Can I read Relaxed Transformer Decoders for Direct Action Proposal Generation on EtoBox?

Relaxed Transformer Decoders for Direct Action Proposal Generation by Tan, Jing; Tang, Jiaqi; Wang, Limin; Wu, Gangshan is a scholarly article available to read on EtoBox.

What is Relaxed Transformer Decoders for Direct Action Proposal Generation about?

Temporal action proposal generation is an important and challenging task in video understanding, which aims at detecting all temporal segments containing action instances of interest. The existing proposal generation approaches are generally based on pre-defined anchor windows or heuristic bottom-up boundary matching strategies. This paper presents a simple and efficient framework (RTD-Net) for direct action proposal generation, by re-purposing a Transformer-alike architecture. To tackle the essential visual difference between time and space, we make three important improvements over the original transformer detection framework (DETR). First, to deal with slowness prior in videos, we replace the original Transformer encoder with a boundary attentive module to better capture long-range temporal information. Second, due to the ambiguous temporal boundary and relatively sparse annotations, we present a relaxed matching scheme to relieve the strict criteria of single assignment to each groundtruth. Finally, we devise a three-branch head to further improve the proposal confidence estimation by explicitly predicting its completeness. Extensive experiments on THUMOS14 and ActivityNet-1.3

Author

Tan, Jing; Tang, Jiaqi; Wang, Limin; Wu, Gangshan

Published

2021

Language

EN