Event-based analysis of video

By Lihi Zelnik-Manor, Michal Irani. Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001, 2001

512 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Signal Processing

View Paper: https://www.semanticscholar.org/paper/cef1a7aab17a1e4c7e7abdc027c7706287d6edad

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

In Signal Processing

Citations in the corpus

Recognizing human actions: a local SVM approach (2004, background): “…are i) local features described by spatio-temporal jets l (2) of order four (LF), ii) 128-bin histograms of local features (HistLF), see Section 2 and iii) marginalized histograms of normalized spatio-temporal gradients (HistSTG) computed at 4 temporal scales of a temporal pyramid [15].”
Retrieving actions in movies (2007, methodology): “A number of methods exploit motion descriptors in the regions of actions [25, 27, 6, 16, 3, 17].”
A survey of video datasets for human action and activity recognition (2013, background): “Finally, Section 5 presents the conclusion of this survey.”
Human Action Recognition With Video Data: Research and Evaluation Challenges (2014, background): “This is the primary reason why many researchers create their own dataset for evaluation [34], [35], [79], [103], [119], [126].”
Actions as space-time shapes (2005, unknown): “Some of the recent work done in the area of action recognition [7, 21, 11, 17] have shown that it is useful to analyze actions by looking at the video sequence as a space-time intensity volume.”
Exploring Weak Stabilization for Motion Feature Extraction (2013, background): “Prior work makes different assumptions about which motion types are useful versus nuisance factors.”
Actions as Space-Time Shapes (2007, unknown): “The authors thank Lihi Zelnik-Manor for helpful discussions and her assistance in adjusting the method in [33] for comparison.”
Modeling Activity-Dependent Plasticity in BCM Spiking Neural Networks With Application to Human Behavior Recognition (2011, background): “1045–9227/$26.00 © 2011 IEEE Whereas the results in this paper suggest that the GRNBCM model is very promising for spatiotemporal pattern recognition such as human behavior detection, it should also be pointed that all scenarios in the two datasets used in this paper have only one single moving…”
On Space-Time Interest Points (2005, unknown): “…extents in both space and time (Koenderink, 1988; Lindeberg and Fagerstr¨om, 1996; Florack, 1997; Lindeberg, 1997; Chomat, Martin and Crowley, 2000b; Zelnik-Manor and Irani, 2001), we investigate the behavior of interest points in spatio-temporal scale-space and adapt both the spatial and the…”
Conditional models for contextual human motion recognition (2006, background): “Manor and Irani [ 14 ] represent events using feature histograms at multiple temporal scales and compare different actions using a histogram measure based on X2”
Machine Recognition of Human Activities: A Survey (2008, methodology): “As an extension to this approach, local histograms of normalized ST gradients at several temporal scales are extracted by Zelnik-Manor and Irani [45].”
Unsupervised Activity Perception by Hierarchical Bayesian Models (2007, background): “We do not adopt global motion features ([15, 14]), because in our case multiple activities occur simultaneously and we want to separate single-agent activities from interactions.”
Behavior recognition via sparse spatio-temporal features (2005, methodology): “We implement the algorithms of Efros et al. [5] and Zelnik-Manor and Irani [30], we refer to these as EFROS and ZMI, respectively.”
A survey on activity recognition and behavior understanding in video surveillance (2013, background): “It represents and recognizes simple action like sitting, arm waving, and crouching, etc. Shechtman and Irani [169] avoid explicit flow computation by employing a rank-based constraint directly on the intensity information of spatio-temporal cuboids to enforce consistency between a template and a tar”
Automatic annotation of human actions in video (2009, methodology): “Unsupervised action clustering and localization has been addressed in [24] by means of normalized cuts [16].”
Discovering Motion Primitives for Unsupervised Grouping and One-Shot Learning of Human Actions, Gestures, and Expressions (2013, unknown): “Other holistic representations of actions involve optical flow [32], spatiotemporal gradients [52], and HoG [39].”
Discriminative Subsequence Mining for Action Classification (2007, background): “In [22], Zelnik-Manor and Irani describe features derived from space-time gradients at multiple temporal scales.”
Detecting activities of daily living in first-person camera views (2012, background): “Classic datasets tend to consist of scripted actions [24, 44], though recent work has looked at actions in televised and film footage [27].”
Temporal Localization of Actions with Actoms (2013, unknown): “[4, 6, 7, 10–12 , 38– 45”