Evan Herbst

Bio: Evan Herbst is an academic researcher from University of Washington. The author has contributed to research in topics: RGB color model & Image segmentation. The author has an hindex of 12, co-authored 17 publications receiving 9372 citations. Previous affiliations of Evan Herbst include United States Naval Research Laboratory & Cornell University.

Moses: Open Source Toolkit for Statistical Machine Translation

Abstract: We describe an open-source toolkit for statistical machine translation whose novel contributions are (a) support for linguistically motivated factors, (b) confusion network decoding, and (c) efficient data formats for translation models and language models. In addition to the SMT decoder, the toolkit also includes a wide variety of tools for training, tuning and applying the system to many translation tasks.

RGB-D mapping: Using Kinect-style depth cameras for dense 3D modeling of indoor environments

Abstract: RGB-D cameras (such as the Microsoft Kinect) are novel sensing systems that capture RGB images along with per-pixel depth information. In this paper we investigate how such cameras can be used for building dense 3D maps of indoor environments. Such maps have applications in robot navigation, manipulation, semantic mapping, and telepresence. We present RGB-D Mapping, a full 3D mapping system that utilizes a novel joint optimization algorithm combining visual features and shape-based alignment. Visual and depth information are also combined for view-based loop-closure detection, followed by pose optimization to achieve globally consistent maps. We evaluate RGB-D Mapping on two large indoor environments, and show that it effectively combines the visual and shape information available from RGB-D cameras.

RGB-D Mapping: Using Depth Cameras for Dense 3D Modeling of Indoor Environments

Abstract: RGB-D cameras are novel sensing systems that capture RGB images along with per-pixel depth information. In this paper we investigate how such cameras can be used in the context of robotics, specifically for building dense 3D maps of indoor environments. Such maps have applications in robot navigation, manipulation, semantic mapping, and telepresence. We present RGB-D Mapping, a full 3D mapping system that utilizes a novel joint optimization algorithm combining visual features and shape-based alignment. Visual and depth information are also combined for view-based loop closure detection, followed by pose optimization to achieve globally consistent maps.We evaluate RGB-D Mapping on two large indoor environments, and show that it effectively combines the visual and shape information available from RGB-D cameras.

The SOL Genomics Network. A Comparative Resource for Solanaceae Biology and Beyond

Abstract: The SOL Genomics Network (SGN; http://sgn.cornell.edu) is a rapidly evolving comparative resource for the plants of the Solanaceae family, which includes important crop and model plants such as potato (Solanum tuberosum), eggplant (Solanum melongena), pepper (Capsicum annuum), and tomato (Solanum lycopersicum). The aim of SGN is to relate these species to one another using a comparative genomics approach and to tie them to the other dicots through the fully sequenced genome of Arabidopsis (Arabidopsis thaliana). SGN currently houses map and marker data for Solanaceae species, a large expressed sequence tag collection with computationally derived unigene sets, an extensive database of phenotypic information for a mutagenized tomato population, and associated tools such as real-time quantitative trait loci. Recently, the International Solanaceae Project (SOL) was formed as an umbrella organization for Solanaceae research in over 30 countries to address important questions in plant biology. The first cornerstone of the SOL project is the sequencing of the entire euchromatic portion of the tomato genome. SGN is collaborating with other bioinformatics centers in building the bioinformatics infrastructure for the tomato sequencing project and implementing the bioinformatics strategy of the larger SOL project. The overarching goal of SGN is to make information available in an intuitive comparative format, thereby facilitating a systems approach to investigations into the basis of adaptation and phenotypic diversity in the Solanaceae family, other species in the Asterid clade such as coffee (Coffea arabica), Rubiaciae, and beyond.

Pattern Recognition and Machine Learning

Abstract: Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Neural Machine Translation of Rare Words with Subword Units

Abstract: Neural machine translation (NMT) models typically operate with a fixed vocabulary, but translation is an open-vocabulary problem. Previous work addresses the translation of out-of-vocabulary words by backing off to a dictionary. In this paper, we introduce a simpler and more effective approach, making the NMT model capable of open-vocabulary translation by encoding rare and unknown words as sequences of subword units. This is based on the intuition that various word classes are translatable via smaller units than words, for instance names (via character copying or transliteration), compounds (via compositional translation), and cognates and loanwords (via phonological and morphological transformations). We discuss the suitability of different word segmentation techniques, including simple character ngram models and a segmentation based on the byte pair encoding compression algorithm, and empirically show that subword models improve over a back-off dictionary baseline for the WMT 15 translation tasks English!German and English!Russian by up to 1.1 and 1.3 BLEU, respectively.

Moses: Open Source Toolkit for Statistical Machine Translation

Abstract: We describe an open-source toolkit for statistical machine translation whose novel contributions are (a) support for linguistically motivated factors, (b) confusion network decoding, and (c) efficient data formats for translation models and language models. In addition to the SMT decoder, the toolkit also includes a wide variety of tools for training, tuning and applying the system to many translation tasks.

Long-term recurrent convolutional networks for visual recognition and description

Abstract: Models based on deep convolutional networks have dominated recent image interpretation tasks; we investigate whether models which are also recurrent, or “temporally deep”, are effective for tasks involving sequences, visual and otherwise. We develop a novel recurrent convolutional architecture suitable for large-scale visual learning which is end-to-end trainable, and demonstrate the value of these models on benchmark video recognition tasks, image description and retrieval problems, and video narration challenges. In contrast to current models which assume a fixed spatio-temporal receptive field or simple temporal averaging for sequential processing, recurrent convolutional models are “doubly deep” in that they can be compositional in spatial and temporal “layers”. Such models may have advantages when target concepts are complex and/or training data are limited. Learning long-term dependencies is possible when nonlinearities are incorporated into the network state updates. Long-term RNN models are appealing in that they directly can map variable-length inputs (e.g., video frames) to variable length outputs (e.g., natural language text) and can model complex temporal dynamics; yet they can be optimized with backpropagation. Our recurrent long-term models are directly connected to modern visual convnet models and can be jointly trained to simultaneously learn temporal dynamics and convolutional perceptual representations. Our results show such models have distinct advantages over state-of-the-art models for recognition or generation which are separately defined and/or optimized.

KinectFusion: Real-time dense surface mapping and tracking

Abstract: We present a system for accurate real-time mapping of complex and arbitrary indoor scenes in variable lighting conditions, using only a moving low-cost depth camera and commodity graphics hardware. We fuse all of the depth data streamed from a Kinect sensor into a single global implicit surface model of the observed scene in real-time. The current sensor pose is simultaneously obtained by tracking the live depth frame relative to the global model using a coarse-to-fine iterative closest point (ICP) algorithm, which uses all of the observed depth data available. We demonstrate the advantages of tracking against the growing full surface model compared with frame-to-frame tracking, obtaining tracking and mapping results in constant time within room sized scenes with limited drift and high accuracy. We also show both qualitative and quantitative results relating to various aspects of our tracking and mapping system. Modelling of natural scenes, in real-time with only commodity sensor and GPU hardware, promises an exciting step forward in augmented reality (AR), in particular, it allows dense surfaces to be reconstructed in real-time, with a level of detail and robustness beyond any solution yet presented using passive computer vision.