All Research Areas
Research Areas
Year Published

220 Results

June 18, 2018

Low-shot learning with large-scale diffusion

Computer Vision and Pattern Recognition (CVPR)

This paper considers the problem of inferring image labels from images when only a few annotated examples are available at training time.

By: Matthijs Douze, Arthur Szlam, Bharath Hariharan, Hervé Jégou
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

Stacked Latent Attention for Multimodal Reasoning

Computer Vision and Pattern Recognition (CVPR)

Attention has shown to be a pivotal development in deep learning and has been used for a multitude of multimodal learning tasks such as visual question answering and image captioning. In this work, we pinpoint the potential limitations to the design of a traditional attention model.

By: Haoqi Fan, Jiatong Zhou
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

Eye In-Painting with Exemplar Generative Adversarial Networks

Computer Vision and Pattern Recognition (CVPR)

This paper introduces a novel approach to in-painting where the identity of the object to remove or change is preserved and accounted for at inference time: Exemplar GANs (ExGANs). ExGANs are a type of conditional GAN that utilize exemplar information to produce high-quality, personalized in-painting results.

By: Brian Dolhansky, Cristian Canton Ferrer
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 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 1, 2018

Colorless Green Recurrent Networks Dream Hierarchically

North American Chapter of the Association for Computational Linguistics (NAACL)

Recurrent neural networks (RNNs) have achieved impressive results in a variety of linguistic processing tasks, suggesting that they can induce non-trivial properties of language. We investigate here to what extent RNNs learn to track abstract hierarchical syntactic structure. We test whether RNNs trained with a generic language modeling objective in four languages (Italian, English, Hebrew, Russian) can predict long-distance number agreement in various constructions.

By: Kristina Gulordava, Piotr Bojanowski, Edouard Grave, Tal Linzen, Marco Baroni
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