The AVA dataset densely annotates 80 atomic visual actions in 430 15-minute video clips, where actions are localized in space and time, resulting in 1. 58M action labels with multiple labels per person occurring frequently.
We demonstrate that using both RNNs (using LSTMs) and Temporal-ConvNets on spatiotemporal feature matrices are able to exploit spatiotemporal dynamics to improve the overall performance.
In particular, we evaluate our method on the large-scale multi-modal Youtube-8M v2 dataset and outperform all other methods in the Youtube 8M Large-Scale Video Understanding challenge.
In this paper, we introduce a network architecture that takes long-term content into account and enables fast per-video processing at the same time.
Despite the recent success of end-to-end learned representations, hand-crafted optical flow features are still widely used in video analysis tasks.
The explosive growth in video streaming gives rise to challenges on efficiently extracting the spatial-temporal information to perform video understanding at low computation cost.
A test video is processed by forming correspondences between its clips and the clips of reference videos with known semantics, following which, reference semantics can be transferred to the test video.