By 2024 end, a model exhibits action recognition (video) equivalent to human level accuracy on Something Something V2?
13
17
αΉ145αΉ270
Dec 31
40%
chance
1D
1W
1M
ALL
https://paperswithcode.com/sota/action-recognition-in-videos-on-something
Action Recognition is a computer vision task that involves recognizing human actions in videos or images.
The goal is to classify and categorize the actions being performed in the video or image into a predefined set of action classes.
In the video domain, it is an open question whether training an action classification network on a sufficiently large dataset, will give a similar boost in performance when applied to a different temporal task or dataset. The challenges of building video datasets has meant that most popular benchmarks for action recognition are small, having on the order of 10k videos.
(i'll accept if within 2% of human performance)
Get αΉ200 play money
More related questions
Related questions
By 2025 end, a model exhibits action recognition (video) equivalent to human level accuracy on Something Something V2?
56% chance
Will AI be able to create a video with this much detail by 2030?
91% chance
Human-machine intelligence parity achieved before 2028
57% chance
Will an AI model outperform 95% of Manifold users on accuracy before 2026?
67% chance
Movement in "In 2028, will an AI be able to generate a full high-quality movie to a prompt?" by EOY 2024. (500M subsidy)
28% chance
By 2029, will an AI be able to generate a full high quality Video Game to a prompt?
31% chance
Will a model costing >$30M be intentionally trained to be more mechanistically interpretable by end of 2027? (see desc)
57% chance
Will AI generate realistic video of animal movement before 2025?
84% chance
In 2028, will an AI be able to generate a full high-quality movie to a prompt, with human aid?
56% chance
Will it be effectively impossible to tell a human and a high quality AI apart on social media before 2026?
89% chance