MRSN: Multi-Relation Support Network for Video Action Detection

04/24/2023
by   Yin-Dong Zheng, et al.
0

Action detection is a challenging video understanding task, requiring modeling spatio-temporal and interaction relations. Current methods usually model actor-actor and actor-context relations separately, ignoring their complementarity and mutual support. To solve this problem, we propose a novel network called Multi-Relation Support Network (MRSN). In MRSN, Actor-Context Relation Encoder (ACRE) and Actor-Actor Relation Encoder (AARE) model the actor-context and actor-actor relation separately. Then Relation Support Encoder (RSE) computes the supports between the two relations and performs relation-level interactions. Finally, Relation Consensus Module (RCM) enhances two relations with the long-term relations from the Long-term Relation Bank (LRB) and yields a consensus. Our experiments demonstrate that modeling relations separately and performing relation-level interactions can achieve and outperformer state-of-the-art results on two challenging video datasets: AVA and UCF101-24.

READ FULL TEXT

page 1

page 3

research
03/28/2023

CycleACR: Cycle Modeling of Actor-Context Relations for Video Action Detection

The relation modeling between actors and scene context advances video ac...
research
07/28/2018

Actor-Centric Relation Network

Current state-of-the-art approaches for spatio-temporal action localizat...
research
06/14/2020

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

Localizing persons and recognizing their actions from videos is a challe...
research
06/29/2021

Spatio-Temporal Context for Action Detection

Research in action detection has grown in the recentyears, as it plays a...
research
08/26/2021

Identity-aware Graph Memory Network for Action Detection

Action detection plays an important role in high-level video understandi...
research
12/30/2018

Actor Conditioned Attention Maps for Video Action Detection

Interactions with surrounding objects and people contain important infor...
research
07/15/2021

What and When to Look?: Temporal Span Proposal Network for Video Visual Relation Detection

Identifying relations between objects is central to understanding the sc...

Please sign up or login with your details

Forgot password? Click here to reset