CVPR 2014

DeepPose: Human Pose Estimation via Deep Neural Networks

CVPR 2014 mitmul/deeppose

We propose a method for human pose estimation based on Deep Neural Networks (DNNs).

POSE ESTIMATION

Cross-Scale Cost Aggregation for Stereo Matching

CVPR 2014 rookiepig/CrossScaleStereo

We firstly reformulate cost aggregation from a unified optimization perspective and show that different cost aggregation methods essentially differ in the choices of similarity kernels.

STEREO MATCHING STEREO MATCHING HAND

Learning Fine-grained Image Similarity with Deep Ranking

CVPR 2014 Zhenye-Na/image-similarity-using-deep-ranking

This paper proposes a deep ranking model that employs deep learning techniques to learn similarity metric directly from images. It has higher learning capability than models based on hand-crafted features.

Online Object Tracking, Learning and Parsing with And-Or Graphs

CVPR 2014 tfwu/RGM-AOGTracker

In the former, our AOGTracker outperforms state-of-the-art tracking algorithms including two trackers based on deep convolutional network.

OBJECT TRACKING

Fast and Robust Archetypal Analysis for Representation Learning

CVPR 2014 vitkl/ParetoTI

We revisit a pioneer unsupervised learning technique called archetypal analysis, which is related to successful data analysis methods such as sparse coding and non-negative matrix factorization.

REPRESENTATION LEARNING

PANDA: Pose Aligned Networks for Deep Attribute Modeling

CVPR 2014 FanjieLUO/matlab

We propose a method for inferring human attributes (such as gender, hair style, clothes style, expression, action) from images of people under large variation of viewpoint, pose, appearance, articulation and occlusion.

OBJECT RECOGNITION

Scalable Object Detection using Deep Neural Networks

CVPR 2014 Adren98/EczemaApp

Deep convolutional neural networks have recently achieved state-of-the-art performance on a number of image recognition benchmarks, including the ImageNet Large-Scale Visual Recognition Challenge (ILSVRC-2012).

OBJECT DETECTION OBJECT RECOGNITION

Novel methods for multilinear data completion and de-noising based on tensor-SVD

CVPR 2014 Nigoding/tensor-completion

Based on t-SVD, the notion of multilinear rank and a related tensor nuclear norm was proposed in [11] to characterize informational and structural complexity of multilinear data.