top-1 accuracy and the mean of top-1 and top-5 accuracy on Kinetics-400/600/700 [15– 17].”
InternVideo: General Video Foundation Models via Generative and Discriminative Learning (2022, methodology): “We evaluate VideoMAE and UniFormerV2 in InternVideo on Kinetics-400 [27], Kinetics-600 [69], Kinetics-700 [70], Something-in-Something-V1 [68], Something-in-Something-V2 [68], ActivityNet [79], HACS [80], and HMDB51 [81].”