HAtt-Flow: Hierarchical Attention-Flow Mechanism for Group Activity Scene Graph Generation in Videos

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chappa, Naga VS Raviteja, Nguyen, Pha, Le, Thi Hoang Ngan, Luu, Khoa
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917811424591872
author Chappa, Naga VS Raviteja
Nguyen, Pha
Le, Thi Hoang Ngan
Luu, Khoa
author_facet Chappa, Naga VS Raviteja
Nguyen, Pha
Le, Thi Hoang Ngan
Luu, Khoa
contents Group Activity Scene Graph (GASG) generation is a challenging task in computer vision, aiming to anticipate and describe relationships between subjects and objects in video sequences. Traditional Video Scene Graph Generation (VidSGG) methods focus on retrospective analysis, limiting their predictive capabilities. To enrich the scene understanding capabilities, we introduced a GASG dataset extending the JRDB dataset with nuanced annotations involving \textit{Appearance, Interaction, Position, Relationship, and Situation} attributes. This work also introduces an innovative approach, \textbf{H}ierarchical \textbf{Att}ention-\textbf{Flow} (HAtt-Flow) Mechanism, rooted in flow network theory to enhance GASG performance. Flow-Attention incorporates flow conservation principles, fostering competition for sources and allocation for sinks, effectively preventing the generation of trivial attention. Our proposed approach offers a unique perspective on attention mechanisms, where conventional "values" and "keys" are transformed into sources and sinks, respectively, creating a novel framework for attention-based models. Through extensive experiments, we demonstrate the effectiveness of our Hatt-Flow model and the superiority of our proposed Flow-Attention mechanism. This work represents a significant advancement in predictive video scene understanding, providing valuable insights and techniques for applications that require real-time relationship prediction in video data.
format Preprint
id arxiv_https___arxiv_org_abs_2312_07740
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle HAtt-Flow: Hierarchical Attention-Flow Mechanism for Group Activity Scene Graph Generation in Videos
Chappa, Naga VS Raviteja
Nguyen, Pha
Le, Thi Hoang Ngan
Luu, Khoa
Computer Vision and Pattern Recognition
Group Activity Scene Graph (GASG) generation is a challenging task in computer vision, aiming to anticipate and describe relationships between subjects and objects in video sequences. Traditional Video Scene Graph Generation (VidSGG) methods focus on retrospective analysis, limiting their predictive capabilities. To enrich the scene understanding capabilities, we introduced a GASG dataset extending the JRDB dataset with nuanced annotations involving \textit{Appearance, Interaction, Position, Relationship, and Situation} attributes. This work also introduces an innovative approach, \textbf{H}ierarchical \textbf{Att}ention-\textbf{Flow} (HAtt-Flow) Mechanism, rooted in flow network theory to enhance GASG performance. Flow-Attention incorporates flow conservation principles, fostering competition for sources and allocation for sinks, effectively preventing the generation of trivial attention. Our proposed approach offers a unique perspective on attention mechanisms, where conventional "values" and "keys" are transformed into sources and sinks, respectively, creating a novel framework for attention-based models. Through extensive experiments, we demonstrate the effectiveness of our Hatt-Flow model and the superiority of our proposed Flow-Attention mechanism. This work represents a significant advancement in predictive video scene understanding, providing valuable insights and techniques for applications that require real-time relationship prediction in video data.
title HAtt-Flow: Hierarchical Attention-Flow Mechanism for Group Activity Scene Graph Generation in Videos
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2312.07740