End-to-End Spatio-Temporal Action Localisation with Video Transformers
This work addresses the complexity and inefficiency in action localization models for video analysis, offering a more streamlined approach, though it is incremental in improving existing methods.
The paper tackles the problem of spatio-temporal action localization by proposing an end-to-end transformer-based model that directly outputs tubelets from input videos, eliminating the need for external proposals or post-processing. It achieves state-of-the-art results on four benchmarks with both sparse and full annotations.
The most performant spatio-temporal action localisation models use external person proposals and complex external memory banks. We propose a fully end-to-end, purely-transformer based model that directly ingests an input video, and outputs tubelets -- a sequence of bounding boxes and the action classes at each frame. Our flexible model can be trained with either sparse bounding-box supervision on individual frames, or full tubelet annotations. And in both cases, it predicts coherent tubelets as the output. Moreover, our end-to-end model requires no additional pre-processing in the form of proposals, or post-processing in terms of non-maximal suppression. We perform extensive ablation experiments, and significantly advance the state-of-the-art results on four different spatio-temporal action localisation benchmarks with both sparse keyframes and full tubelet annotations.