Skip to search formSkip to main contentSkip to account menu
DOI:10.1109/TMM.2024.3349923 - Corpus ID: 266781096
@article{Wu2024LearningLS, title={Learning Label Semantics for Weakly Supervised Group Activity Recognition}, author={Lifang Wu and Meng-Syue Tian and Ye Xiang and Ke Gu and Ge Shi}, journal={IEEE Transactions on Multimedia}, year={2024}, volume={26}, pages={6386-6397}, url={https://api.semanticscholar.org/CorpusID:266781096}}
- Lifang Wu, Meng-Syue Tian, Ge Shi
- Published in IEEE transactions on… 2024
- Computer Science
This article investigates the hierarchical structure inherent in group-level labels to extract the fine-grained semantics without using detectors for weakly supervised group activity recognition by employing the multi-label classification and integrating the scores of hierarchical activity labels.
Figures and Tables from this paper
- figure 1
- figure 2
- figure 3
- figure 4
- figure 5
- figure 6
- figure 7
- figure 8
- figure 9
- table I
- table II
- table III
- table IV
- table IX
- table V
- table VI
- table VII
- table VIII
Topics
Semantic Decoder (opens in a new tab)Group Activity Recognition (opens in a new tab)Complex Scenes (opens in a new tab)Hierarchical Structure (opens in a new tab)Label Semantic Embeddings (opens in a new tab)Weakly-supervised (opens in a new tab)Benchmarks (opens in a new tab)Volleyball Dataset (opens in a new tab)Semantic Encoder (opens in a new tab)Multi-Label Classification (opens in a new tab)
57 References
- Dongkeun KimJin S. LeeMinsu ChoSuha Kwak
- 2022
Computer Science
2022 IEEE/CVF Conference on Computer Vision and…
This work proposes a novel model for group activity recognition that depends neither on bounding box labels nor on object detector, and localizes and encodes partial contexts of a group activity by leveraging the attention mechanism, and represents a video clip as a set of partial context embeddings.
- 26
- Highly Influential[PDF]
- Hangjie YuanD. Ni
- 2021
Computer Science
AAAI
This paper proposes a new reasoning paradigm to incorporate global contextual information, Transformer based Context Encoding (TCE) module, which enhances individual representation by encodingglobal contextual information to individual features and refining the aggregated information.
- 43
- PDF
- Peizhen ZhangYongyi TangJianfang HuWeishi Zheng
- 2020
Computer Science
IEEE Transactions on Image Processing
A fast weakly supervised deep learning architecture for collective activity recognition and a latent embedding scheme for mining person-group interactive relationship to get rid of the use of any pairwise relation between people and the individual action labels as well are proposed.
- 33
- Lifang WuXianglong LangYe XiangChang Wen ChenZun LiZhuming Wang
- 2023
Computer Science
IEEE Transactions on Circuits and Systems for…
This framework is designed to locate active spatial positions and use them as visual tokens to infer the relations for token embeddings and demonstrates that the proposed framework is competitive against existing schemes that require more laboring and computation to generate labels.
- 4
- Highly Influential
- Rui YanLingxi XieJinhui TangXiangbo ShuQi Tian
- 2020
Computer Science
ECCV
This paper presents a new task named weakly-supervised group activity recognition (GAR) which differs from conventional GAR tasks in that only video-level labels are available, yet the important…
- 68
- Highly Influential[PDF]
- Jianchao WuLimin WangLi WangJie GuoGangshan Wu
- 2019
Computer Science
2019 IEEE/CVF Conference on Computer Vision and…
This paper proposes to build a flexible and efficient Actor Relation Graph (ARG) to simultaneously capture the appearance and position relation between actors, and performs extensive experiments on two standard group activity recognition datasets.
- 200
- Highly Influential[PDF]
- Zhao-Min ChenQuan CuiXiu-Shen WeiXin JinYanwen Guo
- 2021
Computer Science
IEEE Transactions on Multimedia
A unified deep learning framework to Disentangle, Embed and Rank the corresponding label cues and proposes an embedding operation from a metric learning perspective to pull the relevant label vectors together and push irrelevant label vectors away.
- 15
- Guyue HuBo CuiYuan HeShan Yu
- 2020
Computer Science
2020 IEEE/CVF Conference on Computer Vision and…
A novel method based on deep reinforcement learning to progressively refine the low-level features and high-level relations of group activities and construct a semantic relation graph (SRG) to explicitly model the relations among persons.
- 67 [PDF]
- Zhiwei DengArash VahdatHexiang HuGreg Mori
- 2016
Computer Science
2016 IEEE Conference on Computer Vision and…
A method to integrate graphical models and deep neural networks into a joint framework that uses a sequential inference modeled by a recurrent neural network and demonstrates the potential of this model to handle highly structured learning tasks.
- 230 [PDF]
- Zhao-Min ChenXiu-Shen WeiPeng WangYanwen Guo
- 2019
Computer Science
2019 IEEE/CVF Conference on Computer Vision and…
This work proposes a multi-label classification model based on Graph Convolutional Network (GCN), and proposes a novel re-weighted scheme to create an effective label correlation matrix to guide information propagation among the nodes in GCN.
- 856 [PDF]
...
...
Related Papers
Showing 1 through 3 of 0 Related Papers
TABLE III COMPARISON WITH STATE-OF-THE-ART SCHEMES ON VD AND CAD
Published in IEEE transactions on multimedia 2024
Learning Label Semantics for Weakly Supervised Group Activity Recognition
Lifang WuMeng-Syue TianYe XiangKe GuGe Shi
Figure 12 of 18