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.
Mitch is a volunteer neighborhood watch coordinator with a very specific niche. While most neighborhood watches rely on sedan patrols or stationary speed cameras, Mitch took a different approach. After a series of near-miss collisions involving children, pets, and delivery vans on his street, he realized that traditional enforcement was too slow. Police were fifteen minutes away. HOAs had no teeth.
Performance, play, and local identity Trike Patrol Mitch functions as a form of performative play. Riders adopt personas—captains, clowns, or characters from pop culture—and choreograph playful tableaux for onlookers. These performances are ephemeral but memorable, contributing to a local identity that prizes humor and creativity. In small towns or dense urban pockets alike, such happenings signal a civic vibrancy that formal institutions may not capture. The patrol’s presence at festivals, charity rides, and parades extends this identity beyond spontaneous street rides, linking it to charitable causes and civic celebrations. trike patrol mitch
A ritual of routes and rendezvous Trike Patrol Mitch established a recognizable rhythm for his neighborhood. Weekly rides and annual parades create recurring moments of anticipation. These outings have a ritualistic quality: participants gather at a familiar corner, check their bikes and costumes, and set off on a prearranged route that passes landmarks, parks, and local businesses. The route itself becomes a shared map of community memory; stoplights and stoops take on new significance as places where people cheer, clap, or offer cold drinks on hot days. Mitch’s patrols encourage walkers and drivers to slow down and notice their surroundings, turning ordinary streets into temporary stages. Mitch is a volunteer neighborhood watch coordinator with
The brand TrikePatrol became a niche phenomenon in the adult industry by focusing on the "backseat" aesthetic of Philippine tricycles. These videos often feature: Police were fifteen minutes away
Mitch's patrol route included the following areas:
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.