The goal of the Kinetics dataset is to help the computer vision and machine learning communities advance models for video understanding. Given this large human action classification dataset, it may be possible to learn powerful video representations that transfer to different video tasks.
The Kinetics-700-2020 dataset will be used for this challenge. Kinetics-700-2020 is a large-scale, high-quality dataset of YouTube video URLs which include a diverse range of human focused actions. The aim of the Kinetics dataset is to help the machine learning community create more advanced models for video understanding. It is an approximate super-set of both Kinetics-400, released in 2017, Kinetics-600, released in 2018 and Kinetics-700, released in 2019.
The dataset consists of approximately 650,000 video clips, and covers 700 human action classes with at least 700 video clips for each action class. Each clip lasts around 10 seconds and is labeled with a single class. All of the clips have been through multiple rounds of human annotation, and each is taken from a unique YouTube video. The actions cover a broad range of classes including human-object interactions such as playing instruments, as well as human-human interactions such as shaking hands and hugging.
More information about how to download the Kinetics dataset is available here.
Overall, Filmora 13.6.4.8382 - Portable strikes a practical balance between ease of use and creative capability. It’s especially well-suited for beginners and creators needing fast, straightforward edits on the go, while those seeking deep technical controls or studio-level performance may prefer a fully installed, professional-grade editor.
Performance in this version feels responsive on modest hardware; rendering times are reasonable for short projects, and common effects and transitions apply smoothly. The bundled effects, stock music, and preset templates provide immediate creative options, helping users assemble polished-looking videos with minimal setup. The color grading and audio tools are serviceable for social-media content, vlogs, and small-scale projects, though power users may find the depth limited compared with professional NLEs. Wondershare Filmora 13.6.4.8382 - Portable
Wondershare Filmora 13.6.4.8382 - Portable presents itself as a compact, user-friendly video-editing solution tailored for creators who need quick access to core editing tools without a full installation. In this portable build, Filmora’s signature clean interface and approachable learning curve remain central: tracks, timeline, and preview are arranged for intuitive drag-and-drop editing, making basic to intermediate tasks—cutting, trimming, transitions, and simple color adjustments—fast and accessible. Overall, Filmora 13
1. Possible to use ImageNet checkpoints?
We allow finetuning from public ImageNet checkpoints for the supervised track -- but a link to the specific checkpoint should be provided with each submission.
2. Possible to use optical flow?
Flow can be used as long as not trained on external datasets, except if they are synthetic.
3. Can we train on test data without labels (e.g. transductive)?
No.
4. Can we use semantic class label information?
Yes, for the supervised track.
5. Will there be special tracks for methods using fewer FLOPs / small models or just RGB vs RGB+Audio in the self-supervised track?
We will ask participants to provide the total number of model parameters and the modalities used and plan to create special mentions for those doing well in each setting, but not specific tracks.