Výsledky vyhledávání - "2013 IEEE Conference on Computer Vision and Pattern Recognition"

POOF: Part-Based One-vs.-One Features for Fine-Grained Categorization, Face Verification, and Attribute Estimation Autor Berg, Thomas, Belhumeur, Peter N.

“…From a set of images in a particular domain, labeled with part locations and class, we present a method to automatically learn a large and diverse set of…”
Získat plný text

Sketch Tokens: A Learned Mid-level Representation for Contour and Object Detection Autor Lim, Joseph J., Zitnick, C. Lawrence, Dollar, Piotr

“…We propose a novel approach to both learning and detecting local contour-based representations for mid-level features. Our features, called sketch tokens, are…”
Získat plný text

Motionlets: Mid-level 3D Parts for Human Motion Recognition Autor LiMin Wang, Yu Qiao, Xiaoou Tang

“…This paper proposes motionlet, a mid-level and spatiotemporal part, for human motion recognition. Motion let can be seen as a tight cluster in motion and…”
Získat plný text

Online Object Tracking: A Benchmark Autor Yi Wu, Jongwoo Lim, Ming-Hsuan Yang

“…Object tracking is one of the most important components in numerous applications of computer vision. While much progress has been made in recent years with…”
Získat plný text

Saliency Detection via Graph-Based Manifold Ranking Autor Chuan Yang, Lihe Zhang, Huchuan Lu, Xiang Ruan, Ming-Hsuan Yang

“…Most existing bottom-up methods measure the foreground saliency of a pixel or region based on its contrast within a local context or the entire image, whereas…”
Získat plný text

Hierarchical Saliency Detection Autor Qiong Yan, Li Xu, Jianping Shi, Jiaya Jia

“…When dealing with objects with complex structures, saliency detection confronts a critical problem - namely that detection accuracy could be adversely affected…”
Získat plný text

Supervised Descent Method and Its Applications to Face Alignment Autor Xuehan Xiong, De la Torre, Fernando

“…Many computer vision problems (e.g., camera calibration, image alignment, structure from motion) are solved through a nonlinear optimization method. It is…”
Získat plný text

Deep Convolutional Network Cascade for Facial Point Detection Autor Yi Sun, Xiaogang Wang, Xiaoou Tang

“…We propose a new approach for estimation of the positions of facial key points with three-level carefully designed convolutional networks. At each level, the…”
Získat plný text

Unnatural L0 Sparse Representation for Natural Image Deblurring Autor Li Xu, Shicheng Zheng, Jiaya Jia

“…We show in this paper that the success of previous maximum a posterior (MAP) based blur removal methods partly stems from their respective intermediate steps,…”
Získat plný text

Salient Object Detection: A Discriminative Regional Feature Integration Approach Autor Huaizu Jiang, Jingdong Wang, Zejian Yuan, Yang Wu, Nanning Zheng, Shipeng Li

“…Salient object detection has been attracting a lot of interest, and recently various heuristic computational models have been designed. In this paper, we…”
Získat plný text

Multi-source Multi-scale Counting in Extremely Dense Crowd Images Autor Idrees, Haroon, Saleemi, Imran, Seibert, Cody, Shah, Mubarak

“…We propose to leverage multiple sources of information to compute an estimate of the number of individuals present in an extremely dense crowd visible in a…”
Získat plný text

Selective Transfer Machine for Personalized Facial Action Unit Detection Autor Chu, Wen-Sheng, De la Torre, Fernando, Cohn, Jeffery F.

“…Automatic facial action unit (AFA) detection from video is a long-standing problem in facial expression analysis. Most approaches emphasize choices of features…”
Získat plný text

Unsupervised Salience Learning for Person Re-identification Autor Rui Zhao, Wanli Ouyang, Xiaogang Wang

“…Human eyes can recognize person identities based on some small salient regions. However, such valuable salient information is often hidden when computing…”
Získat plný text

Label-Embedding for Attribute-Based Classification Autor Akata, Zeynep, Perronnin, Florent, Harchaoui, Zaid, Schmid, Cordelia

“…Attributes are an intermediate representation, which enables parameter sharing between classes, a must when training data is scarce. We propose to view…”
Získat plný text

Pedestrian Detection with Unsupervised Multi-stage Feature Learning Autor Sermanet, Pierre, Kavukcuoglu, Koray, Chintala, Soumith, Lecun, Yann

“…Pedestrian detection is a problem of considerable practical interest. Adding to the list of successful applications of deep learning methods to vision, we…”
Získat plný text

HON4D: Histogram of Oriented 4D Normals for Activity Recognition from Depth Sequences Autor Oreifej, Omar, Zicheng Liu

“…We present a new descriptor for activity recognition from videos acquired by a depth sensor. Previous descriptors mostly compute shape and motion features…”
Získat plný text

Blessing of Dimensionality: High-Dimensional Feature and Its Efficient Compression for Face Verification Autor Dong Chen, Xudong Cao, Fang Wen, Jian Sun

“…Making a high-dimensional (e.g., 100K-dim) feature for face recognition seems not a good idea because it will bring difficulties on consequent training,…”
Získat plný text

Scene Coordinate Regression Forests for Camera Relocalization in RGB-D Images Autor Shotton, Jamie, Glocker, Ben, Zach, Christopher, Izadi, Shahram, Criminisi, Antonio, Fitzgibbon, Andrew

“…We address the problem of inferring the pose of an RGB-D camera relative to a known 3D scene, given only a single acquired image. Our approach employs a…”
Získat plný text

Decoding, Calibration and Rectification for Lenselet-Based Plenoptic Cameras Autor Dansereau, Donald G., Pizarro, Oscar, Williams, Stefan B.

“…Plenoptic cameras are gaining attention for their unique light gathering and post-capture processing capabilities. We describe a decoding, calibration and…”
Získat plný text

Locally Aligned Feature Transforms across Views Autor Wei Li, Xiaogang Wang

“…In this paper, we propose a new approach for matching images observed in different camera views with complex cross-view transforms and apply it to person…”
Získat plný text