Paper Group ANR 436
User Model-Based Intent-Aware Metrics for Multilingual Search Evaluation. Instance-Aware Hashing for Multi-Label Image Retrieval. X-ray In-Depth Decomposition: Revealing The Latent Structures. Multiplicative weights, equalizers, and P=PPAD. Hierarchical Clustering of Asymmetric Networks. On the Evaluation of Dialogue Systems with Next Utterance Cla …
User Model-Based Intent-Aware Metrics for Multilingual Search Evaluation
| Title | User Model-Based Intent-Aware Metrics for Multilingual Search Evaluation |
| Authors | Alexey Drutsa, Andrey Shutovich, Philipp Pushnyakov, Evgeniy Krokhalyov, Gleb Gusev, Pavel Serdyukov |
| Abstract | Despite the growing importance of multilingual aspect of web search, no appropriate offline metrics to evaluate its quality are proposed so far. At the same time, personal language preferences can be regarded as intents of a query. This approach translates the multilingual search problem into a particular task of search diversification. Furthermore, the standard intent-aware approach could be adopted to build a diversified metric for multilingual search on the basis of a classical IR metric such as ERR. The intent-aware approach estimates user satisfaction under a user behavior model. We show however that the underlying user behavior models is not realistic in the multilingual case, and the produced intent-aware metric do not appropriately estimate the user satisfaction. We develop a novel approach to build intent-aware user behavior models, which overcome these limitations and convert to quality metrics that better correlate with standard online metrics of user satisfaction. |
| Tasks | |
| Published | 2016-12-13 |
| URL | http://arxiv.org/abs/1612.04418v1 |
| http://arxiv.org/pdf/1612.04418v1.pdf | |
| PWC | https://paperswithcode.com/paper/user-model-based-intent-aware-metrics-for |
| Repo | |
| Framework | |
Instance-Aware Hashing for Multi-Label Image Retrieval
| Title | Instance-Aware Hashing for Multi-Label Image Retrieval |
| Authors | Hanjiang Lai, Pan Yan, Xiangbo Shu, Yunchao Wei, Shuicheng Yan |
| Abstract | Similarity-preserving hashing is a commonly used method for nearest neighbour search in large-scale image retrieval. For image retrieval, deep-networks-based hashing methods are appealing since they can simultaneously learn effective image representations and compact hash codes. This paper focuses on deep-networks-based hashing for multi-label images, each of which may contain objects of multiple categories. In most existing hashing methods, each image is represented by one piece of hash code, which is referred to as semantic hashing. This setting may be suboptimal for multi-label image retrieval. To solve this problem, we propose a deep architecture that learns \textbf{instance-aware} image representations for multi-label image data, which are organized in multiple groups, with each group containing the features for one category. The instance-aware representations not only bring advantages to semantic hashing, but also can be used in category-aware hashing, in which an image is represented by multiple pieces of hash codes and each piece of code corresponds to a category. Extensive evaluations conducted on several benchmark datasets demonstrate that, for both semantic hashing and category-aware hashing, the proposed method shows substantial improvement over the state-of-the-art supervised and unsupervised hashing methods. |
| Tasks | Image Retrieval, Multi-Label Image Retrieval |
| Published | 2016-03-10 |
| URL | http://arxiv.org/abs/1603.03234v1 |
| http://arxiv.org/pdf/1603.03234v1.pdf | |
| PWC | https://paperswithcode.com/paper/instance-aware-hashing-for-multi-label-image |
| Repo | |
| Framework | |
X-ray In-Depth Decomposition: Revealing The Latent Structures
| Title | X-ray In-Depth Decomposition: Revealing The Latent Structures |
| Authors | Shadi Albarqouni, Javad Fotouhi, Nassir Navab |
| Abstract | X-ray radiography is the most readily available imaging modality and has a broad range of applications that spans from diagnosis to intra-operative guidance in cardiac, orthopedics, and trauma procedures. Proper interpretation of the hidden and obscured anatomy in X-ray images remains a challenge and often requires high radiation dose and imaging from several perspectives. In this work, we aim at decomposing the conventional X-ray image into d X-ray components of independent, non-overlapped, clipped sub-volumes using deep learning approach. Despite the challenging aspects of modeling such a highly ill-posed problem, exciting and encouraging results are obtained paving the path for further contributions in this direction. |
| Tasks | |
| Published | 2016-12-19 |
| URL | http://arxiv.org/abs/1612.06096v2 |
| http://arxiv.org/pdf/1612.06096v2.pdf | |
| PWC | https://paperswithcode.com/paper/x-ray-in-depth-decomposition-revealing-the |
| Repo | |
| Framework | |
Multiplicative weights, equalizers, and P=PPAD
| Title | Multiplicative weights, equalizers, and P=PPAD |
| Authors | Ioannis Avramopoulos |
| Abstract | We show that, by using multiplicative weights in a game-theoretic thought experiment (and an important convexity result on the composition of multiplicative weights with the relative entropy function), a symmetric bimatrix game (that is, a bimatrix matrix wherein the payoff matrix of each player is the transpose of the payoff matrix of the other) either has an interior symmetric equilibrium or there is a pure strategy that is weakly dominated by some mixed strategy. Weakly dominated pure strategies can be detected and eliminated in polynomial time by solving a linear program. Furthermore, interior symmetric equilibria are a special case of a more general notion, namely, that of an “equalizer,” which can also be computed efficiently in polynomial time by solving a linear program. An elegant “symmetrization method” of bimatrix games [Jurg et al., 1992] and the well-known PPAD-completeness results on equilibrium computation in bimatrix games [Daskalakis et al., 2009, Chen et al., 2009] imply then the compelling P = PPAD. |
| Tasks | |
| Published | 2016-09-28 |
| URL | http://arxiv.org/abs/1609.08934v1 |
| http://arxiv.org/pdf/1609.08934v1.pdf | |
| PWC | https://paperswithcode.com/paper/multiplicative-weights-equalizers-and-pppad |
| Repo | |
| Framework | |
Hierarchical Clustering of Asymmetric Networks
| Title | Hierarchical Clustering of Asymmetric Networks |
| Authors | Gunnar Carlsson, Facundo Mémoli, Alejandro Ribeiro, Santiago Segarra |
| Abstract | This paper considers networks where relationships between nodes are represented by directed dissimilarities. The goal is to study methods that, based on the dissimilarity structure, output hierarchical clusters, i.e., a family of nested partitions indexed by a connectivity parameter. Our construction of hierarchical clustering methods is built around the concept of admissible methods, which are those that abide by the axioms of value - nodes in a network with two nodes are clustered together at the maximum of the two dissimilarities between them - and transformation - when dissimilarities are reduced, the network may become more clustered but not less. Two particular methods, termed reciprocal and nonreciprocal clustering, are shown to provide upper and lower bounds in the space of admissible methods. Furthermore, alternative clustering methodologies and axioms are considered. In particular, modifying the axiom of value such that clustering in two-node networks occurs at the minimum of the two dissimilarities entails the existence of a unique admissible clustering method. |
| Tasks | |
| Published | 2016-07-21 |
| URL | http://arxiv.org/abs/1607.06294v1 |
| http://arxiv.org/pdf/1607.06294v1.pdf | |
| PWC | https://paperswithcode.com/paper/hierarchical-clustering-of-asymmetric |
| Repo | |
| Framework | |
On the Evaluation of Dialogue Systems with Next Utterance Classification
| Title | On the Evaluation of Dialogue Systems with Next Utterance Classification |
| Authors | Ryan Lowe, Iulian V. Serban, Mike Noseworthy, Laurent Charlin, Joelle Pineau |
| Abstract | An open challenge in constructing dialogue systems is developing methods for automatically learning dialogue strategies from large amounts of unlabelled data. Recent work has proposed Next-Utterance-Classification (NUC) as a surrogate task for building dialogue systems from text data. In this paper we investigate the performance of humans on this task to validate the relevance of NUC as a method of evaluation. Our results show three main findings: (1) humans are able to correctly classify responses at a rate much better than chance, thus confirming that the task is feasible, (2) human performance levels vary across task domains (we consider 3 datasets) and expertise levels (novice vs experts), thus showing that a range of performance is possible on this type of task, (3) automated dialogue systems built using state-of-the-art machine learning methods have similar performance to the human novices, but worse than the experts, thus confirming the utility of this class of tasks for driving further research in automated dialogue systems. |
| Tasks | |
| Published | 2016-05-18 |
| URL | http://arxiv.org/abs/1605.05414v2 |
| http://arxiv.org/pdf/1605.05414v2.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-evaluation-of-dialogue-systems-with |
| Repo | |
| Framework | |
Compact Hash Codes for Efficient Visual Descriptors Retrieval in Large Scale Databases
| Title | Compact Hash Codes for Efficient Visual Descriptors Retrieval in Large Scale Databases |
| Authors | Simone Ercoli, Marco Bertini, Alberto Del Bimbo |
| Abstract | In this paper we present an efficient method for visual descriptors retrieval based on compact hash codes computed using a multiple k-means assignment. The method has been applied to the problem of approximate nearest neighbor (ANN) search of local and global visual content descriptors, and it has been tested on different datasets: three large scale public datasets of up to one billion descriptors (BIGANN) and, supported by recent progress in convolutional neural networks (CNNs), also on the CIFAR-10 and MNIST datasets. Experimental results show that, despite its simplicity, the proposed method obtains a very high performance that makes it superior to more complex state-of-the-art methods. |
| Tasks | |
| Published | 2016-05-10 |
| URL | http://arxiv.org/abs/1605.02892v1 |
| http://arxiv.org/pdf/1605.02892v1.pdf | |
| PWC | https://paperswithcode.com/paper/compact-hash-codes-for-efficient-visual |
| Repo | |
| Framework | |
Multimodal Pivots for Image Caption Translation
| Title | Multimodal Pivots for Image Caption Translation |
| Authors | Julian Hitschler, Shigehiko Schamoni, Stefan Riezler |
| Abstract | We present an approach to improve statistical machine translation of image descriptions by multimodal pivots defined in visual space. The key idea is to perform image retrieval over a database of images that are captioned in the target language, and use the captions of the most similar images for crosslingual reranking of translation outputs. Our approach does not depend on the availability of large amounts of in-domain parallel data, but only relies on available large datasets of monolingually captioned images, and on state-of-the-art convolutional neural networks to compute image similarities. Our experimental evaluation shows improvements of 1 BLEU point over strong baselines. |
| Tasks | Image Retrieval, Machine Translation |
| Published | 2016-01-15 |
| URL | http://arxiv.org/abs/1601.03916v3 |
| http://arxiv.org/pdf/1601.03916v3.pdf | |
| PWC | https://paperswithcode.com/paper/multimodal-pivots-for-image-caption |
| Repo | |
| Framework | |
Approximate Message Passing with Nearest Neighbor Sparsity Pattern Learning
| Title | Approximate Message Passing with Nearest Neighbor Sparsity Pattern Learning |
| Authors | Xiangming Meng, Sheng Wu, Linling Kuang, Defeng, Huang, Jianhua Lu |
| Abstract | We consider the problem of recovering clustered sparse signals with no prior knowledge of the sparsity pattern. Beyond simple sparsity, signals of interest often exhibits an underlying sparsity pattern which, if leveraged, can improve the reconstruction performance. However, the sparsity pattern is usually unknown a priori. Inspired by the idea of k-nearest neighbor (k-NN) algorithm, we propose an efficient algorithm termed approximate message passing with nearest neighbor sparsity pattern learning (AMP-NNSPL), which learns the sparsity pattern adaptively. AMP-NNSPL specifies a flexible spike and slab prior on the unknown signal and, after each AMP iteration, sets the sparse ratios as the average of the nearest neighbor estimates via expectation maximization (EM). Experimental results on both synthetic and real data demonstrate the superiority of our proposed algorithm both in terms of reconstruction performance and computational complexity. |
| Tasks | |
| Published | 2016-01-04 |
| URL | http://arxiv.org/abs/1601.00543v1 |
| http://arxiv.org/pdf/1601.00543v1.pdf | |
| PWC | https://paperswithcode.com/paper/approximate-message-passing-with-nearest |
| Repo | |
| Framework | |
Balancing Suspense and Surprise: Timely Decision Making with Endogenous Information Acquisition
| Title | Balancing Suspense and Surprise: Timely Decision Making with Endogenous Information Acquisition |
| Authors | Ahmed M. Alaa, Mihaela van der Schaar |
| Abstract | We develop a Bayesian model for decision-making under time pressure with endogenous information acquisition. In our model, the decision maker decides when to observe (costly) information by sampling an underlying continuous-time stochastic process (time series) that conveys information about the potential occurrence or non-occurrence of an adverse event which will terminate the decision-making process. In her attempt to predict the occurrence of the adverse event, the decision-maker follows a policy that determines when to acquire information from the time series (continuation), and when to stop acquiring information and make a final prediction (stopping). We show that the optimal policy has a rendezvous structure, i.e. a structure in which whenever a new information sample is gathered from the time series, the optimal “date” for acquiring the next sample becomes computable. The optimal interval between two information samples balances a trade-off between the decision maker’s surprise, i.e. the drift in her posterior belief after observing new information, and suspense, i.e. the probability that the adverse event occurs in the time interval between two information samples. Moreover, we characterize the continuation and stopping regions in the decision-maker’s state-space, and show that they depend not only on the decision-maker’s beliefs, but also on the context, i.e. the current realization of the time series. |
| Tasks | Decision Making, Time Series |
| Published | 2016-10-24 |
| URL | http://arxiv.org/abs/1610.07505v1 |
| http://arxiv.org/pdf/1610.07505v1.pdf | |
| PWC | https://paperswithcode.com/paper/balancing-suspense-and-surprise-timely |
| Repo | |
| Framework | |
Canonical Correlation Inference for Mapping Abstract Scenes to Text
| Title | Canonical Correlation Inference for Mapping Abstract Scenes to Text |
| Authors | Nikos Papasarantopoulos, Helen Jiang, Shay B. Cohen |
| Abstract | We describe a technique for structured prediction, based on canonical correlation analysis. Our learning algorithm finds two projections for the input and the output spaces that aim at projecting a given input and its correct output into points close to each other. We demonstrate our technique on a language-vision problem, namely the problem of giving a textual description to an “abstract scene”. |
| Tasks | Structured Prediction |
| Published | 2016-08-09 |
| URL | http://arxiv.org/abs/1608.02784v2 |
| http://arxiv.org/pdf/1608.02784v2.pdf | |
| PWC | https://paperswithcode.com/paper/canonical-correlation-inference-for-mapping |
| Repo | |
| Framework | |
ConfocalGN : a minimalistic confocal image simulator
| Title | ConfocalGN : a minimalistic confocal image simulator |
| Authors | Serge Dmitrieff, François Nédélec |
| Abstract | SUMMARY : We developed a user-friendly software to generate synthetic confocal microscopy images from a ground truth specified as a 3D bitmap with pixels of arbitrary size. The software can analyze a real confocal stack to derivate noise parameters and will use them directly to generate new images with similar noise characteristics. Such synthetic images can then be used to assert the quality and robustness of an image analysis pipeline, as well as be used to train machine-learning image analysis procedures. We illustrate the approach with closed curves corresponding to the microtubule ring present in blood platelet. AVAILABILITY AND IMPLEMENTATION: ConfocalGN is written in Matlab but does not require any toolbox. The source code is distributed under the GPL 3.0 licence on https://github.com/SergeDmi/ConfocalGN. |
| Tasks | |
| Published | 2016-10-31 |
| URL | http://arxiv.org/abs/1610.10042v2 |
| http://arxiv.org/pdf/1610.10042v2.pdf | |
| PWC | https://paperswithcode.com/paper/confocalgn-a-minimalistic-confocal-image |
| Repo | |
| Framework | |
Weakly Supervised Localization using Deep Feature Maps
| Title | Weakly Supervised Localization using Deep Feature Maps |
| Authors | Archith J. Bency, Heesung Kwon, Hyungtae Lee, S. Karthikeyan, B. S. Manjunath |
| Abstract | Object localization is an important computer vision problem with a variety of applications. The lack of large scale object-level annotations and the relative abundance of image-level labels makes a compelling case for weak supervision in the object localization task. Deep Convolutional Neural Networks are a class of state-of-the-art methods for the related problem of object recognition. In this paper, we describe a novel object localization algorithm which uses classification networks trained on only image labels. This weakly supervised method leverages local spatial and semantic patterns captured in the convolutional layers of classification networks. We propose an efficient beam search based approach to detect and localize multiple objects in images. The proposed method significantly outperforms the state-of-the-art in standard object localization data-sets with a 8 point increase in mAP scores. |
| Tasks | Object Localization, Object Recognition, Weakly Supervised Object Detection |
| Published | 2016-03-01 |
| URL | http://arxiv.org/abs/1603.00489v2 |
| http://arxiv.org/pdf/1603.00489v2.pdf | |
| PWC | https://paperswithcode.com/paper/weakly-supervised-localization-using-deep |
| Repo | |
| Framework | |
Alternating Optimisation and Quadrature for Robust Control
| Title | Alternating Optimisation and Quadrature for Robust Control |
| Authors | Supratik Paul, Konstantinos Chatzilygeroudis, Kamil Ciosek, Jean-Baptiste Mouret, Michael A. Osborne, Shimon Whiteson |
| Abstract | Bayesian optimisation has been successfully applied to a variety of reinforcement learning problems. However, the traditional approach for learning optimal policies in simulators does not utilise the opportunity to improve learning by adjusting certain environment variables: state features that are unobservable and randomly determined by the environment in a physical setting but are controllable in a simulator. This paper considers the problem of finding a robust policy while taking into account the impact of environment variables. We present Alternating Optimisation and Quadrature (ALOQ), which uses Bayesian optimisation and Bayesian quadrature to address such settings. ALOQ is robust to the presence of significant rare events, which may not be observable under random sampling, but play a substantial role in determining the optimal policy. Experimental results across different domains show that ALOQ can learn more efficiently and robustly than existing methods. |
| Tasks | Bayesian Optimisation |
| Published | 2016-05-24 |
| URL | http://arxiv.org/abs/1605.07496v3 |
| http://arxiv.org/pdf/1605.07496v3.pdf | |
| PWC | https://paperswithcode.com/paper/alternating-optimisation-and-quadrature-for |
| Repo | |
| Framework | |
Divergent discourse between protests and counter-protests: #BlackLivesMatter and #AllLivesMatter
| Title | Divergent discourse between protests and counter-protests: #BlackLivesMatter and #AllLivesMatter |
| Authors | Ryan J. Gallagher, Andrew J. Reagan, Christopher M. Danforth, Peter Sheridan Dodds |
| Abstract | Since the shooting of Black teenager Michael Brown by White police officer Darren Wilson in Ferguson, Missouri, the protest hashtag #BlackLivesMatter has amplified critiques of extrajudicial killings of Black Americans. In response to #BlackLivesMatter, other Twitter users have adopted #AllLivesMatter, a counter-protest hashtag whose content argues that equal attention should be given to all lives regardless of race. Through a multi-level analysis of over 860,000 tweets, we study how these protests and counter-protests diverge by quantifying aspects of their discourse. We find that #AllLivesMatter facilitates opposition between #BlackLivesMatter and hashtags such as #PoliceLivesMatter and #BlueLivesMatter in such a way that historically echoes the tension between Black protesters and law enforcement. In addition, we show that a significant portion of #AllLivesMatter use stems from hijacking by #BlackLivesMatter advocates. Beyond simply injecting #AllLivesMatter with #BlackLivesMatter content, these hijackers use the hashtag to directly confront the counter-protest notion of “All lives matter.” Our findings suggest that Black Lives Matter movement was able to grow, exhibit diverse conversations, and avoid derailment on social media by making discussion of counter-protest opinions a central topic of #AllLivesMatter, rather than the movement itself. |
| Tasks | |
| Published | 2016-06-22 |
| URL | http://arxiv.org/abs/1606.06820v5 |
| http://arxiv.org/pdf/1606.06820v5.pdf | |
| PWC | https://paperswithcode.com/paper/divergent-discourse-between-protests-and |
| Repo | |
| Framework | |
