
Sign up to save your podcasts
Or


Opt-CWM is a self-supervised method for motion estimation from videos, achieving state-of-the-art performance without labeled data by optimizing counterfactual probes from a pre-trained model.
https://arxiv.org/abs//2503.19953
YouTube: https://www.youtube.com/@ArxivPapers
TikTok: https://www.tiktok.com/@arxiv_papers
Apple Podcasts: https://podcasts.apple.com/us/podcast/arxiv-papers/id1692476016
Spotify: https://podcasters.spotify.com/pod/show/arxiv-papers
By Igor Melnyk5
33 ratings
Opt-CWM is a self-supervised method for motion estimation from videos, achieving state-of-the-art performance without labeled data by optimizing counterfactual probes from a pre-trained model.
https://arxiv.org/abs//2503.19953
YouTube: https://www.youtube.com/@ArxivPapers
TikTok: https://www.tiktok.com/@arxiv_papers
Apple Podcasts: https://podcasts.apple.com/us/podcast/arxiv-papers/id1692476016
Spotify: https://podcasters.spotify.com/pod/show/arxiv-papers

960 Listeners

1,929 Listeners

432 Listeners

112,236 Listeners

9,938 Listeners

5,509 Listeners

216 Listeners

49 Listeners

93 Listeners

465 Listeners