The AVA-Kinetics Localized Human Actions Video Dataset
By Ang Li, Meghana Thotakuri, David A. Ross, João Carreira, A. Vostrikov, Andrew Zisserman. 2020
157 citations recorded by the source corpus.
This paper describes the AVA-Kinetics localized human actions video dataset. The dataset is collected by annotating videos from the Kinetics-700 dataset using the AVA annotation protocol, and extending the original AVA dataset with these new AVA annotated Kinetics clips. The dataset contains over 230k clips annotated with the 80 AVA action classes for each of the humans in key-frames. We describe the annotation process and provide statistics about the new dataset. We also include a baseline evaluation using the Video Action Transformer Network on the AVA-Kinetics dataset, demonstrating improved performance for action classification on the AVA test set. The dataset can be downloaded from this https URL
Subfields: Artificial Intelligence, Biomedical Engineering, 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
- Christoph Feichtenhofer
- Andrew Zisserman
- Kaiming He
- Jitendra Malik
- Ross B. Girshick
- Mohit Bansal
- Kristen Grauman
- Cordelia Schmid
In Biomedical Engineering
- Andrew Zisserman
- Kaiming He
- Ross B. Girshick
- Haoqi Fan
- João Carreira
- Dima Damen
- David F. Fouhey
- Christoph Feichtenhofer
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Jitendra Malik
- Andrew Zisserman
- Trevor Darrell
- Kristen Grauman
- Cordelia Schmid
- Dacheng Tao
- Xiaogang Wang
In Evaluation & Benchmarks
- Kaiming He
- Christoph Feichtenhofer
- Haoqi Fan
- Ross B. Girshick
- Andrew Zisserman
- João Carreira
- Sanja Fidler
- Lucas Smaira
Citations in the corpus
- A Short Note on the Kinetics-700-2020 Human Action Dataset (2020, methodology): “The link also includes additional annotations for the AVA-Kinetics [7] and Countix [4] datasets.”
- EPIC-KITCHENS VISOR Benchmark: VIdeo Segmentations and Object Relations (2022, background): “8, 10, 39 [22] Ang Li, Meghana Thotakuri, David A Ross, Joao Carreira, Alexander Vostrikov, and Andrew Zisserman.”
- InternVideo: General Video Foundation Models via Generative and Discriminative Learning (2022, unknown): “2 [67] and AVA-Kinetics [84].”
- A Large-Scale Study on Unsupervised Spatiotemporal Representation Learning (2021, result): “Overall this is a surprising result as the tasks in K400 and AVA are similar [52], only that the temporal granularity of the actions in AVA is finer while their semantic granularity is coarser; e.”