January 27, 2020

3359 words 16 mins read

Paper Group ANR 1096

Are Outlier Detection Methods Resilient to Sampling?. Practical Semantic Parsing for Spoken Language Understanding. Generative Well-intentioned Networks. Monocular 3D Sway Tracking for Assessing Postural Instability in Cerebral Hypoperfusion During Quiet Standing. Learning Perceptual Inference by Contrasting. Pushing the Frontiers of Unconstrained …

Are Outlier Detection Methods Resilient to Sampling?


Title	Are Outlier Detection Methods Resilient to Sampling?
Authors	Laure Berti-Equille, Ji Meng Loh, Saravanan Thirumuruganathan
Abstract	Outlier detection is a fundamental task in data mining and has many applications including detecting errors in databases. While there has been extensive prior work on methods for outlier detection, modern datasets often have sizes that are beyond the ability of commonly used methods to process the data within a reasonable time. To overcome this issue, outlier detection methods can be trained over samples of the full-sized dataset. However, it is not clear how a model trained on a sample compares with one trained on the entire dataset. In this paper, we introduce the notion of resilience to sampling for outlier detection methods. Orthogonal to traditional performance metrics such as precision/recall, resilience represents the extent to which the outliers detected by a method applied to samples from a sampling scheme matches those when applied to the whole dataset. We propose a novel approach for estimating the resilience to sampling of both individual outlier methods and their ensembles. We performed an extensive experimental study on synthetic and real-world datasets where we study seven diverse and representative outlier detection methods, compare results obtained from samples versus those obtained from the whole datasets and evaluate the accuracy of our resilience estimates. We observed that the methods are not equally resilient to a given sampling scheme and it is often the case that careful joint selection of both the sampling scheme and the outlier detection method is necessary. It is our hope that the paper initiates research on designing outlier detection algorithms that are resilient to sampling.
Tasks	Outlier Detection
Published	2019-07-31
URL	https://arxiv.org/abs/1907.13276v1
PDF	https://arxiv.org/pdf/1907.13276v1.pdf
PWC	https://paperswithcode.com/paper/are-outlier-detection-methods-resilient-to
Repo
Framework

Practical Semantic Parsing for Spoken Language Understanding


Title	Practical Semantic Parsing for Spoken Language Understanding
Authors	Marco Damonte, Rahul Goel, Tagyoung Chung
Abstract	Executable semantic parsing is the task of converting natural language utterances into logical forms that can be directly used as queries to get a response. We build a transfer learning framework for executable semantic parsing. We show that the framework is effective for Question Answering (Q&A) as well as for Spoken Language Understanding (SLU). We further investigate the case where a parser on a new domain can be learned by exploiting data on other domains, either via multi-task learning between the target domain and an auxiliary domain or via pre-training on the auxiliary domain and fine-tuning on the target domain. With either flavor of transfer learning, we are able to improve performance on most domains; we experiment with public data sets such as Overnight and NLmaps as well as with commercial SLU data. The experiments carried out on data sets that are different in nature show how executable semantic parsing can unify different areas of NLP such as Q&A and SLU.
Tasks	Multi-Task Learning, Question Answering, Semantic Parsing, Spoken Language Understanding, Transfer Learning
Published	2019-03-11
URL	http://arxiv.org/abs/1903.04521v3
PDF	http://arxiv.org/pdf/1903.04521v3.pdf
PWC	https://paperswithcode.com/paper/practical-semantic-parsing-for-spoken
Repo
Framework

Generative Well-intentioned Networks


Title	Generative Well-intentioned Networks
Authors	Justin Cosentino, Jun Zhu
Abstract	We propose Generative Well-intentioned Networks (GWINs), a novel framework for increasing the accuracy of certainty-based, closed-world classifiers. A conditional generative network recovers the distribution of observations that the classifier labels correctly with high certainty. We introduce a reject option to the classifier during inference, allowing the classifier to reject an observation instance rather than predict an uncertain label. These rejected observations are translated by the generative network to high-certainty representations, which are then relabeled by the classifier. This architecture allows for any certainty-based classifier or rejection function and is not limited to multilayer perceptrons. The capability of this framework is assessed using benchmark classification datasets and shows that GWINs significantly improve the accuracy of uncertain observations.
Tasks
Published	2019-10-28
URL	https://arxiv.org/abs/1910.12481v1
PDF	https://arxiv.org/pdf/1910.12481v1.pdf
PWC	https://paperswithcode.com/paper/generative-well-intentioned-networks
Repo
Framework

Monocular 3D Sway Tracking for Assessing Postural Instability in Cerebral Hypoperfusion During Quiet Standing


Title	Monocular 3D Sway Tracking for Assessing Postural Instability in Cerebral Hypoperfusion During Quiet Standing
Authors	Robert Amelard, Kevin R Murray, Eric T Hedge, Taylor W Cleworth, Mamiko Noguchi, Andrew Laing, Richard L Hughson
Abstract	Postural instability is prevalent in aging and neurodegenerative disease, decreasing quality of life and independence. Quantitatively monitoring balance control is important for assessing treatment efficacy and rehabilitation progress. However, existing technologies for assessing postural sway are complex and expensive, limiting their widespread utility. Here, we propose a monocular imaging system capable of assessing sub-millimeter 3D sway dynamics during quiet standing. Two anatomical targets with known feature geometries were placed on the lumbar and shoulder. Upper and lower trunk 3D kinematic motion was automatically assessed from a set of 2D frames through geometric feature tracking and an inverse motion model. Sway was tracked in 3D and compared between control and hypoperfusion conditions in 14 healthy young adults. The proposed system demonstrated high agreement with a commercial motion capture system (error $1.5 \times 10^{-4}~\text{mm}$, [$-0.52$, $0.52$]). Between-condition differences in sway dynamics were observed in anterior-posterior sway during early and mid stance, and medial-lateral sway during mid stance commensurate with decreased cerebral perfusion, followed by recovered sway dynamics during late stance with cerebral perfusion recovery. This inexpensive single-camera system enables quantitative 3D sway monitoring for assessing neuromuscular balance control in weakly constrained environments.
Tasks	Motion Capture
Published	2019-07-11
URL	https://arxiv.org/abs/1907.05376v2
PDF	https://arxiv.org/pdf/1907.05376v2.pdf
PWC	https://paperswithcode.com/paper/assessing-postural-instability-during
Repo
Framework

Learning Perceptual Inference by Contrasting


Title	Learning Perceptual Inference by Contrasting
Authors	Chi Zhang, Baoxiong Jia, Feng Gao, Yixin Zhu, Hongjing Lu, Song-Chun Zhu
Abstract	“Thinking in pictures,” [1] i.e., spatial-temporal reasoning, effortless and instantaneous for humans, is believed to be a significant ability to perform logical induction and a crucial factor in the intellectual history of technology development. Modern Artificial Intelligence (AI), fueled by massive datasets, deeper models, and mighty computation, has come to a stage where (super-)human-level performances are observed in certain specific tasks. However, current AI’s ability in “thinking in pictures” is still far lacking behind. In this work, we study how to improve machines’ reasoning ability on one challenging task of this kind: Raven’s Progressive Matrices (RPM). Specifically, we borrow the very idea of “contrast effects” from the field of psychology, cognition, and education to design and train a permutation-invariant model. Inspired by cognitive studies, we equip our model with a simple inference module that is jointly trained with the perception backbone. Combining all the elements, we propose the Contrastive Perceptual Inference network (CoPINet) and empirically demonstrate that CoPINet sets the new state-of-the-art for permutation-invariant models on two major datasets. We conclude that spatial-temporal reasoning depends on envisaging the possibilities consistent with the relations between objects and can be solved from pixel-level inputs.
Tasks
Published	2019-11-29
URL	https://arxiv.org/abs/1912.00086v1
PDF	https://arxiv.org/pdf/1912.00086v1.pdf
PWC	https://paperswithcode.com/paper/learning-perceptual-inference-by-contrasting-1
Repo
Framework

Pushing the Frontiers of Unconstrained Crowd Counting: New Dataset and Benchmark Method


Title	Pushing the Frontiers of Unconstrained Crowd Counting: New Dataset and Benchmark Method
Authors	Vishwanath A. Sindagi, Rajeev Yasarla, Vishal M. Patel
Abstract	In this work, we propose a novel crowd counting network that progressively generates crowd density maps via residual error estimation. The proposed method uses VGG16 as the backbone network and employs density map generated by the final layer as a coarse prediction to refine and generate finer density maps in a progressive fashion using residual learning. Additionally, the residual learning is guided by an uncertainty-based confidence weighting mechanism that permits the flow of only high-confidence residuals in the refinement path. The proposed Confidence Guided Deep Residual Counting Network (CG-DRCN) is evaluated on recent complex datasets, and it achieves significant improvements in errors. Furthermore, we introduce a new large scale unconstrained crowd counting dataset (JHU-CROWD) that is ~2.8 larger than the most recent crowd counting datasets in terms of the number of images. It contains 4,250 images with 1.11 million annotations. In comparison to existing datasets, the proposed dataset is collected under a variety of diverse scenarios and environmental conditions. Specifically, the dataset includes several images with weather-based degradations and illumination variations in addition to many distractor images, making it a very challenging dataset. Additionally, the dataset consists of rich annotations at both image-level and head-level. Several recent methods are evaluated and compared on this dataset.
Tasks	Crowd Counting
Published	2019-10-28
URL	https://arxiv.org/abs/1910.12384v1
PDF	https://arxiv.org/pdf/1910.12384v1.pdf
PWC	https://paperswithcode.com/paper/pushing-the-frontiers-of-unconstrained-crowd-1
Repo
Framework

Query-focused Sentence Compression in Linear Time


Title	Query-focused Sentence Compression in Linear Time
Authors	Abram Handler, Brendan O’Connor
Abstract	Search applications often display shortened sentences which must contain certain query terms and must fit within the space constraints of a user interface. This work introduces a new transition-based sentence compression technique developed for such settings. Our query-focused method constructs length and lexically constrained compressions in linear time, by growing a subgraph in the dependency parse of a sentence. This theoretically efficient approach achieves an 11X empirical speedup over baseline ILP methods, while better reconstructing gold constrained shortenings. Such speedups help query-focused applications, because users are measurably hindered by interface lags. Additionally, our technique does not require an ILP solver or a GPU.
Tasks	Sentence Compression
Published	2019-04-19
URL	https://arxiv.org/abs/1904.09051v2
PDF	https://arxiv.org/pdf/1904.09051v2.pdf
PWC	https://paperswithcode.com/paper/query-focused-sentence-compression-in-linear
Repo
Framework

Visual Feature Fusion and its Application to Support Unsupervised Clustering Tasks


Title	Visual Feature Fusion and its Application to Support Unsupervised Clustering Tasks
Authors	Gladys Hilasaca, Fernando Paulovich
Abstract	On visual analytics applications, the concept of putting the user on the loop refers to the ability to replace heuristics by user knowledge on machine learning and data mining tasks. On supervised tasks, the user engagement occurs via the manipulation of the training data. However, on unsupervised tasks, the user involvement is limited to changes in the algorithm parametrization or the input data representation, also known as features. Depending on the application domain, different types of features can be extracted from the raw data. Therefore, the result of unsupervised algorithms heavily depends on the type of employed feature. Since there is no perfect feature extractor, combining different features have been explored in a process called feature fusion. The feature fusion is straightforward when the machine learning or data mining task has a cost function. However, when such a function does not exist, user support for combination needs to be provided otherwise the process is impractical. In this paper, we present a novel feature fusion approach that uses small data samples to allows users not only to effortless control the combination of different feature sets but also to interpret the attained results. The effectiveness of our approach is confirmed by a comprehensive set of qualitative and quantitative tests, opening up different possibilities of user-guided analytical scenarios not covered yet. The ability of our approach to providing real-time feedback for the feature fusion is exploited on the context of unsupervised clustering techniques, where the composed groups reflect the semantics of the feature combination.
Tasks
Published	2019-01-16
URL	http://arxiv.org/abs/1901.05556v1
PDF	http://arxiv.org/pdf/1901.05556v1.pdf
PWC	https://paperswithcode.com/paper/visual-feature-fusion-and-its-application-to
Repo
Framework

The iterative convolution-thresholding method (ICTM) for image segmentation


Title	The iterative convolution-thresholding method (ICTM) for image segmentation
Authors	Dong Wang, Xiao-Ping Wang
Abstract	In this paper, we propose a novel iterative convolution-thresholding method (ICTM) that is applicable to a range of variational models for image segmentation. A variational model usually minimizes an energy functional consisting of a fidelity term and a regularization term. In the ICTM, the interface between two different segment domains is implicitly represented by their characteristic functions. The fidelity term is then usually written as a linear functional of the characteristic functions and the regularized term is approximated by a functional of characteristic functions in terms of heat kernel convolution. This allows us to design an iterative convolution-thresholding method to minimize the approximate energy. The method is simple, efficient and enjoys the energy-decaying property. Numerical experiments show that the method is easy to implement, robust and applicable to various image segmentation models.
Tasks	Semantic Segmentation
Published	2019-04-24
URL	http://arxiv.org/abs/1904.10917v1
PDF	http://arxiv.org/pdf/1904.10917v1.pdf
PWC	https://paperswithcode.com/paper/the-iterative-convolution-thresholding-method
Repo
Framework

Agriculture Commodity Arrival Prediction using Remote Sensing Data: Insights and Beyond


Title	Agriculture Commodity Arrival Prediction using Remote Sensing Data: Insights and Beyond
Authors	Gautam Prasad, Upendra Reddy Vuyyuru, Mithun Das Gupta
Abstract	In developing countries like India agriculture plays an extremely important role in the lives of the population. In India, around 80% of the population depend on agriculture or its by-products as the primary means for employment. Given large population dependency on agriculture, it becomes extremely important for the government to estimate market factors in advance and prepare for any deviation from those estimates. Commodity arrivals to market is an extremely important factor which is captured at district level throughout the country. Historical data and short-term prediction of important variables such as arrivals, prices, crop quality etc. for commodities are used by the government to take proactive steps and decide various policy measures. In this paper, we present a framework to work with short timeseries in conjunction with remote sensing data to predict future commodity arrivals. We deal with extremely high dimensional data which exceed the observation sizes by multiple orders of magnitude. We use cascaded layers of dimensionality reduction techniques combined with regularized regression models for prediction. We present results to predict arrivals to major markets and state wide prices for `Tur’ (red gram) crop in Karnataka, India. Our model consistently beats popular ML techniques on many instances. Our model is scalable, time efficient and can be generalized to many other crops and regions. We draw multiple insights from the regression parameters, some of which are important aspects to consider when predicting more complex quantities such as prices in the future. We also combine the insights to generate important recommendations for different government organizations. \|
Tasks	Dimensionality Reduction
Published	2019-06-14
URL	https://arxiv.org/abs/1906.07573v1
PDF	https://arxiv.org/pdf/1906.07573v1.pdf
PWC	https://paperswithcode.com/paper/agriculture-commodity-arrival-prediction
Repo
Framework

Directional TSDF: Modeling Surface Orientation for Coherent Meshes


Title	Directional TSDF: Modeling Surface Orientation for Coherent Meshes
Authors	Malte Splietker, Sven Behnke
Abstract	Real-time 3D reconstruction from RGB-D sensor data plays an important role in many robotic applications, such as object modeling and mapping. The popular method of fusing depth information into a truncated signed distance function (TSDF) and applying the marching cubes algorithm for mesh extraction has severe issues with thin structures: not only does it lead to loss of accuracy, but it can generate completely wrong surfaces. To address this, we propose the directional TSDF - a novel representation that stores opposite surfaces separate from each other. The marching cubes algorithm is modified accordingly to retrieve a coherent mesh representation. We further increase the accuracy by using surface gradient-based ray casting for fusing new measurements. We show that our method outperforms state-of-the-art TSDF reconstruction algorithms in mesh accuracy.
Tasks	3D Reconstruction
Published	2019-08-14
URL	https://arxiv.org/abs/1908.05146v1
PDF	https://arxiv.org/pdf/1908.05146v1.pdf
PWC	https://paperswithcode.com/paper/directional-tsdf-modeling-surface-orientation
Repo
Framework

Challenges of Human-Aware AI Systems


Title	Challenges of Human-Aware AI Systems
Authors	Subbarao Kambhampati
Abstract	From its inception, AI has had a rather ambivalent relationship to humans—swinging between their augmentation and replacement. Now, as AI technologies enter our everyday lives at an ever increasing pace, there is a greater need for AI systems to work synergistically with humans. To do this effectively, AI systems must pay more attention to aspects of intelligence that helped humans work with each other—including social intelligence. I will discuss the research challenges in designing such human-aware AI systems, including modeling the mental states of humans in the loop, recognizing their desires and intentions, providing proactive support, exhibiting explicable behavior, giving cogent explanations on demand, and engendering trust. I will survey the progress made so far on these challenges, and highlight some promising directions. I will also touch on the additional ethical quandaries that such systems pose. I will end by arguing that the quest for human-aware AI systems broadens the scope of AI enterprise, necessitates and facilitates true inter-disciplinary collaborations, and can go a long way towards increasing public acceptance of AI technologies.
Tasks
Published	2019-10-15
URL	https://arxiv.org/abs/1910.07089v1
PDF	https://arxiv.org/pdf/1910.07089v1.pdf
PWC	https://paperswithcode.com/paper/challenges-of-human-aware-ai-systems
Repo
Framework

Deep Learning Strategies For Joint Channel Estimation and Hybrid Beamforming in Multi-Carrier mm-Wave Massive MIMO Systems


Title	Deep Learning Strategies For Joint Channel Estimation and Hybrid Beamforming in Multi-Carrier mm-Wave Massive MIMO Systems
Authors	Ahmet M. Elbir, Kumar Vijay Mishra
Abstract	Hybrid analog and digital beamforming transceivers are instrumental in addressing the challenge of expensive hardware and high training overheads in the next generation millimeter-wave (mm-Wave) massive MIMO (multiple-input multiple-output) systems. However, lack of fully digital beamforming in hybrid architectures and short coherence times at mm-Wave impose additional constraints on the channel estimation. Prior works on addressing these challenges have focused largely on narrowband channels wherein optimization-based or greedy algorithms were employed to derive hybrid beamformers. In this paper, we introduce a deep learning (DL) approach for joint channel estimation and hybrid beamforming for frequency-selective, wideband mm-Wave systems. In particular, we consider a massive MIMO Orthogonal Frequency Division Multiplexing (MIMO-OFDM) system and propose three different DL frameworks comprising convolutional neural networks (CNNs), which accept the received pilot signal as input and yield the hybrid beamformers at the output. Numerical experiments demonstrate that, compared to the current state-of-the-art optimization and DL methods, our approach provides higher spectral efficiency, lesser computational cost, and higher tolerance against the deviations in the received pilot data, corrupted channel matrix, and propagation environment.
Tasks
Published	2019-12-20
URL	https://arxiv.org/abs/1912.10036v1
PDF	https://arxiv.org/pdf/1912.10036v1.pdf
PWC	https://paperswithcode.com/paper/deep-learning-strategies-for-joint-channel
Repo
Framework

Squared English Word: A Method of Generating Glyph to Use Super Characters for Sentiment Analysis


Title	Squared English Word: A Method of Generating Glyph to Use Super Characters for Sentiment Analysis
Authors	Baohua Sun, Lin Yang, Catherine Chi, Wenhan Zhang, Michael Lin
Abstract	The Super Characters method addresses sentiment analysis problems by first converting the input text into images and then applying 2D-CNN models to classify the sentiment. It achieves state of the art performance on many benchmark datasets. However, it is not as straightforward to apply in Latin languages as in Asian languages. Because the 2D-CNN model is designed to recognize two-dimensional images, it is better if the inputs are in the form of glyphs. In this paper, we propose SEW (Squared English Word) method generating a squared glyph for each English word by drawing Super Characters images of each English word at the alphabet level, combining the squared glyph together into a whole Super Characters image at the sentence level, and then applying the CNN model to classify the sentiment within the sentence. We applied the SEW method to Wikipedia dataset and obtained a 2.1% accuracy gain compared to the original Super Characters method. For multi-modal data with both structured tabular data and unstructured natural language text, the modified SEW method integrates the data into a single image and classifies sentiment with one unified CNN model.
Tasks	Sentiment Analysis
Published	2019-01-24
URL	https://arxiv.org/abs/1902.02160v2
PDF	https://arxiv.org/pdf/1902.02160v2.pdf
PWC	https://paperswithcode.com/paper/squared-english-word-a-method-of-generating
Repo
Framework

Fast Prototyping a Dialogue Comprehension System for Nurse-Patient Conversations on Symptom Monitoring


Title	Fast Prototyping a Dialogue Comprehension System for Nurse-Patient Conversations on Symptom Monitoring
Authors	Zhengyuan Liu, Hazel Lim, Nur Farah Ain Binte Suhaimi, Shao Chuen Tong, Sharon Ong, Angela Ng, Sheldon Lee, Michael R. Macdonald, Savitha Ramasamy, Pavitra Krishnaswamy, Wai Leng Chow, Nancy F. Chen
Abstract	Data for human-human spoken dialogues for research and development are currently very limited in quantity, variety, and sources; such data are even scarcer in healthcare. In this work, we investigate fast prototyping of a dialogue comprehension system by leveraging on minimal nurse-to-patient conversations. We propose a framework inspired by nurse-initiated clinical symptom monitoring conversations to construct a simulated human-human dialogue dataset, embodying linguistic characteristics of spoken interactions like thinking aloud, self-contradiction, and topic drift. We then adopt an established bidirectional attention pointer network on this simulated dataset, achieving more than 80% F1 score on a held-out test set from real-world nurse-to-patient conversations. The ability to automatically comprehend conversations in the healthcare domain by exploiting only limited data has implications for improving clinical workflows through red flag symptom detection and triaging capabilities. We demonstrate the feasibility for efficient and effective extraction, retrieval and comprehension of symptom checking information discussed in multi-turn human-human spoken conversations.
Tasks
Published	2019-03-08
URL	http://arxiv.org/abs/1903.03530v2
PDF	http://arxiv.org/pdf/1903.03530v2.pdf
PWC	https://paperswithcode.com/paper/fast-prototyping-a-dialogue-comprehension
Repo
Framework