Bergen [top] | Barnevakten

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.

For information related to this task, please contact:

Dataset

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.

Bergen [top] | Barnevakten

Barnevakten (The Children's Watch) is a national competency center focused on digital safety and media literacy for children and youth. While it is a nationwide service, it has deep roots and strong relevance for the local community in Bergen.

Barnevakten hosts interactive seminars and theme nights for schools and kindergartens, focusing on topics like internet safety and digital literacy.

The rain in Bergen didn't just fall; it reclaimed the city, turning the cobblestones of Bryggen into a shimmering dark mirror. Inside a narrow, leaning wooden house, Elias—the most sought-after barnevakt (babysitter) in the neighborhood—was losing a battle against a seven-year-old named Karoline and a very stubborn goat-shaped stuffed animal. "The Fløibanen doesn't go to the moon, Karoline," Elias said, adjusting his glasses. "It does if you push the blue button twice," she insisted, peering out the window at the mist-shrouded peak of Mount Fløyen. Elias smiled. He had moved to Bergen for his studies, and babysitting was his way of learning the local rhythm. He loved the way the city felt like a village tucked between giants. Tonight, with Karoline’s parents at a concert at Grieghallen, the old house felt alive with the creaks of centuries-old timber. To settle her down, Elias started a game they called "The Seven Mountains." He gathered seven pillows and scattered them across the living room rug. "To get to sleep," he whispered, "you have to trek across every peak. But watch out for the Trolls under the Ulriken pillow." Karoline giggled, hopping from "Mount Lyderhorn" to "Mount Damsgårdsfjellet." By the time she reached "Mount Fløyen"—her actual bed—the wind was whistling through the attic vents like a soft flute. As she tucked herself in, she looked at Elias . "Will it be sunny tomorrow?" Elias looked at the rain lashing against the glass, the quintessential Bergen evening. "In this city, Karoline , the sun is just playing hide and seek. But we have the best umbrellas in the world." He turned off the light, leaving the door cracked just enough to hear the steady, comforting rhythm of the rain. Downstairs, he made himself a cup of tea and watched the lights of the ships in the harbor, thinking that being a barnevakten bergen

Barnevakten er mer enn bare nettvett-regler; de er en aktiv samarbeidspartner for lokalsamfunnet i Bergen: Om oss | Barnevakten

| | How Barnevakten Bergen Implements It | |----------------------|-------------------------------------------| | Early intervention | Identifies at-risk children before formal child welfare involvement | | Voluntary participation | Parents and children can use services without referral | | Collaboration with schools | Staff meet weekly with school social workers | | Least intrusive measures | Offers support without removing child from home | | Best interests of the child | Activities tailored to child’s age, needs, and wishes | Barnevakten (The Children's Watch) is a national competency

Based on the analysis, the following recommendations are proposed:

Barnevakten Bergen operationalizes key principles of the Norwegian Child Welfare Act (§§ 3-1 to 3-6) concerning preventive measures: The rain in Bergen didn't just fall; it

This is the flagship tool provided by Barnevakten. It is a free, digital resource that helps parents understand the specific apps, games, and platforms their children are using. Whether your child is asking for TikTok, Snapchat, or Roblox, the guide breaks down:

Further research should include longitudinal studies tracking child outcomes and comparative analyses of Barnevakt models in other Nordic cities.

FAQ

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.