IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, VOL., NO. 1 Hidden Part Models for Human Action Recognition: Probabilistic vs. Max-Margin

Citations in the corpus

• Actions ~ Transformations (2015, background): “Mid-to high-level representation are also used to model complex actions [41, 55, 36, 60, 14, 24].”
• Similarity Constrained Latent Support Vector Machine: An Application to Weakly Supervised Action Classification (2012, unknown): “A standard method for learning parameters to such a model is the latent SVM [1, 17] or max-margin hCRF [16].”
• Combing RGB and Depth Map Features for human activity recognition (2012, unknown): “Roughly, we divide activity recognition techniques into four categories, Bag-of-Features/SVM (BoF/SVM) approaches [10], Deformable Part Models (DPM) approaches[19], silhouette representation [2], feature trajectories [18].”
• Activity representation with motion hierarchies (2013, unknown): “Discriminative alternatives to these generative models, e.g. , [Bilen et al, 2011, Liu et al, 2011, Niebles et al, 2010, Raptis et al, 2012, Tang et al, 2012, Wang and Mori, 2011], often use techniques related to the popular deformable part model of Felzenszwalb et al [2010].”
• Videos as Space-Time Region Graphs (2018, background): “For example, a large effort has been spent on manually designing the video features [22,23,24,25,26,27,28,29,30,31].”