Video 3D Sampling for Self-supervised Representation Learning
This work addresses the need for better video representation learning in computer vision, offering a novel method that integrates spatial and temporal cues, though it appears incremental in building upon existing self-supervised approaches.
The paper tackles the problem of video self-supervised representation learning by proposing Video 3D Sampling (V3S), which leverages spatial and temporal information from width, height, and time dimensions, resulting in improved state-of-the-art performance on action recognition, video retrieval, and action similarity labeling tasks.
Most of the existing video self-supervised methods mainly leverage temporal signals of videos, ignoring that the semantics of moving objects and environmental information are all critical for video-related tasks. In this paper, we propose a novel self-supervised method for video representation learning, referred to as Video 3D Sampling (V3S). In order to sufficiently utilize the information (spatial and temporal) provided in videos, we pre-process a video from three dimensions (width, height, time). As a result, we can leverage the spatial information (the size of objects), temporal information (the direction and magnitude of motions) as our learning target. In our implementation, we combine the sampling of the three dimensions and propose the scale and projection transformations in space and time respectively. The experimental results show that, when applied to action recognition, video retrieval and action similarity labeling, our approach improves the state-of-the-arts with significant margins.