Detecting Irregularities in Images and in Video

By Oren Boiman, Michal Irani. 2005

704 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

How researchers see this paper

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

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

C3D: Generic Features for Video Analysis (2014, background): “The computer vision community has been working on video analysis for decades and tackled different problems such as action recognition [2, 31, 40], abnormal event detection [3, 7, 55], and activity understanding [29].”
Unstructured human activity detection from RGBD images (2011, methodology): “We have also made the dataset and code available open-source at: http://pr.cs.cornell.edu/humanactivities”
The Interestingness of Images (2013, methodology): “It is inspired by the work of Boiman and Irani for the detection irregularities in images and videos [4].”
Violent flows: Real-time detection of violent crowd behavior (2012, background): “Boiman and Irani proposed an approach for detecting unexpected events in videos by using a data-driven approach [6].”
Context-aware saliency detection (2010, background): “Comparison of our saliency to the irregularity detection algorithm of [5].”
Matching Local Self-Similarities across Images and Videos (2007, methodology): “To find a good match for the “ensemble of descriptors” of F within G, we use a modified version of the efficient “ensemble matching” algorithm of [3].”
A Hierarchical Model of Shape and Appearance for Human Action Classification (2007, background): “Spatial-temporal features have shown particular promise in motion understanding due to its rich descriptive power [3, 14, 17].”
Dense-Captioning Events in Videos (2017, methodology): “In an effort to start describing videos, methods in video summarization aimed to congregate segments of videos that include important or interesting visual information [62, 59, 16, 3].”
The Generalized PatchMatch Correspondence Algorithm (2010, background): “Moreover, many analysis applications [8–11] and synthesis applications [12–15] inherently require dense global correspondences for adequate performance.”
Retrieving actions in movies (2007, methodology): “These methods often rely on external localization of people prior to action recognition with exception to [16, 3, 17].”
DL-SFA: Deeply-Learned Slow Feature Analysis for Action Recognition (2014, background): “Recognizing human action in realistic videos is challenging while has widespread applications, including unusual activity detection [22], human computer interactions [5] and so forth.”
Adversarially Learned One-Class Classifier for Novelty Detection (2018, background): “IBC [6] 13% RE [36] 15% MPCCA [19] 30% Ravanbakhsh et al.”
Visual attention detection in video sequences using spatiotemporal cues (2006, background): “Bioman and Irani [2] have proposed a spatiotemporal irregularity detection in videos.”
Image Completion Using Efficient Belief Propagation Via Priority Scheduling and Dynamic Pruning (2007, methodology): “techniques that have been proposed were valid only for restricted classes of MRFs [30], [ 31 ].”
Lattice Long Short-Term Memory for Human Action Recognition (2017, background): “mal activity detection [3], human computer interaction (HCI) [6] and so forth.”
Anomaly detection in extremely crowded scenes using spatio-temporal motion pattern models (2009, background): “The modeling of motion within spatio-temporal volumes has been limited to volume distance [5, 15] or interest points [11], enforcing an explicit detection model.”
Spatio-temporal Matching for Human Detection in Video (2014, neutral): “, [2]) and marker-less motion capture (e.”