Papers.

Indoor Semantic Segmentation using depth information

This work addresses multi-class segmentation of indoor scenes with RGB-D inputs. While this area of research has gained much attention recently, most works still rely on hand-crafted features. In contrast, we apply a multiscale convolutional network to learn features directly from the images and the depth information. We obtain state-of-the-art on the NYU-v2 depth dataset with an accuracy of 64.5%. We illustrate the labeling of indoor scenes in videos sequences that could be processed in real-time using appropriate hardware such as an FPGA.

Clustering Learning for Robotic Vision

We present the clustering learning technique applied to multi-layer feedforward deep neural networks. We show that this unsupervised learning technique can compute network filters with only a few minutes and a much reduced set of parameters. The goal of this paper is to promote the technique for general-purpose robotic vision systems. We report its use in static image datasets and object tracking datasets. We show that networks trained with clustering learning can outperform large networks trained for many hours on complex datasets.

Probabilistic Models for Unified Collaborative and Content-Based Recommendation in Sparse-Data Environments

Recommender systems leverage product and community information to target products to consumers. Researchers have developed collaborative recommenders, content-based recommenders, and (largely ad-hoc) hybrid systems. We propose a unified probabilistic framework for merging collaborative and content-based recommendations. We extend Hofmann's [1999] aspect model to incorporate three-way co-occurrence data among users, items, and item content. The relative influence of collaboration data versus content data is not imposed as an exogenous parameter, but rather emerges naturally from the given data sources. Global probabilistic models coupled with standard Expectation Maximization (EM) learning algorithms tend to drastically overfit in sparse-data situations, as is typical in recommendation applications. We show that secondary content information can often be used to overcome sparsity. Experiments on data from the ResearchIndex library of Computer Science publications show that appropriate mixture models incorporating secondary data produce significantly better quality recommenders than k-nearest neighbors (k-NN). Global probabilistic models also allow more general inferences than local methods like k-NN.

VitalHome - VitalJacket® as an AAL service for the Living Usability Lab

Virtual Production Intelligence : ein Beitrag zur virtuellen Fabrik

Vector Space Semantic Parsing: A Framework for Compositional Vector Space Models

UMBC_EBIQUITY-CORE: Semantic Textual Similarity Systems

Tribler Mobile : P2P Video Streaming from and to Mobile Devices

Towards Real-Time Image Understanding with Convolutional Networks (Analyse sémantique des images en temps-réel avec des réseaux convolutifs)

Topic Model Diagnostics: Assessing Domain Relevance via Topical Alignment

The Reactive Manifesto

The Impact of Communicative Constraints on the Emergence of a Graphical Communication System

The Case for Tiny Tasks in Compute Clusters

The 3rd Temporal Web Analytics Workshop (TempWeb)

Text Analysis and Word Pronunciation in Text-to-speech Synthesis

Taming Text: How to Find, Organize, and Manipulate It

Tachyon: Memory Throughput I/O for Cluster Computing Frameworks

Supporting the ARP 4761 Safety Assessment Process with AADL

Robust Extraction of Metaphor from Novel Data

Reasoning With Neural Tensor Networks for Knowledge Base Completion

Rayo: Remote Control of Media Resources over XMPP

Quasiquotes for Scala

Quality analysis after action report for the crowdsourced aerial imagery assessment following hurricane sandy.

Provable Bounds for Learning Some Deep Representations.

Programme Chairs' Welcome

Product Innovations by Young and Small Firms

Proceedings of the 3rd International Temporal Web Analytics Workshop (TempWeb 2013)

Proceedings of the 22nd international conference on World Wide Web companion

Proceedings of the 22nd international conference on World Wide Web

Proceedings of the 2013 IEEE International Conference on Big Data

Preface for the TempWeb '13 Workshop.

Preface

Patterns of Information Management

Parsing with Compositional Vector Grammars

Optimizing Shuffle Performance in Spark

Spark is a cluster framework that performs in-memory computing, with the goal of outperforming disk-based engines like Hadoop. As with other distributed data processing platforms, it is common to collect data in a many-to-many fashion, a stage traditionally known as the shuffle phase. In Spark, many sources of inefficiency exist in the shuffle phase that, once addressed, potentially promise vast performance improvements. In this paper, we identify the bottlenecks in the execution of the current design, and propose alternatives that solve the observed problems. We evaluate our results in terms of application level throughput.

Open2Edit: A peer-to-peer platform for collaboration

Object-Oriented Pickler Combinators and an Extensible Generation Framework

More Tweets, More Votes: The Link Between Twitter and the 2010 Congressional Elections

Micro-volunteering: helping the helpers in development

INTEGRATED GENOMIC ANALYSIS OF EGFR-MUTANT NON-SMALL CELL LUNG CANCER IMMEDIATELY FOLLOWING ERLOTINIB INITIATION IN PATIENTS

INTEGRATED GENOMIC ANALYSIS BY WHOLE EXOME AND TRANSCRIPTOME SEQUENCING OF TUMOR SAMPLES FROM EGFR-MUTANT NON-SMALL-CELL LUNG CANCER (NSCLC) PATIENTS WITH ACQUIRED RESISTANCE TO ERLOTINIB

Human-Computer Interactive Chinese Word Segmentation: An Adaptive Dirichlet Process Mixture Model Approach

Html5 Pocket Primer

HTML5 Mobile

HTML 5 Pocket Primer

How Did We Get Into This Mess? Isolating Fault- Inducing Inputs to SDN Control Software

HAT, not CAP: towards highly available transactions

HAT, not CAP: Highly Available Transactions for Everybody.

HAT, not CAP: Highly Available Transactions

Fast Data Processing with Spark