Research Area
Year Published

286 Results

June 18, 2018

Detail-Preserving Pooling in Deep Networks

Computer Vision and Pattern Recognition (CVPR)

In this paper, we aim to leverage recent results on image downscaling for the purposes of deep learning.

By: Faraz Saeedan, Nicolas Weber, Michael Goesele, Stefan Roth
June 18, 2018

Deep Spatio-Temporal Random Fields for Efficient Video Segmentation

Computer Vision and Pattern Recognition (CVPR)

In this work we introduce a time- and memory-efficient method for structured prediction that couples neuron decisions across both space at time. We show that we are able to perform exact and efficient inference on a densely connected spatio-temporal graph by capitalizing on recent advances on deep Gaussian random fields.

By: Siddhartha Chandra, Camille Couprie, Iasonas Kokkinos
June 18, 2018

Canonical Tensor Decomposition for Knowledge Base Completion

International Conference on Machine Learning (ICML)

The problem of Knowledge Base Completion can be framed as a 3rd-order binary tensor completion problem. In this light, the Canonical Tensor Decomposition (CP) (Hitchcock, 1927) seems like a natural solution. However, current implementations of CP on standard Knowledge Base Completion benchmarks are lagging behind their competitors. In this work, we attempt to understand the limits of CP for knowledge base completion.

By: Timothée Lacroix, Nicolas Usunier, Guillaume Obozinski
June 18, 2018

Separating Self-Expression and Visual Content in Hashtag Supervision

Computer Vision and Pattern Recognition (CVPR)

This paper presents an approach that extends upon modeling simple image-label pairs with a joint model of images, hashtags, and users. We demonstrate the efficacy of such approaches in image tagging and retrieval experiments, and show how the joint model can be used to perform user-conditional retrieval and tagging.

By: Andreas Veit, Maximilian Nickel, Serge Belongie, Laurens van der Maaten
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

Learning by Asking Questions

Computer Vision and Pattern Recognition (CVPR)

We introduce an interactive learning framework for the development and testing of intelligent visual systems, called learning-by-asking (LBA). We explore LBA in context of the Visual Question Answering (VQA) task.

By: Ishan Misra, Ross Girshick, Rob Fergus, Martial Hebert, Abhinav Gupta, Laurens van der Maaten
June 18, 2018

Non-Local Neural Networks

Computer Vision and Pattern Recognition (CVPR)

Both convolutional and recurrent operations are building blocks that process one local neighborhood at a time. In this paper, we present non-local operations as a generic family of building blocks for capturing long-range dependencies.

By: Xiaolong Wang*, Ross Girshick, Abhinav Gupta, Kaiming He
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 10, 2018

Randomized Value Functions via Multiplicative Normalizing Flows

ICML Workshop on Exploration in RL

In this work, we leverage recent advances in variational Bayesian neural networks and combine these with traditional Deep Q-Networks (DQN) to achieve randomized value functions for high-dimensional domains.

By: Ahmed Touati, Harsh Satija, Joshua Romoff, Joelle Pineau, Pascal Vincent
June 1, 2018

The Immersive VR Self: Performance, Embodiment and Presence in Immersive Virtual Reality Environments

Book chapter from A Networked Self and Human Augmentics, AI, Sentience

Virtual avatars are a common way to present oneself in online social interactions. From cartoonish emoticons to hyper-realistic humanoids, these online representations help us portray a certain image to our respective audiences.

By: Raz Schwartz, William Steptoe