Detection Evolution with Multi-order Contextual Co-occurrence

By Guang Chen, Yuanyuan Ding, Jing Xiao, Tony X. Han. 2013

91 citations recorded by the source corpus.

Subfields: 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 Computer Vision and Pattern Recognition

Citations in the corpus

Learning Non-maximum Suppression (2017, methodology): “Some methods improve object detection by jointly rescoring detections locally [30, 4] or globally [31] using image information.”
Real-Time Pedestrian Detection with Deep Network Cascades (2015, background): “A wide variety of methods have been applied to pedestrian detection over the years, with continued improvement in performance [4, 5, 6, 7, 9, 10, 12, 13, 33, 38, 39, 42].”
A Convnet for Non-maximum Suppression (2015, methodology): “We adopt from Stewart & Andriluka (2015) the idea of computing the loss by matching detections to annotations, but instead of regressing bounding boxes at every location we predict new detection scores that are high for matched detections and low everywhere else.”
Scale-Aware Fast R-CNN for Pedestrian Detection (2015, methodology): “A multi-order context representation was used in [6] to ex-”
Non-maximum Suppression for Object Detection by Passing Messages Between Windows (2014, methodology): “In [18], the authors also adopt an iterative procedure.”
Single-Pedestrian Detection Aided by Multi-pedestrian Detection (2013, methodology): “context [9], [18], [62], [92] or motion [18], [80] is used by these approaches.”
Pedestrian detection with a Large-Field-Of-View deep network (2015, unknown): “13 1 Inria MOCO[42] 45.”
COSTA: Co-Occurrence Statistics for Zero-Shot Classification (2014, methodology): “They have been used to improve image segmentation [11], object detection [3, 22], to reason about what to expect in a scene [4, 14], and for image and attribute classification [8, 15].”
Multiview random forest of local experts combining RGB and LIDAR data for pedestrian detection (2015, unknown): “A common approach is to detect pedestrians independently in the 3D cloud of points and in the visible spectrum images, and then combining the detections using an appropriate strategy [18], [19], [22].”
Ten Years of Pedestrian Detection, What Have We Learned? (2014, unknown): “Strategies for exploiting context include: ground plane constraints ( MultiResC [33], Rand-Forest [30]), variants of auto-context [49] ( MOCO [36]), other category detectors ( MT-DPM+Context [39]), and person-to-person patterns ( DBN−Mut [34], +2Ped [35], JointDeep [40]) .”
On-Board Object Detection: Multicue, Multimodal, and Multiview Random Forest of Local Experts (2017, background): “Context features have also been seen to aid [17], [18] and could be easily integrated as well.”
Pedestrian detection aided by deep learning semantic tasks (2014, background): “[4] modeled the context information in a multi-order manner.”