Conference

# European Conference on Computer Vision

About: European Conference on Computer Vision is an academic conference. The conference publishes majorly in the area(s): Segmentation & Feature (computer vision). Over the lifetime, 6309 publication(s) have been published by the conference receiving 596209 citation(s).

##### Papers
More

Open accessBook Chapter
Tsung-Yi Lin1, Michael Maire2, Serge Belongie1, James Hays  +4 moreInstitutions (4)
06 Sep 2014-
Abstract: We present a new dataset with the goal of advancing the state-of-the-art in object recognition by placing the question of object recognition in the context of the broader question of scene understanding. This is achieved by gathering images of complex everyday scenes containing common objects in their natural context. Objects are labeled using per-instance segmentations to aid in precise object localization. Our dataset contains photos of 91 objects types that would be easily recognizable by a 4 year old. With a total of 2.5 million labeled instances in 328k images, the creation of our dataset drew upon extensive crowd worker involvement via novel user interfaces for category detection, instance spotting and instance segmentation. We present a detailed statistical analysis of the dataset in comparison to PASCAL, ImageNet, and SUN. Finally, we provide baseline performance analysis for bounding box and segmentation detection results using a Deformable Parts Model.

Topics: Object detection (54%)

18,843 Citations

Open accessBook Chapter
Herbert Bay1, Tinne Tuytelaars2, Luc Van Gool1Institutions (2)
07 May 2006-
Abstract: In this paper, we present a novel scale- and rotation-invariant interest point detector and descriptor, coined SURF (Speeded Up Robust Features). It approximates or even outperforms previously proposed schemes with respect to repeatability, distinctiveness, and robustness, yet can be computed and compared much faster. This is achieved by relying on integral images for image convolutions; by building on the strengths of the leading existing detectors and descriptors (in casu, using a Hessian matrix-based measure for the detector, and a distribution-based descriptor); and by simplifying these methods to the essential. This leads to a combination of novel detection, description, and matching steps. The paper presents experimental results on a standard evaluation set, as well as on imagery obtained in the context of a real-life object recognition application. Both show SURF's strong performance.

Topics: , GLOH (56%),  ...read more

12,404 Citations

Open accessBook Chapter
Wei Liu1, Dragomir Anguelov, Dumitru Erhan2, Christian Szegedy2  +3 moreInstitutions (3)
08 Oct 2016-
Abstract: We present a method for detecting objects in images using a single deep neural network. Our approach, named SSD, discretizes the output space of bounding boxes into a set of default boxes over different aspect ratios and scales per feature map location. At prediction time, the network generates scores for the presence of each object category in each default box and produces adjustments to the box to better match the object shape. Additionally, the network combines predictions from multiple feature maps with different resolutions to naturally handle objects of various sizes. SSD is simple relative to methods that require object proposals because it completely eliminates proposal generation and subsequent pixel or feature resampling stages and encapsulates all computation in a single network. This makes SSD easy to train and straightforward to integrate into systems that require a detection component. Experimental results on the PASCAL VOC, COCO, and ILSVRC datasets confirm that SSD has competitive accuracy to methods that utilize an additional object proposal step and is much faster, while providing a unified framework for both training and inference. For $$300 \times 300$$ input, SSD achieves 74.3 % mAP on VOC2007 test at 59 FPS on a Nvidia Titan X and for $$512 \times 512$$ input, SSD achieves 76.9 % mAP, outperforming a comparable state of the art Faster R-CNN model. Compared to other single stage methods, SSD has much better accuracy even with a smaller input image size. Code is available at https://github.com/weiliu89/caffe/tree/ssd.

Topics: Minimum bounding box (51%)

11,792 Citations

Open accessBook Chapter
Matthew D. Zeiler1, Rob Fergus1Institutions (1)
06 Sep 2014-
Abstract: Large Convolutional Network models have recently demonstrated impressive classification performance on the ImageNet benchmark Krizhevsky et al. [18]. However there is no clear understanding of why they perform so well, or how they might be improved. In this paper we explore both issues. We introduce a novel visualization technique that gives insight into the function of intermediate feature layers and the operation of the classifier. Used in a diagnostic role, these visualizations allow us to find model architectures that outperform Krizhevsky et al on the ImageNet classification benchmark. We also perform an ablation study to discover the performance contribution from different model layers. We show our ImageNet model generalizes well to other datasets: when the softmax classifier is retrained, it convincingly beats the current state-of-the-art results on Caltech-101 and Caltech-256 datasets.

Topics: , Softmax function (50%)

11,585 Citations

Open accessBook Chapter
Kaiming He1, Xiangyu Zhang1, Shaoqing Ren1, Jian Sun1Institutions (1)
08 Oct 2016-
Abstract: Deep residual networks have emerged as a family of extremely deep architectures showing compelling accuracy and nice convergence behaviors. In this paper, we analyze the propagation formulations behind the residual building blocks, which suggest that the forward and backward signals can be directly propagated from one block to any other block, when using identity mappings as the skip connections and after-addition activation. A series of ablation experiments support the importance of these identity mappings. This motivates us to propose a new residual unit, which makes training easier and improves generalization. We report improved results using a 1001-layer ResNet on CIFAR-10 (4.62 % error) and CIFAR-100, and a 200-layer ResNet on ImageNet. Code is available at: https://github.com/KaimingHe/resnet-1k-layers.

Topics: Residual (52%)

6,410 Citations

##### Performance
###### Metrics
No. of papers from the Conference in previous years
YearPapers
20212
20201,623
201919
20181,101
20172
2016608

###### Top Attributes

Show by:

Conference's top 5 most impactful authors

Luc Van Gool

76 papers, 22K citations

Andrew Zisserman

52 papers, 7.1K citations

Ming-Hsuan Yang

35 papers, 4.7K citations

Marc Pollefeys

25 papers, 3.2K citations

Philip H. S. Torr

24 papers, 4.8K citations

##### Network Information
###### Related Conferences (5)
Computer Vision and Pattern Recognition

19.7K papers, 2.2M citations

98% related
International Conference on Computer Vision

9.8K papers, 821.5K citations

97% related
Workshop on Applications of Computer Vision

2.6K papers, 62.6K citations

95% related
British Machine Vision Conference

3.6K papers, 127.8K citations

95% related
Asian Conference on Computer Vision

2.5K papers, 43.9K citations

94% related