Moving vistas: Exploiting motion for describing scenes

By Nitesh Shroff, Pavan K. Turaga, Ramalingam Chellappa. 2010

100 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

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

In Computer Vision and Pattern Recognition

Citations in the corpus

C3D: Generic Features for Video Analysis (2014, methodology): “We evaluate C3D features on two scene recognition benchmarks: YUPENN [10] and Maryland [42].”
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.”
A Comprehensive Look at Coding Techniques on Riemannian Manifolds (2018, methodology): “RECOGNITION ACCURACIES IN % FOR THE MARYLAND [30], DYNTEX++ [12], AND YTC [23] DATA SETS”
Dynamic scene understanding: The role of orientation features in space and time in scene classification (2012, methodology): “Maryland “in-the-wild” scenes data set [30].”
Dynamic Scene Classification: Learning Motion Descriptors with Slow Features Analysis (2013, methodology): “Scenes HOF [23, 9] GIST [26, 9] Chaos [29] SOE [9] [35] SFA Embedding No SFA Our Model Avalange 0 10 30 10 80 90 90 Boiling.”
Learning Spatiotemporal Features with 3D Convolutional Networks (2014, methodology): “YUPENN consists of 420 videos of 14 scene categories and Maryland has 130 videos of 13 scene categories.”
Spacetime Forests with Complementary Features for Dynamic Scene Recognition (2013, background): “The final class distributions at the leaves are calculated as the ratio between the number of feature vectors of each class and the total number of features which reach the leaf after training.”
Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks (2017, background): “P3D ResNet outperforms the state-of-the-art hand-crafted features [5] by 16.9% and 3.3% on Dynamic Scene and YUPENN benchmark, respectively.”
Temporal Residual Networks for Dynamic Scene Recognition (2017, methodology): “Video-based dynamic scene classification has been approached based on linear dynamical systems [7], chaotic invariants [34], local measures of spatiotemporal orientation [5, 10, 11], slowly varying spatial orientations [42] and spatiotemporal ConvNets [44], with spatiotemporal orientation and ConvNe”