Search papers, labs, and topics across Lattice.
Indian Institute of Technology Hyderabad, Microsoft Research India
Microsoft Research3
0
4
Colorization methods can now adaptively handle both modern and historical grayscale images, reducing color artifacts and improving visual fidelity.
Achieving up to 3.5% mAP gains and 1.3x higher throughput, RT-SFOD redefines the trade-offs in source-free object detection by being faster and more compact without sacrificing accuracy.
Skip the training and the hyperparameter tuning: Swift Sampling uses Taylor series to find the most informative frames in a video, beating existing methods with a 30x reduction in overhead.
