The Pascal Visual Object Classes (VOC) Challenge

Everingham, Mark; Gool, Luc Van; Williams, Christopher; Winn, John; Zisserman, Andrew

doi:10.1007/s11263-009-0275-4

Cited by 17,471 publications

(12,276 citation statements)

References 51 publications

Supporting

Mentioning

11,504

Contrasting

Unclassified

Order By: Relevance

“…Thus for clarity we only present the results using RBF kernels. To facilitate comparisons with the Hollywood 1 and 2 datasets, the Average Precision (AP) measure was used, as explained in the PAS-CAL VOC (Everingham et al 2010). Relevant source code is available online along with the data (Hadfield and Bowden).…”

Section: Fig 9hmentioning

confidence: 99%

Hollywood 3D: What are the Best 3D Features for Action Recognition?

2016

View full text Add to dashboard Cite

Action recognition "in the wild" is extremely challenging, particularly when complex 3D actions are projected down to the image plane, losing a great deal of information. The recent growth of 3D data in broadcast content and commercial depth sensors, makes it possible to overcome this. However, there is little work examining the best way to exploit this new modality. In this paper we introduce the Hollywood 3D benchmark, which is the first dataset containing "in the wild" action footage including 3D data. This dataset consists of 650 stereo video clips across 14 action classes, taken from Hollywood movies. We provide stereo calibrations and depth reconstructions for each clip. We also provide an action recognition pipeline, and propose a number of specialised depth-aware techniques including five interest point detectors and three feature descriptors. Extensive tests allow evaluation of different appearance and depth encoding schemes. Our novel techniques exploiting this depth allow us to reach performance levels more than triple those of the best baseline algorithm using only appearance information. The benchmark data, code and calibrations are all made available to the community.

show abstract

Section: Fig 9hmentioning

confidence: 99%

Hollywood 3D: What are the Best 3D Features for Action Recognition?

2016

View full text Add to dashboard Cite

show abstract

“…A star-structured deformable part method was proposed by Felzenszwalb et al (2010) in which latent support vector machines are employed for classification. The part-based method uses HOG features for image representation and yields excellent performance on the PAS-CAL VOC datasets (Everingham et al, 2010), especially on the person category. Recently (Khan et al, 2012a) proposed augmenting the standard part-based approach with color information, which results in significant improvement in performance.…”

Section: Related Workmentioning

confidence: 99%

“…The deformable part-based approach yields stateof-the-art results for generic object and person detection (Everingham et al, 2010). Here we investigate this approach for the task of action detection.…”

Section: Coloring Action Detectionmentioning

confidence: 99%

Coloring Action Recognition in Still Images

et al. 2013

View full text Add to dashboard Cite

In this article we investigate the problem of human action recognition in static images. By action recognition we intend a class of problems which includes both action classification and action detection (i.e. simultaneous localization and classification). Bagof-words image representations yield promising results for action classification, and deformable part models perform very well object detection. The representations for action recognition typically use only shape cues and ignore color information. Inspired by the recent success of color in image classification and object detection, we investigate the potential of color for action classification and detection in static images.We perform a comprehensive evaluation of color descriptors and fusion approaches for action recognition. Experiments were conducted on the three datasets most used for benchmarking action recognition in still images: Willow, PASCAL VOC 2010 and Stanford-40. Our experiments demonstrate that incorporating color information considerably improves recognition performance, and that a descriptor based on color names outperforms pure color descriptors. Our experiments demonstrate that late fusion of color and shape information outperforms other approaches on action recognition. Finally, we show that the different color-shape fusion approaches result in complementary information and combining them yields state-of-the-art performance for action classification.

show abstract

“…We use the road surveillance dataset and the gate entrance dataset built by Industrial Technology Research In- We evaluate the object detection performance via the average precision (AP) of precision-recall curves as in [12]. We evaluate the final foreground detection output with the F1 measure, computed as follows.…”

Section: Experiments Datasetmentioning

confidence: 99%

Joint optimization of background subtraction and object detection for night surveillance

Lin

et al. 2011

2011 18th IEEE International Conference on Image Processing

View full text Add to dashboard Cite

Detecting foreground objects for night surveillance videos remains a challenging problem in scene understanding. Though many efforts have been made for robust background subtraction and robust object detection respectively, the complex illumination condition in night scenes makes it hard to solve each of these tasks individually. In practice, we see these two tasks are coupled and can be combined to help each other. In this work, we apply a recently proposed algorithm -Feedback Enabled Cascaded Classification Models (FECCM) -to combine the background subtraction task and the object detection task into a generic framework. The proposed framework treats each classifier for the respective task as a 'blackbox', thus allows the usage of most existing algorithms as one of the classifiers. Experiment results show that the proposed method outperforms a state-of-the-art background subtraction method and a state-of-the-art object detection method.

show abstract

The Pascal Visual Object Classes (VOC) Challenge

Cited by 17,471 publications

References 51 publications

Hollywood 3D: What are the Best 3D Features for Action Recognition?

Hollywood 3D: What are the Best 3D Features for Action Recognition?

Coloring Action Recognition in Still Images

Joint optimization of background subtraction and object detection for night surveillance

Contact Info

Product

Resources

About