Discriminative Latent Models for Recognizing Contextual Group Activities

By Tian Lan, Yang Wang, Weilong Yang, S. Robinovitch, Greg Mori. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012

318 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/c08bb983a1eeb5daf21f760eed4b72047e882186

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Xiaogang Wang
2. Wanli Ouyang
3. Yu Kong
4. G. Wang
5. Yun Raymond Fu
6. Bingbing Ni
7. Ronald Poppe
8. Xiaokang Yang

In Computer Vision and Pattern Recognition

1. Luc Van Gool
2. Xiaogang Wang
3. Ming-Hsuan Yang
4. Wanli Ouyang
5. Dacheng Tao
6. Yi Yang
7. Jitendra Malik
8. Bernt Schiele

Citations in the corpus

• Human Action Recognition and Prediction: A Survey (2018, methodology): “The method in [132] also utilizes the idea of hierarchical representation, and studies the col-”
• Learning to Share Latent Tasks for Action Recognition (2013, background): “Among them, discriminative part-based action models [31, 17, 25, 12] attract a lot of attention recently.”
• A Review of Human Activity Recognition Methods (2015, background): “Lan et al. (2012b) recognized group activities, whichwere considered as latent variables, encoding the contextual information in a video sequence.”
• Dyadic Interaction Detection from Pose and Flow (2014, background): “[14] introduce the action context descriptor that encodes both the estimated action performed by the person under focus, and those in his vicinity.”
• Recurrent Modeling of Interaction Context for Collective Activity Recognition (2017, methodology): “We follow the train/test splits as suggested in [22], use the tracklet data provided in [5] and only use five group-level activities for training.”
• Hierarchical Deep Temporal Models for Group Activity Recognition (2016, background): “[16] 79.1 Deep Structured Model [49] 80.6 Our Two-stage Hierarchical Model 81.5 Cardinality kernel [63] 83.4 Ablation studies: In Table 1, the classification results of our proposed architecture is compared with the baselines.”
• Multi-task Recurrent Neural Network for Immediacy Prediction (2015, methodology): “For multi-person pose estimation, some approaches used occlusion status [7] and spatial locations [37, 15, 3] of body parts as pairwise constraints.”
• Spatio-Temporal Dynamic Inference Network for Group Activity Recognition (2021, unknown): “Following works [10, 25, 24, 8, 2] were basically to extract hand-crafted features ( e.g. , HOG [12]) and apply graphical models to infer group activity representations.”