Finding Action Tubes with a Sparse-to-Dense Framework

08/30/2020
by   Yuxi Li, et al.
4

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.

READ FULL TEXT

page 1

page 3

page 6

research
01/19/2023

Revisiting the Spatial and Temporal Modeling for Few-shot Action Recognition

Spatial and temporal modeling is one of the most core aspects of few-sho...
research
03/31/2020

Long Short-Term Relation Networks for Video Action Detection

It has been well recognized that modeling human-object or object-object ...
research
06/20/2022

A Novel Long-term Iterative Mining Scheme for Video Salient Object Detection

The existing state-of-the-art (SOTA) video salient object detection (VSO...
research
10/19/2021

LSTC: Boosting Atomic Action Detection with Long-Short-Term Context

In this paper, we place the atomic action detection problem into a Long-...
research
04/11/2021

Temporal Consistency Two-Stream CNN for Human Motion Prediction

Fusion is critical for a two-stream network. In this paper, we propose a...
research
01/15/2023

Learning Sparse Temporal Video Mapping for Action Quality Assessment in Floor Gymnastics

Athlete performance measurement in sports videos requires modeling long ...
research
05/30/2023

Epilepsy Seizure Detection: Anatomy and Analysis

A seizure tracking system is crucial for monitoring and evaluating epile...

Please sign up or login with your details

Forgot password? Click here to reset