Spacetime Forests with Complementary Features for Dynamic Scene Recognition

38 citations recorded by the source corpus.

How researchers see this paper

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

C3D: Generic Features for Video Analysis (2014, neutral): “Dataset [10] [47] [13] [14] C3D Maryland 43.”
Geometry Guided Convolutional Neural Networks for Self-Supervised Video Representation Learning (2018, methodology): “We compare against both the shallow feature representations [10, 6] and CNN based self-supervised feature leaning approaches [37, 24].”
Bags of Spacetime Energies for Dynamic Scene Recognition (2014, background): “The dominant approach to pooling throughout the dynamic scene recognition literature is that of spatial pyramids [6, 9, 22, 24], which employ predefined hierarchically gridded aggregation regions to capture coarse geometric layout in a multiresolution fashion.”
Self-Supervised Spatio-Temporal Representation Learning for Videos by Predicting Motion and Appearance Statistics (2019, unknown): “Method [10] [8] [43] [27] [12] Ours”
Temporal Residual Networks for Dynamic Scene Recognition (2017, background): “The third best performer, [10], is an ancestor of BoSE and is not considered here.”
Learning Spatiotemporal Features with 3D Convolutional Networks (2014, unknown): “Dataset [4] [41] [8] [9] Imagenet C3D Maryland 43.”