Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Finding Action Tubes with a Sparse-to-Dense Framework

About

The task of spatial-temporal action detection has attracted increasing attention among researchers. Existing dominant methods solve this problem by relying on short-term information and dense serial-wise detection on each individual frames or clips. Despite their effectiveness, these methods showed inadequate use of long-term information and are prone to inefficiency. In this paper, we propose for the first time, an efficient framework that generates action tube proposals from video streams with a single forward pass in a sparse-to-dense manner. There are two key characteristics in this framework: (1) Both long-term and short-term sampled information are explicitly utilized in our spatiotemporal network, (2) A new dynamic feature sampling module (DTS) is designed to effectively approximate the tube output while keeping the system tractable. We evaluate the efficacy of our model on the UCF101-24, JHMDB-21 and UCFSports benchmark datasets, achieving promising results that are competitive to state-of-the-art methods. The proposed sparse-to-dense strategy rendered our framework about 7.6 times more efficient than the nearest competitor.

Yuxi Li, Weiyao Lin, Tao Wang, John See, Rui Qian, Ning Xu, Limin Wang, Shugong Xu• 2020

Related benchmarks

TaskDatasetResultRank
Action DetectionJHMDB-21
video-mAP@0.574.3
21
Action DetectionUCF101 24
video-mAP@0.554
13
Spatio-temporal action detectionUCFSports
mAP@0.5093.8
13
Action DetectionJ-HMDB
V-Score (IoU 0.5)74.3
10
Showing 4 of 4 rows

Other info

Follow for update