Filter by Research Area
Filter by Research Area
Year Published

557 Results

June 18, 2018

On the iterative refinement of densely connected representation levels for semantic segmentation

CVPR Workshop (CVPRW) on Autonomous Driving

In this paper, we systematically study the differences introduced by distinct receptive field enlargement methods and their impact on the performance of a novel architecture, called Fully Convolutional DenseResNet (FC-DRN).

By: Arantxa Casanova, Guillem Cucurull, Michal Drozdzal, Adriana Romero, Yoshua Bengio
June 18, 2018

A Two-Step Disentanglement Method

Computer Vision and Pattern Recognition (CVPR)

We address the problem of disentanglement of factors that generate a given data into those that are correlated with the labeling and those that are not.

By: Naama Hadad, Lior Wolf, Moni Shahar
June 18, 2018

DensePose: Dense Human Pose Estimation In The Wild

Computer Vision and Pattern Recognition (CVPR)

In this work we establish dense correspondences between an RGB image and a surface-based representation of the human body, a task we refer to as dense human pose estimation. We gather dense correspondences for 50K persons appearing in the COCO dataset by introducing an efficient annotation pipeline. We then use our dataset to train CNN-based systems that deliver dense correspondence ‘in the wild’, namely in the presence of background, occlusions and scale variations.

By: Riza Alp Guler, Natalia Neverova, Iasonas Kokkinos
June 18, 2018

DeepMVS: Learning Multi-view Stereopsis

Computer Vision and Pattern Recognition (CVPR)

We present DeepMVS, a deep convolutional neural network (ConvNet) for multi-view stereo reconstruction.

By: Po-Han Huang, Kevin Matzen, Johannes Kopf, Narendra Ahuja, Jia-Bin Huang
June 18, 2018

Supervision-by-Registration: An Unsupervised Approach to Improve the Precision of Facial Landmark Detectors

Computer Vision and Pattern Recognition (CVPR)

In this paper, we present supervision-by-registration, an unsupervised approach to improve the precision of facial landmark detectors on both images and video. Our key observation is that the detections of the same landmark in adjacent frames should be coherent with registration, i.e., optical flow.

By: Xuanyi Dong, Shoou-I Yu, Xinshuo Weng, Shih-En Wei, Yi Yang, Yaser Sheikh
June 18, 2018

A Closer Look at Spatiotemporal Convolutions for Action Recognition

Computer Vision and Pattern Recognition (CVPR)

In this paper we discuss several forms of spatiotemporal convolutions for video analysis and study their effects on action recognition. Our motivation stems from the observation that 2D CNNs applied to individual frames of the video have remained solid performers in action recognition.

By: Du Tran, Heng Wang, Lorenzo Torresani, Jamie Ray, Yann LeCun, Manohar Paluri
June 17, 2018

Unsupervised Correlation Analysis

Computer Vision and Pattern Recognition (CVPR)

Linking between two data sources is a basic building block in numerous computer vision problems. In this paper, we set to answer a fundamental cognitive question: are prior correspondences necessary for linking between different domains?

By: Yedid Hoshen, Lior Wolf
June 17, 2018

Neural Baby Talk

Computer Vision and Pattern Recognition (CVPR)

We introduce a novel framework for image captioning that can produce natural language explicitly grounded in entities that object detectors find in the image.

By: Jiasen Lu, Jianwei Yang, Dhruv Batra, Devi Parikh
June 16, 2018

A common cause in the phenomenological and sensorimotor correlates of body ownership

International Multisensory Research Forum

The feeling that our limbs belong to our body is at the core of bodily self-consciousness. Over the years, limb ownership has been assessed through several types of measurements, including questionnaires and sensorimotor tasks assessing the perceived location of the hand with a visual-proprioceptive conflict.

By: Majed Samad, Cesare Parise, Sean Keller, Massimiliano Di Luca
Areas: AR/VR
June 13, 2018

A Comparative Study of Phoneme- and Word-Based Learning of English Words Presented to the Skin

Eurohaptics

Past research has demonstrated that speech communication on the skin is entirely achievable. However, there is still no definitive conclusion on the best training method that minimizes the time it takes for users to reach a prescribed performance level with a speech communication device. The present study reports the design and testing of two learning approaches with a system that translates English phonemes to haptic stimulation patterns (haptic symbols).

By: Yang Jiao, Frederico M. Severgnini, Juan S. Martinez, Jaehong Jung, Hong Z Tan, Charlotte M. Reed, E. Courtenay Wilson, Frances Lau, Ali Israr, Robert Turcott, Keith Klumb, Freddy Abnousi