Deep Structured Models For Group Activity Recognition

Deng, Zhiwei; Zhai, Mengyao; Chen, Lei; Liu, Yuhao; Muralidharan, Srikanth; Roshtkhari, Mehrsan Javan; Mori, Greg

doi:10.5244/c.29.179

Cited by 60 publications

(55 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Considering the recent success of deep neural networks in the field of computer vision, various works studied the group activity recognition using deep learning. Deng et al [7] produces unary potentials using CNN classifiers and develops a neural network that performs message passing to refine the initial predictions. In [6], message passing is performed in a graph with the person and group nodes by a Recurrent Neural Networks (RNN).…”

Section: Group Activity Recognitionmentioning

confidence: 99%

See 1 more Smart Citation

Convolutional Relational Machine for Group Activity Recognition

Azar

Atigh

Nickabadi

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

108

View full text Add to dashboard Cite

We present an end-to-end deep Convolutional Neural Network called Convolutional Relational Machine (CRM) for recognizing group activities that utilizes the information in spatial relations between individual persons in image or video. It learns to produce an intermediate spatial representation (activity map) based on individual and group activities. A multi-stage refinement component is responsible for decreasing the incorrect predictions in the activity map. Finally, an aggregation component uses the refined information to recognize group activities. Experimental results demonstrate the constructive contribution of the information extracted and represented in the form of the activity map. CRM shows advantages over state-of-the-art models on Volleyball and Collective Activity datasets.

show abstract

Section: Group Activity Recognitionmentioning

confidence: 99%

“…All the ψ t s have the same layers which is different from the layers in φ. Three conv (7) and two conv(1) are used to construct the ψ t . See the supplementary material for the details of these layers.…”

Section: Refinementmentioning

confidence: 99%

Convolutional Relational Machine for Group Activity Recognition

Azar

Atigh

Nickabadi

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

108

View full text Add to dashboard Cite

show abstract

“…Note that [4] models groups of humans in still images. More recently, deep structured models have been used for single group activity [10,14]. While these methods reach satisfying results, their generalization to the multiple activity case is not straightforward.…”

Section: Related Workmentioning

confidence: 99%

Recognition of Group Activities in Videos Based on Single-and Two-Person Descriptors

Lathuiliere,

Evangelidis,

Horaud

2017

2017 IEEE Winter Conference on Applications of Computer Vision (WACV)

View full text Add to dashboard Cite

Group activity recognition from videos is a very challenging problem that has barely been addressed. We propose an activity recognition method using group context. In order to encode both single-person description and two-person interactions, we learn mappings from highdimensional feature spaces to low-dimensional dictionaries. In particular the proposed two-person descriptor takes into account geometric characteristics of the relative pose and motion between the two persons. Both single-person and two-person representations are then used to define unary and pairwise potentials of an energy function, whose optimization leads to the structured labeling of persons involved in the same activity. An interesting feature of the proposed method is that, unlike the vast majority of existing methods, it is able to recognize multiple distinct group activities occurring simultaneously in a video. The proposed method is evaluated with datasets widely used for group activity recognition, and is compared with several baseline methods.

show abstract

“…In contrast, by utilising features from both the person level and scene level, and further improving the learning process through the proposed GAN based learning framework, the proposed MLS-GAN model has been able to outperform the state-of-the-art models in both considered metrics. [31] 80.6 NA Cardinality Kernel [29] 83.4 81.9 2-layer LSTMs [6] 81.5 80.9 CERN [7] 87.2 88.3…”

Section: Resultsmentioning

confidence: 99%

Multi-level Sequence GAN for Group Activity Recognition

Gammulle

Denman

Sridharan

et al. 2019

Computer Vision – ACCV 2018

View full text Add to dashboard Cite

We propose a novel semi supervised, Multi Level Sequential Generative Adversarial Network (MLS-GAN ) architecture for group activity recognition. In contrast to previous works which utilise manually annotated individual human action predictions, we allow the models to learn it's own internal representations to discover pertinent subactivities that aid the final group activity recognition task. The generator is fed with person-level and scene-level features that are mapped temporally through LSTM networks. Action-based feature fusion is performed through novel gated fusion units that are able to consider long-term dependancies, exploring the relationships among all individual actions, to learn an intermediate representation or 'action code' for the current group activity. The network achieves it's semi-supervised behaviour by allowing it to perform group action classification together with the adversarial real/fake validation. We perform extensive evaluations on different architectural variants to demonstrate the importance of the proposed architecture. Furthermore, we show that utilising both person-level and scene-level features facilitates the group activity prediction better than using only person-level features. Our proposed architecture outperforms current state-of-the-art results for sports and pedestrian based classification tasks on Volleyball and Collective Activity datasets, showing it's flexible nature for effective learning of group activities. 1

show abstract

Deep Structured Models For Group Activity Recognition

Cited by 60 publications

References 23 publications

Convolutional Relational Machine for Group Activity Recognition

Convolutional Relational Machine for Group Activity Recognition

Recognition of Group Activities in Videos Based on Single-and Two-Person Descriptors

Multi-level Sequence GAN for Group Activity Recognition

Contact Info

Product

Resources

About