paper-with-me

Papers

Spatio-Temporal Context for Action Detection

2021-06-29 · Manuel Sarmiento Calderó, David Varas, Elisenda Bou-Balust

Research in action detection has grown in the recentyears, as it plays a key role in video understanding. Modelling the interactions (either spatial or temporal) between actors and their context has proven to be essential for this task. While recent works use spatial features with aggregated temporal information, this work proposes to use non-aggregated temporal information. This is done by adding an attention based method that leverages spatio-temporal interactions between elements in the scene along the clip.The main contribution of this work is the introduction of two cross attention blocks to effectively model the spatial relations and capture short range temporal interactions.Experiments on the AVA dataset show the advantages of the proposed approach that models spatio-temporal relations between relevant elements in the scene, outperforming other methods that model actor interactions with their context by +0.31 mAP.

📄 PDF Abstract BibTeX arXiv:2106.15171

Code (0)

등록된 구현이 없습니다.

Tasks

Action DetectionVideo Understanding

Similar Papers 제목 키워드 기반

Graph-Theoretic Spatiotemporal Context Modeling for Video Saliency Detection

2017-07-25 · Lina Wei, Fangfang Wang, Xi Li, Fei Wu 외

As an important and challenging problem in computer vision, video saliency detection is typically cast as a spatiotemporal context modeling problem over consecutive frames. As a result, a key issue in video saliency dete…

Saliency DetectionVideo Saliency Detection

TACNet: Transition-Aware Context Network for Spatio-Temporal Action Detection

2019-05-31 · CVPR 2019 6 · Lin Song, Shiwei Zhang, Gang Yu, Hongbin Sun

Current state-of-the-art approaches for spatio-temporal action detection have achieved impressive results but remain unsatisfactory for temporal extent detection. The main reason comes from that, there are some ambiguous…

Action Detection

STEP: Spatio-Temporal Progressive Learning for Video Action Detection

2019-04-19 · CVPR 2019 6 · Xitong Yang, Xiaodong Yang, Ming-Yu Liu, Fanyi Xiao 외

In this paper, we propose Spatio-TEmporal Progressive (STEP) action detector---a progressive learning framework for spatio-temporal action detection in videos. Starting from a handful of coarse-scale proposal cuboids, ou…

Action DetectionAction RecognitionVideo Action Detection

TubeR: Tubelet Transformer for Video Action Detection

2021-04-02 · CVPR 2022 1 · Jiaojiao Zhao, Yanyi Zhang, Xinyu Li, Hao Chen 외

We propose TubeR: a simple solution for spatio-temporal video action detection. Different from existing methods that depend on either an off-line actor detector or hand-designed actor-positional hypotheses like proposals…

Action ClassificationAction DetectionAction LocalizationVideo Action Detection+1

A Proposal-Based Solution to Spatio-Temporal Action Detection in Untrimmed Videos

2018-11-20 · Joshua Gleason, Rajeev Ranjan, Steven Schwarcz, Carlos D. Castillo 외

Existing approaches for spatio-temporal action detection in videos are limited by the spatial extent and temporal duration of the actions. In this paper, we present a modular system for spatio-temporal action detection i…

Action ClassificationAction DetectionClusteringobject-detection+1