Search Results for "identity"

CoTracker is a learning-based point tracking system that jointly follows many user-specified points across a video, rather than tracking each point independently. By reasoning about all tracks together, it can maintain temporal consistency, handle mutual occlusions, and reduce identity swaps when trajectories cross. The model takes sparse point queries on one frame and predicts their sub-pixel locations and a visibility score for every subsequent frame, producing long, coherent trajectories. Its transformer-style architecture aggregates information both along time and across points, allowing it to recover tracks even after brief disappearances. ...

this is a project for the computer vision class. We intend to track multi-targets while preserving the identity of the targets. We propose to represent this as a Flow optimization problem and solve it using K-shortest path algorithm.