The 2005 PASCAL Visual Object Classes Challenge

@inproceedings{Everingham2005The2P,
  title={The 2005 PASCAL Visual Object Classes Challenge},
  author={Mark Everingham and Andrew Zisserman and Christopher K. I. Williams and Luc Van Gool and Moray Allan and Charles M. Bishop and Olivier Chapelle and Navneet Dalal and Thomas Deselaers and Gyuri Dork{\'o} and Stefan Duffner and Jan Eichhorn and Jason D. R. Farquhar and Mario Fritz and Christophe Garcia and Thomas L. Griffiths and Fr{\'e}d{\'e}ric Jurie and Daniel Keysers and Markus Koskela and Jorma T. Laaksonen and Diane Larlus and B. Leibe and Hongying Meng and Hermann Ney and Bernt Schiele and Cordelia Schmid and Edgar Seemann and John Shawe-Taylor and Amos J. Storkey and S{\'a}ndor Szedm{\'a}k and Bill Triggs and ilkay Ulusoy and Ville Viitaniemi and Jianguo Zhang},
  booktitle={MLCW},
  year={2005}
}
The PASCAL Visual Object Classes Challenge ran from February to March 2005. The goal of the challenge was to recognize objects from a number of visual object classes in realistic scenes (i.e. not pre-segmented objects). Four object classes were selected: motorbikes, bicycles, cars and people. Twelve teams entered the challenge. In this chapter we provide details of the datasets, algorithms used by the teams, evaluation criteria, and results achieved. 
The Pascal Visual Object Classes (VOC) Challenge
TLDR
The state-of-the-art in evaluated methods for both classification and detection are reviewed, whether the methods are statistically different, what they are learning from the images, and what the methods find easy or confuse.
Overview of the ImageCLEF 2007 Object Retrieval Task
TLDR
The results of the evaluation show that the object retrieval task of ImageCLEF 2007 was very challenging and that different methods for relevance assessment can have a strong influence on the results of an evaluation.
Semantic Hierarchies for Visual Object Recognition
TLDR
The semantics of image labels are used to integrate prior knowledge about inter-class relationships into the visual appearance learning and to build and train a semantic hierarchy of discriminative classifiers and how to use it to perform object detection.
Learning concepts from visual scenes using a binary probabilistic model
  • N. Bouguila, K. Daoudi
  • Computer Science
    2009 IEEE International Workshop on Multimedia Signal Processing
  • 2009
TLDR
It is shown that this problem can be reduced to a simultaneous weighting of appropriate features and detection of clusters in a binary feature space and a probabilistic model is proposed to quantify the effectiveness of visual words when treated as binary features.
Accurate Object Localization with Shape Masks
TLDR
This paper proposes an approach for object class localization which goes beyond bounding boxes, as it also determines the outline of the object, and directly generates, evaluates and clusters shape masks.
Flexible Object Models for Category-Level 3D Object Recognition
TLDR
This work proposes a novel framework for visual object recognition where object classes are represented by assemblies of partial surface models obeying loose local geometric constraints, and it outperforms the state-of-the-art algorithms for object detection and localization.
Dataset Issues in Object Recognition
TLDR
Current datasets are lacking in several respects, and this paper discusses some of the lessons learned from existing efforts, as well as innovative ways to obtain very large and diverse annotated datasets.
Patch-based Object Recognition Using Discriminatively Trained Gaussian Mixtures
TLDR
An approach using Gaussian mixture models for part-based object recognition where spatial relationships of the parts are explicitly modeled and parameters of the generative model are tuned discriminatively lead to great improvements of the classification accuracy.
Real-Time Moving Object Classification with Automatic Scene Division
TLDR
This work addresses the problem of moving object classification of traffic scene videos into pedestrians, bicycles and vehicles with instead of supervised learning and manual labeling of large training samples, the classifiers are initialized and refined online automatically.
Modeling, representing and learning of visual categories
TLDR
A hybrid approach is developed that makes use of different levels of supervision and consequently achieves better performance by considering unannotated data and extracts structures that combine the mentioned representation paradigms in a single approach.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 61 REFERENCES
Patch-based Object Recognition Using Discriminatively Trained Gaussian Mixtures
TLDR
An approach using Gaussian mixture models for part-based object recognition where spatial relationships of the parts are explicitly modeled and parameters of the generative model are tuned discriminatively lead to great improvements of the classification accuracy.
YEF∗Real-Time Object Detection
TLDR
An improvement to the object detection scheme of Viola and Jones is presented, using the example of face detection, with an improved system which detects faces in quarter-PAL images in only 9 millisecond per image on a 2.4GHz pentium.
A Combined Corner and Edge Detector
The problem we are addressing in Alvey Project MMI149 is that of using computer vision to understand the unconstrained 3D world, in which the viewed scenes will in general contain too wide a
Combined Object Categorization and Segmentation With an Implicit Shape Model
TLDR
Results for articulated objects, which show that the proposed method can categorize and segment unfamiliar objects in differ- ent articulations and with widely varying texture patterns, even under significant partial occlusion.
Unsupervised Learning of Models for Recognition
TLDR
A method to learn object class models from unlabeled and unsegmented cluttered cluttered scenes for the purpose of visual object recognition that achieves very good classification results on human faces and rear views of cars.
Learning to detect objects in images via a sparse, part-based representation
TLDR
A learning-based approach to the problem of detecting objects in still, gray-scale images that makes use of a sparse, part-based representation is developed and a critical evaluation of the approach under the proposed standards is presented.
Learning Generative Visual Models from Few Training Examples: An Incremental Bayesian Approach Tested on 101 Object Categories
Discriminative training for object recognition using image patches
TLDR
A method for automatically learning discriminative image patches for the recognition of given object classes is presented and decides that patches containing an eye are most important for distinguishing face from background images.
Improving a Discriminative Approach to Object Recognition Using Image Patches
TLDR
A method that uses image patch histograms and discriminative training to recognize objects in cluttered scenes is substantially improved by adding multi-scale features so that it better accounts for objects of different sizes.
Visual categorization with bags of keypoints
TLDR
This bag of keypoints method is based on vector quantization of affine invariant descriptors of image patches and shows that it is simple, computationally efficient and intrinsically invariant.
...
1
2
3
4
5
...