CVAIJul 9, 2021

RGB Stream Is Enough for Temporal Action Detection

arXiv:2107.04362v128 citationsHas Code
Originality Incremental advance
AI Analysis

This work addresses the computational inefficiency and methodological issues in temporal action detection for video analysis, though it is incremental as it builds on existing detector frameworks.

The paper tackles the problem of temporal action detection by showing that optical flow is unnecessary, achieving comparable accuracy to state-of-the-art two-stream detectors with a single RGB stream and image-level data augmentation, while reaching an inference speed of 6668 fps.

State-of-the-art temporal action detectors to date are based on two-stream input including RGB frames and optical flow. Although combining RGB frames and optical flow boosts performance significantly, optical flow is a hand-designed representation which not only requires heavy computation, but also makes it methodologically unsatisfactory that two-stream methods are often not learned end-to-end jointly with the flow. In this paper, we argue that optical flow is dispensable in high-accuracy temporal action detection and image level data augmentation (ILDA) is the key solution to avoid performance degradation when optical flow is removed. To evaluate the effectiveness of ILDA, we design a simple yet efficient one-stage temporal action detector based on single RGB stream named DaoTAD. Our results show that when trained with ILDA, DaoTAD has comparable accuracy with all existing state-of-the-art two-stream detectors while surpassing the inference speed of previous methods by a large margin and the inference speed is astounding 6668 fps on GeForce GTX 1080 Ti. Code is available at \url{https://github.com/Media-Smart/vedatad}.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes