TrackMAE: Video Representation Learning via Track Mask and Predict
For video understanding tasks requiring fine-grained motion awareness, TrackMAE provides a simple yet effective way to incorporate motion information into masked video pretraining.
TrackMAE introduces a masked video modeling approach that explicitly uses motion trajectories from point tracking as a reconstruction signal, improving temporal dynamics encoding. It achieves state-of-the-art results on six datasets, outperforming prior self-supervised methods.
Masked video modeling (MVM) has emerged as a simple and scalable self-supervised pretraining paradigm, but only encodes motion information implicitly, limiting the encoding of temporal dynamics in the learned representations. As a result, such models struggle on motion-centric tasks that require fine-grained motion awareness. To address this, we propose TrackMAE, a simple masked video modeling paradigm that explicitly uses motion information as a reconstruction signal. In TrackMAE, we use an off-the-shelf point tracker to sparsely track points in the input videos, generating motion trajectories. Furthermore, we exploit the extracted trajectories to improve random tube masking with a motion-aware masking strategy. We enhance video representations learned in both pixel and feature semantic reconstruction spaces by providing a complementary supervision signal in the form of motion targets. We evaluate on six datasets across diverse downstream settings and find that TrackMAE consistently outperforms state-of-the-art video self-supervised learning baselines, learning more discriminative and generalizable representations. Code available at https://github.com/rvandeghen/TrackMAE