How to Track Objects in Videos with Self-supervised Techniques | AISC
Subscribers:
20,400
Published on ● Video Link: https://www.youtube.com/watch?v=O8O__guO80E
For slides and more information on the paper, visit https://ai.science/e/masta-memory-augmented-self-supervised-tracker--BJ9Chw0kECHfyEivCJS9
Speaker: Soufia Naseri; Discussion Facilitator: Fatemeh Darbehani; Host: Alireza Darbehani
Motivation:
Object tracking is gaining lots of attention and applications. MAST uses only 1 annotated data (pixel level) and achieves a high accuracy.
Comapring with unseen object categories MAST outperforms almost all of trained model using heavy supervision.
Self-supervised algorithms can serve as a strong competitor to their supervised counterparts due to demand for less computation power and better generalizability.