Home      Discussions      About
Join us

@cs.cmu.edu

Aug 31, 2017
By cszhe1
Computer Vision
Computation and Language

Video Captioning with Guidance of Multimodal Latent Topics

The topic diversity of open-domain videos leads to various vocabularies and linguistic expressions in describing video contents, and therefore, mak...
Oct 24, 2018
By yulund
Computer Vision
Artificial Intelligence
Human-Computer Interaction

Multimodal Polynomial Fusion for Detecting Driver Distraction

Distracted driving is deadly, claiming 3,477 lives in the U.S. in 2015 alone. Although there has been a considerable amount of research on modeling...
Nov 01, 2018
Computation and Language
Artificial Intelligence
Machine Learning
Neural and Evolutionary Computation

Dirichlet Variational Autoencoder for Text Modeling

We introduce an improved variational autoencoder (VAE) for text modeling with topic information explicitly modeled as a Dirichlet latent variable. ...
Oct 30, 2018
By wuli
Computation and Language
Artificial Intelligence
Machine Learning

Word Mover's Embedding: From Word2Vec to Document Embedding

While the celebrated Word2Vec technique yields semantically rich representations for individual words, there has been relatively less success in ex...
Nov 05, 2016
By zichaoy
Computation and Language

We introduce reference-aware language models which explicitly model the decision of from where to generate the token at each step. Our model can also learns the decision by treating it as a latent variable. We demonstrate on three applications, ta...

Reference-Aware Language Models

We propose a general class of language models that treat reference as an explicit stochastic latent variable. This architecture allows models to cr...
Nov 20, 2018
Machine Learning

Stackelberg GAN: Towards Provable Minimax Equilibrium via Multi-G...

We study the problem of alleviating the instability issue in the GAN training procedure via new architecture design. The discrepancy between the mi...
Oct 02, 2018
By samemon
Machine Learning

Neural Regression Trees

Regression-via-Classification (RvC) is the process of converting a regression problem to a classification one. Current approaches for RvC use ad-ho...
Oct 04, 2013
By jblocki
Cryptography and Security
Artificial Intelligence

GOTCHA Password Hackers!

We introduce GOTCHAs (Generating panOptic Turing Tests to Tell Computers and Humans Apart) as a way of preventing automated offline dictionary atta...
Sep 20, 2016
Sound
Machine Learning
Multimedia

An Approach for Self-Training Audio Event Detectors Using Web Data

Audio Event Detection (AED) aims to recognize sounds within audio and video recordings. AED employs machine learning algorithms commonly trained an...
Sep 12, 2016
By noamb
Computer Science and Game Theory
Artificial Intelligence

Reduced Space and Faster Convergence in Imperfect-Information Games...

Counterfactual Regret Minimization (CFR) is the most popular iterative algorithm for solving zero-sum imperfect-information games. Regret-Based Pru...
Nov 22, 2018
Computer Vision
Artificial Intelligence
Machine Learning

Learning from Multiview Correlations in Open-Domain Videos

An increasing number of datasets contain multiple views, such as video, sound and automatic captions. A basic challenge in representation learning ...
Aug 28, 2018
By xinyiw1
Computation and Language

A Tree-based Decoder for Neural Machine Translation

Recent advances in Neural Machine Translation (NMT) show that adding syntactic information to NMT systems can improve the quality of their translat...
Nov 24, 2014
By aramdas
Statistics Theory
Artificial Intelligence
Information Theory
Machine Learning

On the High-dimensional Power of Linear-time Kernel Two-Sample Test...

Nonparametric two sample testing deals with the question of consistently deciding if two distributions are different, given samples from both, with...
Mar 14, 2018
Computation and Language

In this work, we have introduced the idea of a neural lattice language model, which allows us to marginalize over all segmentations of a sentence in an end-to-end fashion. In our experiments on the Billion Word Corpus and Chinese GigaWord corpus, ...

Neural Lattice Language Models

In this work, we propose a new language modeling paradigm that has the ability to perform both prediction and moderation of information flow at mul...
Jul 21, 2014
By lmarujo
Information Retrieval
Cryptography and Security

Privacy-Preserving Important Passage Retrieval

State-of-the-art important passage retrieval methods obtain very good results, but do not take into account privacy issues. In this paper, we prese...
Aug 02, 2018
By wyuan1
Computer Vision
Robotics

PCN: Point Completion Network

Shape completion, the problem of estimating the complete geometry of objects from partial observations, lies at the core of many vision and robotic...
Aug 02, 2018
Computer Vision

Adaptive Temporal Encoding Network for Video Instance-level Human ...

Beyond the existing single-person and multiple-person human parsing tasks in static images, this paper makes the first attempt to investigate a mor...
May 31, 2017
By htung
Computer Vision

Adversarial Inverse Graphics Networks: Learning 2D-to-3D Lifting an...

Researchers have developed excellent feed-forward models that learn to map images to desired outputs, such as to the images' latent factors, or to ...
Sep 25, 2015
Machine Learning

Linear-time Learning on Distributions with Approximate Kernel Embed...

Many interesting machine learning problems are best posed by considering instances that are distributions, or sample sets drawn from distributions....
Jul 11, 2018
By htpham
Computation and Language
Machine Learning

Seq2Seq2Sentiment: Multimodal Sequence to Sequence Models for Senti...

Multimodal machine learning is a core research area spanning the language, visual and acoustic modalities. The central challenge in multimodal lear...
There aren't more papers

Request Comment

or Invite via email
You are asking your first question!
How to quickly get a good answer:
  • Keep your question short and to the point
  • Check for grammar or spelling errors.
  • Phrase it like a question
Test
Test description