Please wait a minute...
Frontiers of Computer Science

ISSN 2095-2228

ISSN 2095-2236(Online)

CN 10-1014/TP

邮发代号 80-970

2019 Impact Factor: 1.275

Frontiers of Computer Science  2024, Vol. 18 Issue (6): 186351   https://doi.org/10.1007/s11704-024-40027-3
  本期目录
FIFAWC: a dataset with detailed annotation and rich semantics for group activity recognition
Duoxuan PEI1, Di HUANG1(), Yunhong WANG2
1. State Key Laboratory of Software Development Environment, School of Computer Science and Engineering,Beihang University, Beijing 100191, China
2. Intelligent Recognition and Image Processing Lab., School of Computer Science and Engineering,Beihang University, Beijing 100191, China
 全文: PDF(1312 KB)   HTML
收稿日期: 2024-01-06      出版日期: 2024-06-06
Corresponding Author(s): Di HUANG   
 引用本文:   
. [J]. Frontiers of Computer Science, 2024, 18(6): 186351.
Duoxuan PEI, Di HUANG, Yunhong WANG. FIFAWC: a dataset with detailed annotation and rich semantics for group activity recognition. Front. Comput. Sci., 2024, 18(6): 186351.
 链接本文:  
https://academic.hep.com.cn/fcs/CN/10.1007/s11704-024-40027-3
https://academic.hep.com.cn/fcs/CN/Y2024/V18/I6/186351
Dataset #Videos #Instances Scenario Anno. type Labeling level
CAD [1] 44 ≈ 2,500 Pedestrian Single GA Word
VD [4] 55 4,830 Volleyball Single GA Word
VT [5] 12 4,960 Volleyball Single GA Word
NBA [6] 55 9,172 Basketball Single GA Word
Ours 64 5,196 Soccer Multi GAs Word & Sen.
Tab.1  
Fig.1  
Method MSA↑ Shoot Score Foul Contest Celebrate MPCA↑
ARG [8] 51.0 69.3 87.6 93.9 80.1 98.2 85.8
DFWSGAR [9] 57.0 92.1 87.4 93.8 84.2 98.1 91.1
Tab.2  
Method FT BLEU4↑ CIDEr↑ METEOR↑ ROUGE-L↑
PDVC [7] × 0.9 0.7 4.6 13.3
PDVC [7] 7.0 8.3 9.9 24.5
VTimeLLM [10] × 1.6 2.0 5.1 15.5
Tab.3  
1 Choi W, Shahid K, Savarese S. What are they doing?: Collective activity classification using spatio-temporal relationship among people. In: Proceedings of the 12th IEEE International Conference on Computer Vision Workshops. 2009, 1282–1289
2 Choi W, Shahid K, Savarese S. Learning context for collective activity recognition. In: Proceedings of the Computer Vision & Pattern Recognition. 2011, 3273–3280
3 W, Choi S Savarese . A unified framework for multi-target tracking and collective activity recognition. In: Proceedings of the 12th European Conference on Computer Vision. 2012, 215–230
4 M S, Ibrahim S, Muralidharan Z, Deng A, Vahdat G Mori . A hierarchical deep temporal model for group activity recognition. In: Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. 2016, 1971–1980
5 L, Kong D, Pei R, He D, Huang Y Wang . Spatio-temporal player relation modeling for tactic recognition in sports videos. IEEE Transactions on Circuits and Systems for Video Technology, 2022, 32( 9): 6086–6099
6 R, Yan L, Xie J, Tang X, Shu Q Tian . Social adaptive module for weakly-supervised group activity recognition. In: Proceedings of the 16th European Conference on Computer Vision. 2020, 208–224
7 R, Luo G, Shakhnarovich S, Cohen B Price . Discriminability objective for training descriptive captions. In: Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2018, 6964–6974
8 J, Wu L, Wang L, Wang J, Guo G Wu . Learning actor relation graphs for group activity recognition. In: Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2019, 9964–9974
9 D, Kim J, Lee M, Cho S Kwak . Detector-free weakly supervised group activity recognition. In: Proceedings of 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2022, 20083–20093
10 B, Huang X, Wang H, Chen Z, Song W Zhu . VTimeLLM: empower LLM to grasp video moments. 2023, arXiv preprint arXiv: 2311.18445
[1] Highlights Download
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed