Filters








18 Hits in 2.6 sec

stagNet: An Attentive Semantic RNN for Group Activity and Individual Action Recognition

Mengshi Qi, Yunhong Wang, Jie Qin, Annan Li, Jiebo Luo, Luc Van Gool
2019 IEEE transactions on circuits and systems for video technology (Print)  
In the paper, we present a novel attentive semantic recurrent neural network (RNN), namely stagNet, for understanding group activities and individual actions in videos, by combining the spatio-temporal  ...  Moreover, we adopt a spatio-temporal attention model to focus on key persons/frames for improved recognition performance.  ...  In this paper, we present a novel attentive semantic recurrent neural network, called stagNet for group activity and personal action recognition, which combines spatial-temporal attention and semantic  ... 
doi:10.1109/tcsvt.2019.2894161 fatcat:wcjvyo3wgfbsfcew4x62sw6cfi

Table of contents

2020 IEEE transactions on circuits and systems for video technology (Print)  
Wang 532 stagNet: An Attentive Semantic RNN for Group Activity and Individual Action Recognition ............................ .....................................................................  ...  Wen 468 HeadNet: An End-to-End Adaptive Relational Network for Head Detection ................................................ .......................................................................  ... 
doi:10.1109/tcsvt.2020.2965812 fatcat:g3s3nehpzvci5bf3pf2hfilcky

Progressive Relation Learning for Group Activity Recognition

Guyue Hu, Bo Cui, Yuan He, Shan Yu
2020 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
Therefore, effectively modeling the group-relevant and suppressing the irrelevant actions (and interactions) are vital for group activity recognition.  ...  Another relation-gating (RG) agent in continuous action space adjusts the high-level semantic graph to pay more attention to group-relevant relations.  ...  The Volleyball dataset is currently the largest dataset for group activity recognition. It contains 4830 clips of 55 volleyball videos.  ... 
doi:10.1109/cvpr42600.2020.00106 dblp:conf/cvpr/HuCHY20 fatcat:5k4i73tfgjdpvfpbmdqp6om2s4

Progressive Relation Learning for Group Activity Recognition [article]

Guyue Hu, Bo Cui, Yuan He, Shan Yu
2020 arXiv   pre-print
Therefore, effectively modeling the group-relevant and suppressing the irrelevant actions (and interactions) are vital for group activity recognition.  ...  Another relation-gating (RG) agent in continuous action space adjusts the high-level semantic graph to pay more attention to group-relevant relations.  ...  The Volleyball dataset is currently the largest dataset for group activity recognition. It contains 4830 clips of 55 volleyball videos.  ... 
arXiv:1908.02948v2 fatcat:al5whddoszgyhbwhpvzafko4uq

Learning Actor Relation Graphs for Group Activity Recognition [article]

Jianchao Wu, Limin Wang, Li Wang, Jie Guo, Gangshan Wu
2019 arXiv   pre-print
We also visualize the learned actor graphs and relation features, which demonstrate that the proposed ARG is able to capture the discriminative relation information for group activity recognition.  ...  We perform extensive experiments on two standard group activity recognition datasets: the Volleyball dataset and the Collective Activity dataset, where state-of-the-art performance is achieved on both  ...  group activity recognition.  ... 
arXiv:1904.10117v1 fatcat:mzl6ovx3hzfjpf2h2wqjbk5un4

Learning Actor Relation Graphs for Group Activity Recognition

Jianchao Wu, Limin Wang, Li Wang, Jie Guo, Gangshan Wu
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
We also visualize the learned actor graphs and relation features, which demonstrate that the proposed ARG is able to capture the discriminative relation information for group activity recognition.  ...  We perform extensive experiments on two standard group activity recognition datasets: the Volleyball dataset and the Collective Activity dataset, where state-of-the-art performance is achieved on both  ...  group activity recognition.  ... 
doi:10.1109/cvpr.2019.01020 dblp:conf/cvpr/WuWWGW19 fatcat:v7mkrsbjd5e7vl3zh7p5mw4n5a

Joint Learning of Social Groups, Individuals Action and Sub-group Activities in Videos [article]

Mahsa Ehsanpour, Alireza Abedin, Fatemeh Saleh, Javen Shi, Ian Reid, Hamid Rezatofighi
2020 arXiv   pre-print
traditional group activity recognition task (assuming individuals of the scene form a single group and predicting a single group activity label for the scene); iii) we introduce new annotations on an existing  ...  group activity dataset, re-purposing it for the social task.  ...  In order to consider the spatial relation between the individuals in the scene, an attentive semantic RNN has been proposed in [44] for understanding group activities.  ... 
arXiv:2007.02632v2 fatcat:uj2ngaprvjfujhvuopuqdd6rbu

Distribution Based Crowd Abnormality Detection

2019 VOLUME-8 ISSUE-10, AUGUST 2019, REGULAR ISSUE  
Furthermore, utilize the standard method for classification by considering SVMs (Support Vector Machines) discriminative learning method to recognize the abnormalities.  ...  In paper [16] , they represent RNN (Recurrent Neural Network), also known as stagNet, for better understanding of the individual actions and the group activities in image fame by joining the mechanism  ...  of Spatio-temporal-attention and also modeling the semantic graph.  ... 
doi:10.35940/ijitee.a3977.119119 fatcat:5zyxrjgo2vcg5pqx3p7lvvbdeu

Spatio-Temporal Dynamic Inference Network for Group Activity Recognition [article]

Hangjie Yuan, Dong Ni, Mang Wang
2021 arXiv   pre-print
Group activity recognition aims to understand the activity performed by a group of people. In order to solve it, modeling complex spatio-temporal interactions is the key.  ...  Acknowledgement: We would like to thank Jiayang Ren, Rong Jin and anonymous reviewers for their valuable feedback. This work was supported by the National Science Foundation China grant No. U1609213.  ...  Related Work Group Activity Recognition Group activity recognition was firstly proposed in [9] .  ... 
arXiv:2108.11743v1 fatcat:xt43rxhtmfetjioo5bifdigvdy

Multi-Perspective Representation to Part-Based Graph for Group Activity Recognition

Lifang Wu, Xianglong Lang, Ye Xiang, Qi Wang, Meng Tian
2022 Sensors  
Group activity recognition that infers the activity of a group of people is a challenging task and has received a great deal of interest in recent years.  ...  Different from individual action recognition, group activity recognition needs to model not only the visual cues of individuals but also the relationships between them.  ...  An overview of the proposed framework for group activity recognition. It consists of two branches for modeling the static and dynamic representations.  ... 
doi:10.3390/s22155521 pmid:35898025 fatcat:3czi2llswrehpdfxxxbpzjexky

Hunting Group Clues with Transformers for Social Group Activity Recognition [article]

Masato Tamura, Rahul Vishwakarma, Ravigopal Vennelakanti
2022 arXiv   pre-print
This paper presents a novel framework for social group activity recognition.  ...  As an expanded task of group activity recognition, social group activity recognition requires recognizing multiple sub-group activities and identifying group members.  ...  We design our method in such a way that the attention modules identify and then aggregate features relevant to social group activities, generating an effective feature for each social group.  ... 
arXiv:2207.05254v1 fatcat:dbsn5niz3ncybp3nhgjiadwgfa

A Grid-based Representation for Human Action Recognition [article]

Soufiane Lamghari, Guillaume-Alexandre Bilodeau, Nicolas Saunier
2020 arXiv   pre-print
In this paper, we propose a novel method for human action recognition that encodes efficiently the most discriminative appearance information of an action with explicit attention on representative pose  ...  However, most of existing approaches for action recognition rely on information that is not always relevant for this task, and are limited in the way they fuse the temporal information.  ...  We thank NVIDIA Corporation for their donation of a Titan Xp GPU card.  ... 
arXiv:2010.08841v2 fatcat:iublzset45gxpdsmukvsedptjm

An overview of Human Action Recognition in sports based on Computer Vision

Kristina Host, Marina Ivašić-Kos
2022 Heliyon  
Human Action Recognition (HAR) is a challenging task used in sports such as volleyball, basketball, soccer, and tennis to detect players and recognize their actions and teams' activities during training  ...  Therefore, this paper presents an overview of HAR applications in sports primarily based on Computer Vision as the main contribution, along with popular publicly available datasets for this purpose.  ...  The authors presented an attention semantic RNN, called stagNet, for understanding group activities and individual actions in videos, by combining the Spatio-temporal attention mechanism and semantic graph  ... 
doi:10.1016/j.heliyon.2022.e09633 pmid:35706961 pmcid:PMC9189896 fatcat:5o4x4ywsanfcfo6wvkoc2g6lym

A Comprehensive Review of Group Activity Recognition in Videos

Li-Fang Wu, Qi Wang, Meng Jian, Yu Qiao, Bo-Xuan Zhao
2021 International Journal of Automation and Computing  
From this comprehensive literature review, readers can obtain an overview of progress in group activity recognition for future studies.  ...  AbstractHuman group activity recognition (GAR) has attracted significant attention from computer vision researchers due to its wide practical applications in security surveillance, social role understanding  ...  [61] proposed an attentive semantic recurrent neural network, namely stagNet. A semantic graph is built from word labels and visual data.  ... 
doi:10.1007/s11633-020-1258-8 fatcat:ycka4thcy5a6vghpenpthtrndi

Detector-Free Weakly Supervised Group Activity Recognition [article]

Dongkeun Kim, Jinsung Lee, Minsu Cho, Suha Kwak
2022 arXiv   pre-print
Motivated by this, we propose a novel model for group activity recognition that depends neither on bounding box labels nor on object detector.  ...  Group activity recognition is the task of understanding the activity conducted by a group of people as a whole in a multi-person video.  ...  Conclusion We have presented a detector-free method for weakly supervised group activity recognition, which first embeds the partial contexts of an activity through the attention mechanism, then aggregates  ... 
arXiv:2204.02139v1 fatcat:64gp6rrlfrdo3nptrpess65vya
« Previous Showing results 1 — 15 out of 18 results