Proposal-Free Temporal Action Detection via Global Segmentation Mask Learning
This addresses the computational inefficiency for video analysis researchers and practitioners, offering a novel approach that is not incremental but represents a shift in methodology.
The authors tackled the problem of high computational cost and complexity in temporal action detection by proposing a proposal-free model that learns global segmentation masks, achieving new state-of-the-art performance on two benchmarks with ~20x faster training and ~1.6x more efficient inference.
Existing temporal action detection (TAD) methods rely on generating an overwhelmingly large number of proposals per video. This leads to complex model designs due to proposal generation and/or per-proposal action instance evaluation and the resultant high computational cost. In this work, for the first time, we propose a proposal-free Temporal Action detection model with Global Segmentation mask (TAGS). Our core idea is to learn a global segmentation mask of each action instance jointly at the full video length. The TAGS model differs significantly from the conventional proposal-based methods by focusing on global temporal representation learning to directly detect local start and end points of action instances without proposals. Further, by modeling TAD holistically rather than locally at the individual proposal level, TAGS needs a much simpler model architecture with lower computational cost. Extensive experiments show that despite its simpler design, TAGS outperforms existing TAD methods, achieving new state-of-the-art performance on two benchmarks. Importantly, it is ~ 20x faster to train and ~1.6x more efficient for inference. Our PyTorch implementation of TAGS is available at https://github.com/sauradip/TAGS .