May 5, 2019

3036 words 15 mins read

Paper Group ANR 537

Emulating Human Conversations using Convolutional Neural Network-based IR. Recovering the Missing Link: Predicting Class-Attribute Associations for Unsupervised Zero-Shot Learning. Earliness-Aware Deep Convolutional Networks for Early Time Series Classification. Learning Purposeful Behaviour in the Absence of Rewards. An Application of Network Lass …

Emulating Human Conversations using Convolutional Neural Network-based IR


Title	Emulating Human Conversations using Convolutional Neural Network-based IR
Authors	Abhay Prakash, Chris Brockett, Puneet Agrawal
Abstract	Conversational agents (“bots”) are beginning to be widely used in conversational interfaces. To design a system that is capable of emulating human-like interactions, a conversational layer that can serve as a fabric for chat-like interaction with the agent is needed. In this paper, we introduce a model that employs Information Retrieval by utilizing convolutional deep structured semantic neural network-based features in the ranker to present human-like responses in ongoing conversation with a user. In conversations, accounting for context is critical to the retrieval model; we show that our context-sensitive approach using a Convolutional Deep Structured Semantic Model (cDSSM) with character trigrams significantly outperforms several conventional baselines in terms of the relevance of responses retrieved.
Tasks	Information Retrieval
Published	2016-06-22
URL	http://arxiv.org/abs/1606.07056v1
PDF	http://arxiv.org/pdf/1606.07056v1.pdf
PWC	https://paperswithcode.com/paper/emulating-human-conversations-using
Repo
Framework

Recovering the Missing Link: Predicting Class-Attribute Associations for Unsupervised Zero-Shot Learning


Title	Recovering the Missing Link: Predicting Class-Attribute Associations for Unsupervised Zero-Shot Learning
Authors	Ziad Al-Halah, Makarand Tapaswi, Rainer Stiefelhagen
Abstract	Collecting training images for all visual categories is not only expensive but also impractical. Zero-shot learning (ZSL), especially using attributes, offers a pragmatic solution to this problem. However, at test time most attribute-based methods require a full description of attribute associations for each unseen class. Providing these associations is time consuming and often requires domain specific knowledge. In this work, we aim to carry out attribute-based zero-shot classification in an unsupervised manner. We propose an approach to learn relations that couples class embeddings with their corresponding attributes. Given only the name of an unseen class, the learned relationship model is used to automatically predict the class-attribute associations. Furthermore, our model facilitates transferring attributes across data sets without additional effort. Integrating knowledge from multiple sources results in a significant additional improvement in performance. We evaluate on two public data sets: Animals with Attributes and aPascal/aYahoo. Our approach outperforms state-of-the-art methods in both predicting class-attribute associations and unsupervised ZSL by a large margin.
Tasks	Zero-Shot Learning
Published	2016-10-15
URL	http://arxiv.org/abs/1610.04787v1
PDF	http://arxiv.org/pdf/1610.04787v1.pdf
PWC	https://paperswithcode.com/paper/recovering-the-missing-link-predicting-class
Repo
Framework

Earliness-Aware Deep Convolutional Networks for Early Time Series Classification


Title	Earliness-Aware Deep Convolutional Networks for Early Time Series Classification
Authors	Wenlin Wang, Changyou Chen, Wenqi Wang, Piyush Rai, Lawrence Carin
Abstract	We present Earliness-Aware Deep Convolutional Networks (EA-ConvNets), an end-to-end deep learning framework, for early classification of time series data. Unlike most existing methods for early classification of time series data, that are designed to solve this problem under the assumption of the availability of a good set of pre-defined (often hand-crafted) features, our framework can jointly perform feature learning (by learning a deep hierarchy of \emph{shapelets} capturing the salient characteristics in each time series), along with a dynamic truncation model to help our deep feature learning architecture focus on the early parts of each time series. Consequently, our framework is able to make highly reliable early predictions, outperforming various state-of-the-art methods for early time series classification, while also being competitive when compared to the state-of-the-art time series classification algorithms that work with \emph{fully observed} time series data. To the best of our knowledge, the proposed framework is the first to perform data-driven (deep) feature learning in the context of early classification of time series data. We perform a comprehensive set of experiments, on several benchmark data sets, which demonstrate that our method yields significantly better predictions than various state-of-the-art methods designed for early time series classification. In addition to obtaining high accuracies, our experiments also show that the learned deep shapelets based features are also highly interpretable and can help gain better understanding of the underlying characteristics of time series data.
Tasks	Time Series, Time Series Classification
Published	2016-11-14
URL	http://arxiv.org/abs/1611.04578v1
PDF	http://arxiv.org/pdf/1611.04578v1.pdf
PWC	https://paperswithcode.com/paper/earliness-aware-deep-convolutional-networks
Repo
Framework

Learning Purposeful Behaviour in the Absence of Rewards


Title	Learning Purposeful Behaviour in the Absence of Rewards
Authors	Marlos C. Machado, Michael Bowling
Abstract	Artificial intelligence is commonly defined as the ability to achieve goals in the world. In the reinforcement learning framework, goals are encoded as reward functions that guide agent behaviour, and the sum of observed rewards provide a notion of progress. However, some domains have no such reward signal, or have a reward signal so sparse as to appear absent. Without reward feedback, agent behaviour is typically random, often dithering aimlessly and lacking intentionality. In this paper we present an algorithm capable of learning purposeful behaviour in the absence of rewards. The algorithm proceeds by constructing temporally extended actions (options), through the identification of purposes that are “just out of reach” of the agent’s current behaviour. These purposes establish intrinsic goals for the agent to learn, ultimately resulting in a suite of behaviours that encourage the agent to visit different parts of the state space. Moreover, the approach is particularly suited for settings where rewards are very sparse, and such behaviours can help in the exploration of the environment until reward is observed.
Tasks
Published	2016-05-25
URL	http://arxiv.org/abs/1605.07700v1
PDF	http://arxiv.org/pdf/1605.07700v1.pdf
PWC	https://paperswithcode.com/paper/learning-purposeful-behaviour-in-the-absence
Repo
Framework


Title	An Application of Network Lasso Optimization For Ride Sharing Prediction
Authors	Shaona Ghosh, Kevin Page, David De Roure
Abstract	Ride sharing has important implications in terms of environmental, social and individual goals by reducing carbon footprints, fostering social interactions and economizing commuter costs. The ride sharing systems that are commonly available lack adaptive and scalable techniques that can simultaneously learn from the large scale data and predict in real-time dynamic fashion. In this paper, we study such a problem towards a smart city initiative, where a generic ride sharing system is conceived capable of making predictions about ride share opportunities based on the historically recorded data while satisfying real-time ride requests. Underpinning the system is an application of a powerful machine learning convex optimization framework called Network Lasso that uses the Alternate Direction Method of Multipliers (ADMM) optimization for learning and dynamic prediction. We propose an application of a robust and scalable unified optimization framework within the ride sharing case-study. The application of Network Lasso framework is capable of jointly optimizing and clustering different rides based on their spatial and model similarity. The prediction from the framework clusters new ride requests, making accurate price prediction based on the clusters, detecting hidden correlations in the data and allowing fast convergence due to the network topology. We provide an empirical evaluation of the application of ADMM network Lasso on real trip record and simulated data, proving their effectiveness since the mean squared error of the algorithm’s prediction is minimized on the test rides.
Tasks
Published	2016-06-10
URL	http://arxiv.org/abs/1606.03276v3
PDF	http://arxiv.org/pdf/1606.03276v3.pdf
PWC	https://paperswithcode.com/paper/an-application-of-network-lasso-optimization
Repo
Framework

Going Deeper into First-Person Activity Recognition


Title	Going Deeper into First-Person Activity Recognition
Authors	Minghuang Ma, Haoqi Fan, Kris M. Kitani
Abstract	We bring together ideas from recent work on feature design for egocentric action recognition under one framework by exploring the use of deep convolutional neural networks (CNN). Recent work has shown that features such as hand appearance, object attributes, local hand motion and camera ego-motion are important for characterizing first-person actions. To integrate these ideas under one framework, we propose a twin stream network architecture, where one stream analyzes appearance information and the other stream analyzes motion information. Our appearance stream encodes prior knowledge of the egocentric paradigm by explicitly training the network to segment hands and localize objects. By visualizing certain neuron activation of our network, we show that our proposed architecture naturally learns features that capture object attributes and hand-object configurations. Our extensive experiments on benchmark egocentric action datasets show that our deep architecture enables recognition rates that significantly outperform state-of-the-art techniques – an average $6.6%$ increase in accuracy over all datasets. Furthermore, by learning to recognize objects, actions and activities jointly, the performance of individual recognition tasks also increase by $30%$ (actions) and $14%$ (objects). We also include the results of extensive ablative analysis to highlight the importance of network design decisions..
Tasks	Activity Recognition, Temporal Action Localization
Published	2016-05-12
URL	http://arxiv.org/abs/1605.03688v1
PDF	http://arxiv.org/pdf/1605.03688v1.pdf
PWC	https://paperswithcode.com/paper/going-deeper-into-first-person-activity
Repo
Framework

Comprehensive Feature-based Robust Video Fingerprinting Using Tensor Model


Title	Comprehensive Feature-based Robust Video Fingerprinting Using Tensor Model
Authors	Xiushan Nie, Yilong Yin, Jiande Sun
Abstract	Content-based near-duplicate video detection (NDVD) is essential for effective search and retrieval, and robust video fingerprinting is a good solution for NDVD. Most existing video fingerprinting methods use a single feature or concatenating different features to generate video fingerprints, and show a good performance under single-mode modifications such as noise addition and blurring. However, when they suffer combined modifications, the performance is degraded to a certain extent because such features cannot characterize the video content completely. By contrast, the assistance and consensus among different features can improve the performance of video fingerprinting. Therefore, in the present study, we mine the assistance and consensus among different features based on tensor model, and present a new comprehensive feature to fully use them in the proposed video fingerprinting framework. We also analyze what the comprehensive feature really is for representing the original video. In this framework, the video is initially set as a high-order tensor that consists of different features, and the video tensor is decomposed via the Tucker model with a solution that determines the number of components. Subsequently, the comprehensive feature is generated by the low-order tensor obtained from tensor decomposition. Finally, the video fingerprint is computed using this feature. A matching strategy used for narrowing the search is also proposed based on the core tensor. The robust video fingerprinting framework is resistant not only to single-mode modifications, but also to the combination of them.
Tasks
Published	2016-01-27
URL	http://arxiv.org/abs/1601.07270v1
PDF	http://arxiv.org/pdf/1601.07270v1.pdf
PWC	https://paperswithcode.com/paper/comprehensive-feature-based-robust-video
Repo
Framework

Deep Learning Prototype Domains for Person Re-Identification


Title	Deep Learning Prototype Domains for Person Re-Identification
Authors	Arne Schumann, Shaogang Gong, Tobias Schuchert
Abstract	Person re-identification (re-id) is the task of matching multiple occurrences of the same person from different cameras, poses, lighting conditions, and a multitude of other factors which alter the visual appearance. Typically, this is achieved by learning either optimal features or matching metrics which are adapted to specific pairs of camera views dictated by the pairwise labelled training datasets. In this work, we formulate a deep learning based novel approach to automatic prototype-domain discovery for domain perceptive (adaptive) person re-id (rather than camera pair specific learning) for any camera views scalable to new unseen scenes without training data. We learn a separate re-id model for each of the discovered prototype-domains and during model deployment, use the person probe image to select automatically the model of the closest prototype domain. Our approach requires neither supervised nor unsupervised domain adaptation learning, i.e. no data available from the target domains. We evaluate extensively our model under realistic re-id conditions using automatically detected bounding boxes with low-resolution and partial occlusion. We show that our approach outperforms most of the state-of-the-art supervised and unsupervised methods on the latest CUHK-SYSU and PRW benchmarks.
Tasks	Domain Adaptation, Person Re-Identification, Unsupervised Domain Adaptation
Published	2016-10-17
URL	http://arxiv.org/abs/1610.05047v2
PDF	http://arxiv.org/pdf/1610.05047v2.pdf
PWC	https://paperswithcode.com/paper/deep-learning-prototype-domains-for-person-re
Repo
Framework

Dynamic Collaborative Filtering with Compound Poisson Factorization


Title	Dynamic Collaborative Filtering with Compound Poisson Factorization
Authors	Ghassen Jerfel, Mehmet E. Basbug, Barbara E. Engelhardt
Abstract	Model-based collaborative filtering analyzes user-item interactions to infer latent factors that represent user preferences and item characteristics in order to predict future interactions. Most collaborative filtering algorithms assume that these latent factors are static, although it has been shown that user preferences and item perceptions drift over time. In this paper, we propose a conjugate and numerically stable dynamic matrix factorization (DCPF) based on compound Poisson matrix factorization that models the smoothly drifting latent factors using Gamma-Markov chains. We propose a numerically stable Gamma chain construction, and then present a stochastic variational inference approach to estimate the parameters of our model. We apply our model to time-stamped ratings data sets: Netflix, Yelp, and Last.fm, where DCPF achieves a higher predictive accuracy than state-of-the-art static and dynamic factorization models.
Tasks
Published	2016-08-17
URL	http://arxiv.org/abs/1608.04839v3
PDF	http://arxiv.org/pdf/1608.04839v3.pdf
PWC	https://paperswithcode.com/paper/dynamic-collaborative-filtering-with-compound
Repo
Framework

Feeling the Bern: Adaptive Estimators for Bernoulli Probabilities of Pairwise Comparisons


Title	Feeling the Bern: Adaptive Estimators for Bernoulli Probabilities of Pairwise Comparisons
Authors	Nihar B. Shah, Sivaraman Balakrishnan, Martin J. Wainwright
Abstract	We study methods for aggregating pairwise comparison data in order to estimate outcome probabilities for future comparisons among a collection of n items. Working within a flexible framework that imposes only a form of strong stochastic transitivity (SST), we introduce an adaptivity index defined by the indifference sets of the pairwise comparison probabilities. In addition to measuring the usual worst-case risk of an estimator, this adaptivity index also captures the extent to which the estimator adapts to instance-specific difficulty relative to an oracle estimator. We prove three main results that involve this adaptivity index and different algorithms. First, we propose a three-step estimator termed Count-Randomize-Least squares (CRL), and show that it has adaptivity index upper bounded as $\sqrt{n}$ up to logarithmic factors. We then show that that conditional on the hardness of planted clique, no computationally efficient estimator can achieve an adaptivity index smaller than $\sqrt{n}$. Second, we show that a regularized least squares estimator can achieve a poly-logarithmic adaptivity index, thereby demonstrating a $\sqrt{n}$-gap between optimal and computationally achievable adaptivity. Finally, we prove that the standard least squares estimator, which is known to be optimally adaptive in several closely related problems, fails to adapt in the context of estimating pairwise probabilities.
Tasks
Published	2016-03-22
URL	http://arxiv.org/abs/1603.06881v1
PDF	http://arxiv.org/pdf/1603.06881v1.pdf
PWC	https://paperswithcode.com/paper/feeling-the-bern-adaptive-estimators-for
Repo
Framework

Post-Inference Prior Swapping


Title	Post-Inference Prior Swapping
Authors	Willie Neiswanger, Eric Xing
Abstract	While Bayesian methods are praised for their ability to incorporate useful prior knowledge, in practice, convenient priors that allow for computationally cheap or tractable inference are commonly used. In this paper, we investigate the following question: for a given model, is it possible to compute an inference result with any convenient false prior, and afterwards, given any target prior of interest, quickly transform this result into the target posterior? A potential solution is to use importance sampling (IS). However, we demonstrate that IS will fail for many choices of the target prior, depending on its parametric form and similarity to the false prior. Instead, we propose prior swapping, a method that leverages the pre-inferred false posterior to efficiently generate accurate posterior samples under arbitrary target priors. Prior swapping lets us apply less-costly inference algorithms to certain models, and incorporate new or updated prior information “post-inference”. We give theoretical guarantees about our method, and demonstrate it empirically on a number of models and priors.
Tasks
Published	2016-06-02
URL	http://arxiv.org/abs/1606.00787v2
PDF	http://arxiv.org/pdf/1606.00787v2.pdf
PWC	https://paperswithcode.com/paper/post-inference-prior-swapping
Repo
Framework

Unsupervised Topic Modeling Approaches to Decision Summarization in Spoken Meetings


Title	Unsupervised Topic Modeling Approaches to Decision Summarization in Spoken Meetings
Authors	Lu Wang, Claire Cardie
Abstract	We present a token-level decision summarization framework that utilizes the latent topic structures of utterances to identify “summary-worthy” words. Concretely, a series of unsupervised topic models is explored and experimental results show that fine-grained topic models, which discover topics at the utterance-level rather than the document-level, can better identify the gist of the decision-making process. Moreover, our proposed token-level summarization approach, which is able to remove redundancies within utterances, outperforms existing utterance ranking based summarization methods. Finally, context information is also investigated to add additional relevant information to the summary.
Tasks	Decision Making, Topic Models
Published	2016-06-24
URL	http://arxiv.org/abs/1606.07829v1
PDF	http://arxiv.org/pdf/1606.07829v1.pdf
PWC	https://paperswithcode.com/paper/unsupervised-topic-modeling-approaches-to
Repo
Framework

Active Nearest-Neighbor Learning in Metric Spaces


Title	Active Nearest-Neighbor Learning in Metric Spaces
Authors	Aryeh Kontorovich, Sivan Sabato, Ruth Urner
Abstract	We propose a pool-based non-parametric active learning algorithm for general metric spaces, called MArgin Regularized Metric Active Nearest Neighbor (MARMANN), which outputs a nearest-neighbor classifier. We give prediction error guarantees that depend on the noisy-margin properties of the input sample, and are competitive with those obtained by previously proposed passive learners. We prove that the label complexity of MARMANN is significantly lower than that of any passive learner with similar error guarantees. MARMANN is based on a generalized sample compression scheme, and a new label-efficient active model-selection procedure.
Tasks	Active Learning, Model Selection
Published	2016-05-22
URL	http://arxiv.org/abs/1605.06792v3
PDF	http://arxiv.org/pdf/1605.06792v3.pdf
PWC	https://paperswithcode.com/paper/active-nearest-neighbor-learning-in-metric
Repo
Framework

Factored Temporal Sigmoid Belief Networks for Sequence Learning


Title	Factored Temporal Sigmoid Belief Networks for Sequence Learning
Authors	Jiaming Song, Zhe Gan, Lawrence Carin
Abstract	Deep conditional generative models are developed to simultaneously learn the temporal dependencies of multiple sequences. The model is designed by introducing a three-way weight tensor to capture the multiplicative interactions between side information and sequences. The proposed model builds on the Temporal Sigmoid Belief Network (TSBN), a sequential stack of Sigmoid Belief Networks (SBNs). The transition matrices are further factored to reduce the number of parameters and improve generalization. When side information is not available, a general framework for semi-supervised learning based on the proposed model is constituted, allowing robust sequence classification. Experimental results show that the proposed approach achieves state-of-the-art predictive and classification performance on sequential data, and has the capacity to synthesize sequences, with controlled style transitioning and blending.
Tasks
Published	2016-05-22
URL	http://arxiv.org/abs/1605.06715v1
PDF	http://arxiv.org/pdf/1605.06715v1.pdf
PWC	https://paperswithcode.com/paper/factored-temporal-sigmoid-belief-networks-for
Repo
Framework

Exploring Different Dimensions of Attention for Uncertainty Detection


Title	Exploring Different Dimensions of Attention for Uncertainty Detection
Authors	Heike Adel, Hinrich Schütze
Abstract	Neural networks with attention have proven effective for many natural language processing tasks. In this paper, we develop attention mechanisms for uncertainty detection. In particular, we generalize standardly used attention mechanisms by introducing external attention and sequence-preserving attention. These novel architectures differ from standard approaches in that they use external resources to compute attention weights and preserve sequence information. We compare them to other configurations along different dimensions of attention. Our novel architectures set the new state of the art on a Wikipedia benchmark dataset and perform similar to the state-of-the-art model on a biomedical benchmark which uses a large set of linguistic features.
Tasks
Published	2016-12-20
URL	http://arxiv.org/abs/1612.06549v2
PDF	http://arxiv.org/pdf/1612.06549v2.pdf
PWC	https://paperswithcode.com/paper/exploring-different-dimensions-of-attention
Repo
Framework