All Research Areas
Research Areas
Year Published

98 Results

June 18, 2018

Detect-and-Track: Efficient Pose Estimation in Videos

Computer Vision and Pattern Recognition (CVPR)

This paper addresses the problem of estimating and tracking human body keypoints in complex, multi-person video. We propose an extremely lightweight yet highly effective approach that builds upon the latest advancements in human detection [17] and video understanding [5].

By: Rohit Girdhar, Georgia Gkioxari, Lorenzo Torresani, Manohar Paluri, Du Tran
June 18, 2018

What Makes a Video a Video: Analyzing Temporal Information in Video Understanding Models and Datasets

Computer Vision and Pattern Recognition (CVPR)

While there have been numerous attempts at modeling motion in videos, an explicit analysis of the effect of temporal information for video understanding is still missing. In this work, we aim to bridge this gap and ask the following question: How important is the motion in the video for recognizing the action?

By: De-An Huang, Vignesh Ramanathan, Dhruv Mahajan, Lorenzo Torresani, Manohar Paluri, Li Fei-Fei, Juan Carlos Niebles
June 18, 2018

3D Semantic Segmentation with Submanifold Sparse Convolutional Networks

Computer Vision and Pattern Recognition (CVPR)

We introduce new sparse convolutional operations that are designed to process spatially-sparse data more efficiently, and use them to develop spatially-sparse convolutional networks.

By: Benjamin Graham, Laurens van der Maaten, Martin Engelcke
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

Learning Patch Reconstructability for Accelerating Multi-View Stereo

Computer Vision and Pattern Recognition (CVPR)

We present an approach to accelerate multi-view stereo (MVS) by prioritizing computation on image patches that are likely to produce accurate 3D surface reconstructions. Our key insight is that the accuracy of the surface reconstruction from a given image patch can be predicted significantly faster than performing the actual stereo matching.

By: Alex Poms, Chenglei Wu, Shoou-I Yu, 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 18, 2018

A Holistic Framework for Addressing the World using Machine Learning

Computer Vision and Pattern Recognition (CVPR)

Millions of people are disconnected from basic services due to lack of adequate addressing. We propose an automatic generative algorithm to create street addresses from satellite imagery.

By: Ilke Demir, Forest Hughes, Aman Raj, Kaunil Dhruv, Suryanarayana Murthy Muddala, Sanyam Garg, Barrett Doo
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 13, 2018

Efficient Evaluation of Coding Strategies for Transcutaneous Language Communication

Eurohaptics 2018

Communication of natural language via the skin has seen renewed interest with the advent of mobile devices and wearable technology. Efficient evaluation of candidate haptic encoding algorithms remains a significant challenge. We present 4 algorithms along with our methods for evaluation, which are based on discriminability, learnability, and generalizability. Advantageously, mastery of an extensive vocabulary is not required.

By: Robert Turcott, Jennifer Chen, Pablo Castillo, Brian Knott, Wahyudinata Setiawan, Forrest Briggs, Keith Klumb, Freddy Abnousi, Prasad Chakka, Frances Lau, Ali Israr
May 16, 2018

Glow: Graph Lowering Compiler Techniques for Neural Networks


This paper presents the design of Glow, a machine learning compiler for heterogeneous hardware. It is a pragmatic approach to compilation that enables the generation of highly optimized code for multiple targets. Glow lowers the traditional neural network dataflow graph into a two-phase strongly-typed intermediate representation.

By: Saleem Abdulrasool, Summer Deng, Roman Dzhabarov, Jordan Fix, James Hegeman, Roman Levenstein, Bert Maher, Satish Nadathur, Jakob Olesen, Jongsoo Park, Artem Rakhov, Nadav Rotem, Misha Smelyanskiy