6 datasets found

Video-based person re-identification (re-id) is a cen-

MPCvit: Searching for MPC-Friendly Vision Transformer with Heterogeneous Attention

Face frontalization provides an effective and efficient way for face data augmentation and further improves the face recognition performance in extreme pose scenario.

The dataset used in the paper is a virtual reality driving dataset with gaze coordinates, driving speed, and course information.

The dataset used in the paper is a driving dataset with gaze coordinates, driving speed, and course information.

The MSRVTT is a large-scale dataset for video captioning. It contains 10k video clips and each video clip is accompanied with 20 human-edited English sentence descriptions,...