Spatio-Temporal Action Localization

13 papers with code • 1 benchmarks • 5 datasets

This task has no description! Would you like to contribute one?

Most implemented papers

Actor-Context-Actor Relation Network for Spatio-Temporal Action Localization

Siyu-C/ACAR-Net CVPR 2021

We propose to explicitly model the Actor-Context-Actor Relation, which is the relation between two actors based on their interactions with the context.

Action Tubelet Detector for Spatio-Temporal Action Localization

vkalogeiton/caffe ICCV 2017

We propose the ACtion Tubelet detector (ACT-detector) that takes as input a sequence of frames and outputs tubelets, i. e., sequences of bounding boxes with associated scores.

1st place solution for AVA-Kinetics Crossover in AcitivityNet Challenge 2020

Siyu-C/ACAR-Net 16 Jun 2020

This technical report introduces our winning solution to the spatio-temporal action localization track, AVA-Kinetics Crossover, in ActivityNet Challenge 2020.

Chained Multi-stream Networks Exploiting Pose, Motion, and Appearance for Action Classification and Detection

mzolfaghari/chained-multistream-networks ICCV 2017

In this paper, we propose a network architecture that computes and integrates the most important visual cues for action recognition: pose, motion, and the raw images.

Actor-Centric Relation Network

open-mmlab/mmaction2 ECCV 2018

A visualization of the learned relation features confirms that our approach is able to attend to the relevant relations for each action.

Video action detection by learning graph-based spatio-temporal interactions

aimagelab/STAGE_action_detection 9 Dec 2019

Action Detection is a complex task that aims to detect and classify human actions in video clips.

ST-HOI: A Spatial-Temporal Baseline for Human-Object Interaction Detection in Videos

coldmanck/VidHOI 25 May 2021

Detecting human-object interactions (HOI) is an important step toward a comprehensive visual understanding of machines.

KORSAL: Key-point Detection based Online Real-Time Spatio-Temporal Action Localization

Kalana304/KORSAL 5 Nov 2021

Despite the simplicity of our approach, our lightweight end-to-end architecture achieves state-of-the-art frame-mAP of 74. 7% on the challenging UCF101-24 dataset, demonstrating a performance gain of 6. 4% over the previous best online methods.

Contextualized Spatio-Temporal Contrastive Learning with Self-Supervision

tensorflow/models CVPR 2022

Modern self-supervised learning algorithms typically enforce persistency of instance representations across views.

E^2TAD: An Energy-Efficient Tracking-based Action Detector

VITA-Group/21LPCV-UAV-Solution 9 Apr 2022

Video action detection (spatio-temporal action localization) is usually the starting point for human-centric intelligent analysis of videos nowadays.