May 6, 2019

2709 words 13 mins read

Paper Group ANR 357

On Duality Of Multiple Target Tracking and Segmentation. A Theoretical Study of The Relationship Between Whole An ELM Network and Its Subnetworks. Research Priorities for Robust and Beneficial Artificial Intelligence. Balancing Appearance and Context in Sketch Interpretation. An Approximation Approach for Solving the Subpath Planning Problem. Learn …

On Duality Of Multiple Target Tracking and Segmentation


Title	On Duality Of Multiple Target Tracking and Segmentation
Authors	Yicong Tian, Mubarak Shah
Abstract	Traditionally, object tracking and segmentation are treated as two separate problems and solved independently. However, in this paper, we argue that tracking and segmentation are actually closely related and solving one should help the other. On one hand, the object track, which is a set of bounding boxes with one bounding box in every frame, would provide strong high-level guidance for the target/background segmentation task. On the other hand, the object segmentation would separate object from other objects and background, which will be useful for determining track locations in every frame. We propose a novel framework which combines online multiple target tracking and segmentation in a video. In our approach, the tracking and segmentation problems are coupled by Lagrange dual decomposition, which leads to more accurate segmentation results and also \emph{helps resolve typical difficulties in multiple target tracking, such as occlusion handling, ID-switch and track drifting}. To track targets, an individual appearance model is learned for each target via structured learning and network flow is employed to generate tracks from densely sampled candidates. For segmentation, multi-label Conditional Random Field (CRF) is applied to a superpixel based spatio-temporal graph in a segment of video to assign background or target labels to every superpixel. The experiments on diverse sequences show that our method outperforms state-of-the-art approaches for multiple target tracking as well as segmentation.
Tasks	Object Tracking, Semantic Segmentation
Published	2016-10-14
URL	http://arxiv.org/abs/1610.04542v1
PDF	http://arxiv.org/pdf/1610.04542v1.pdf
PWC	https://paperswithcode.com/paper/on-duality-of-multiple-target-tracking-and
Repo
Framework

A Theoretical Study of The Relationship Between Whole An ELM Network and Its Subnetworks


Title	A Theoretical Study of The Relationship Between Whole An ELM Network and Its Subnetworks
Authors	Enmei Tu, Guanghao Zhang, Lily Rachmawati, Eshan Rajabally, Guang-Bin Huang
Abstract	A biological neural network is constituted by numerous subnetworks and modules with different functionalities. For an artificial neural network, the relationship between a network and its subnetworks is also important and useful for both theoretical and algorithmic research, i.e. it can be exploited to develop incremental network training algorithm or parallel network training algorithm. In this paper we explore the relationship between an ELM neural network and its subnetworks. To the best of our knowledge, we are the first to prove a theorem that shows an ELM neural network can be scattered into subnetworks and its optimal solution can be constructed recursively by the optimal solutions of these subnetworks. Based on the theorem we also present two algorithms to train a large ELM neural network efficiently: one is a parallel network training algorithm and the other is an incremental network training algorithm. The experimental results demonstrate the usefulness of the theorem and the validity of the developed algorithms.
Tasks
Published	2016-10-30
URL	http://arxiv.org/abs/1610.09608v1
PDF	http://arxiv.org/pdf/1610.09608v1.pdf
PWC	https://paperswithcode.com/paper/a-theoretical-study-of-the-relationship
Repo
Framework

Research Priorities for Robust and Beneficial Artificial Intelligence


Title	Research Priorities for Robust and Beneficial Artificial Intelligence
Authors	Stuart Russell, Daniel Dewey, Max Tegmark
Abstract	Success in the quest for artificial intelligence has the potential to bring unprecedented benefits to humanity, and it is therefore worthwhile to investigate how to maximize these benefits while avoiding potential pitfalls. This article gives numerous examples (which should by no means be construed as an exhaustive list) of such worthwhile research aimed at ensuring that AI remains robust and beneficial.
Tasks
Published	2016-02-10
URL	http://arxiv.org/abs/1602.03506v1
PDF	http://arxiv.org/pdf/1602.03506v1.pdf
PWC	https://paperswithcode.com/paper/research-priorities-for-robust-and-beneficial
Repo
Framework

Balancing Appearance and Context in Sketch Interpretation


Title	Balancing Appearance and Context in Sketch Interpretation
Authors	Yale Song, Randall Davis, Kaichen Ma, Dana L. Penny
Abstract	We describe a sketch interpretation system that detects and classifies clock numerals created by subjects taking the Clock Drawing Test, a clinical tool widely used to screen for cognitive impairments (e.g., dementia). We describe how it balances appearance and context, and document its performance on some 2,000 drawings (about 24K clock numerals) produced by a wide spectrum of patients. We calibrate the utility of different forms of context, describing experiments with Conditional Random Fields trained and tested using a variety of features. We identify context that contributes to interpreting otherwise ambiguous or incomprehensible strokes. We describe ST-slices, a novel representation that enables “unpeeling” the layers of ink that result when people overwrite, which often produces ink impossible to analyze if only the final drawing is examined. We characterize when ST-slices work, calibrate their impact on performance, and consider their breadth of applicability.
Tasks
Published	2016-04-25
URL	http://arxiv.org/abs/1604.07429v1
PDF	http://arxiv.org/pdf/1604.07429v1.pdf
PWC	https://paperswithcode.com/paper/balancing-appearance-and-context-in-sketch
Repo
Framework

An Approximation Approach for Solving the Subpath Planning Problem


Title	An Approximation Approach for Solving the Subpath Planning Problem
Authors	Masoud Safilian, S. Mehdi Tashakkori, Sepehr Eghbali, Aliakbar Safilian
Abstract	The subpath planning problem is a branch of the path planning problem, which has widespread applications in automated manufacturing process as well as vehicle and robot navigation. This problem is to find the shortest path or tour subject for travelling a set of given subpaths. The current approaches for dealing with the subpath planning problem are all based on meta-heuristic approaches. It is well-known that meta-heuristic based approaches have several deficiencies. To address them, we propose a novel approximation algorithm in the O(n^3) time complexity class, which guarantees to solve any subpath planning problem instance with the fixed ratio bound of 2. Also, the formal proofs of the claims, our empirical evaluation shows that our approximation method acts much better than a state-of-the-art method, both in result and execution time.
Tasks	Robot Navigation
Published	2016-03-20
URL	http://arxiv.org/abs/1603.06217v1
PDF	http://arxiv.org/pdf/1603.06217v1.pdf
PWC	https://paperswithcode.com/paper/an-approximation-approach-for-solving-the
Repo
Framework

Learning Macro-actions for State-Space Planning


Title	Learning Macro-actions for State-Space Planning
Authors	Sandra Castellanos-Paez, Damien Pellier, Humbert Fiorino, Sylvie Pesty
Abstract	Planning has achieved significant progress in recent years. Among the various approaches to scale up plan synthesis, the use of macro-actions has been widely explored. As a first stage towards the development of a solution to learn on-line macro-actions, we propose an algorithm to identify useful macro-actions based on data mining techniques. The integration in the planning search of these learned macro-actions shows significant improvements over four classical planning benchmarks.
Tasks
Published	2016-10-07
URL	http://arxiv.org/abs/1610.02293v1
PDF	http://arxiv.org/pdf/1610.02293v1.pdf
PWC	https://paperswithcode.com/paper/learning-macro-actions-for-state-space
Repo
Framework

Improving Human-Machine Cooperative Visual Search With Soft Highlighting


Title	Improving Human-Machine Cooperative Visual Search With Soft Highlighting
Authors	Ronald T. Kneusel, Michael C. Mozer
Abstract	Advances in machine learning have produced systems that attain human-level performance on certain visual tasks, e.g., object identification. Nonetheless, other tasks requiring visual expertise are unlikely to be entrusted to machines for some time, e.g., satellite and medical imagery analysis. We describe a human-machine cooperative approach to visual search, the aim of which is to outperform either human or machine acting alone. The traditional route to augmenting human performance with automatic classifiers is to draw boxes around regions of an image deemed likely to contain a target. Human experts typically reject this type of hard highlighting. We propose instead a soft highlighting technique in which the saliency of regions of the visual field is modulated in a graded fashion based on classifier confidence level. We report on experiments with both synthetic and natural images showing that soft highlighting achieves a performance synergy surpassing that attained by hard highlighting.
Tasks
Published	2016-12-24
URL	http://arxiv.org/abs/1612.08117v1
PDF	http://arxiv.org/pdf/1612.08117v1.pdf
PWC	https://paperswithcode.com/paper/improving-human-machine-cooperative-visual
Repo
Framework

Winograd Schemas and Machine Translation


Title	Winograd Schemas and Machine Translation
Authors	Ernest Davis
Abstract	A Winograd schema is a pair of sentences that differ in a single word and that contain an ambiguous pronoun whose referent is different in the two sentences and requires the use of commonsense knowledge or world knowledge to disambiguate. This paper discusses how Winograd schemas and other sentence pairs could be used as challenges for machine translation using distinctions between pronouns, such as gender, that appear in the target language but not in the source.
Tasks	Machine Translation
Published	2016-08-05
URL	http://arxiv.org/abs/1608.01884v2
PDF	http://arxiv.org/pdf/1608.01884v2.pdf
PWC	https://paperswithcode.com/paper/winograd-schemas-and-machine-translation
Repo
Framework

K-Nearest Neighbor Classification Using Anatomized Data


Title	K-Nearest Neighbor Classification Using Anatomized Data
Authors	Koray Mancuhan, Chris Clifton
Abstract	This paper analyzes k nearest neighbor classification with training data anonymized using anatomy. Anatomy preserves all data values, but introduces uncertainty in the mapping between identifying and sensitive values. We first study the theoretical effect of the anatomized training data on the k nearest neighbor error rate bounds, nearest neighbor convergence rate, and Bayesian error. We then validate the derived bounds empirically. We show that 1) Learning from anatomized data approaches the limits of learning through the unprotected data (although requiring larger training data), and 2) nearest neighbor using anatomized data outperforms nearest neighbor on generalization-based anonymization.
Tasks
Published	2016-10-19
URL	http://arxiv.org/abs/1610.06048v1
PDF	http://arxiv.org/pdf/1610.06048v1.pdf
PWC	https://paperswithcode.com/paper/k-nearest-neighbor-classification-using
Repo
Framework

EgoSampling: Wide View Hyperlapse from Egocentric Videos


Title	EgoSampling: Wide View Hyperlapse from Egocentric Videos
Authors	Tavi Halperin, Yair Poleg, Chetan Arora, Shmuel Peleg
Abstract	The possibility of sharing one’s point of view makes use of wearable cameras compelling. These videos are often long, boring and coupled with extreme shake, as the camera is worn on a moving person. Fast forwarding (i.e. frame sampling) is a natural choice for quick video browsing. However, this accentuates the shake caused by natural head motion in an egocentric video, making the fast forwarded video useless. We propose EgoSampling, an adaptive frame sampling that gives stable, fast forwarded, hyperlapse videos. Adaptive frame sampling is formulated as an energy minimization problem, whose optimal solution can be found in polynomial time. We further turn the camera shake from a drawback into a feature, enabling the increase in field-of-view of the output video. This is obtained when each output frame is mosaiced from several input frames. The proposed technique also enables the generation of a single hyperlapse video from multiple egocentric videos, allowing even faster video consumption.
Tasks
Published	2016-04-26
URL	http://arxiv.org/abs/1604.07741v2
PDF	http://arxiv.org/pdf/1604.07741v2.pdf
PWC	https://paperswithcode.com/paper/egosampling-wide-view-hyperlapse-from
Repo
Framework

Deep Gaussian Processes for Regression using Approximate Expectation Propagation


Title	Deep Gaussian Processes for Regression using Approximate Expectation Propagation
Authors	Thang D. Bui, Daniel Hernández-Lobato, Yingzhen Li, José Miguel Hernández-Lobato, Richard E. Turner
Abstract	Deep Gaussian processes (DGPs) are multi-layer hierarchical generalisations of Gaussian processes (GPs) and are formally equivalent to neural networks with multiple, infinitely wide hidden layers. DGPs are nonparametric probabilistic models and as such are arguably more flexible, have a greater capacity to generalise, and provide better calibrated uncertainty estimates than alternative deep models. This paper develops a new approximate Bayesian learning scheme that enables DGPs to be applied to a range of medium to large scale regression problems for the first time. The new method uses an approximate Expectation Propagation procedure and a novel and efficient extension of the probabilistic backpropagation algorithm for learning. We evaluate the new method for non-linear regression on eleven real-world datasets, showing that it always outperforms GP regression and is almost always better than state-of-the-art deterministic and sampling-based approximate inference methods for Bayesian neural networks. As a by-product, this work provides a comprehensive analysis of six approximate Bayesian methods for training neural networks.
Tasks	Gaussian Processes
Published	2016-02-12
URL	http://arxiv.org/abs/1602.04133v1
PDF	http://arxiv.org/pdf/1602.04133v1.pdf
PWC	https://paperswithcode.com/paper/deep-gaussian-processes-for-regression-using
Repo
Framework

Learning opening books in partially observable games: using random seeds in Phantom Go


Title	Learning opening books in partially observable games: using random seeds in Phantom Go
Authors	Tristan Cazenave, Jialin Liu, Fabien Teytaud, Olivier Teytaud
Abstract	Many artificial intelligences (AIs) are randomized. One can be lucky or unlucky with the random seed; we quantify this effect and show that, maybe contrarily to intuition, this is far from being negligible. Then, we apply two different existing algorithms for selecting good seeds and good probability distributions over seeds. This mainly leads to learning an opening book. We apply this to Phantom Go, which, as all phantom games, is hard for opening book learning. We improve the winning rate from 50% to 70% in 5x5 against the same AI, and from approximately 0% to 40% in 5x5, 7x7 and 9x9 against a stronger (learning) opponent.
Tasks
Published	2016-07-08
URL	http://arxiv.org/abs/1607.02431v1
PDF	http://arxiv.org/pdf/1607.02431v1.pdf
PWC	https://paperswithcode.com/paper/learning-opening-books-in-partially
Repo
Framework

Towards the bio-personalization of music recommendation systems: A single-sensor EEG biomarker of subjective music preference


Title	Towards the bio-personalization of music recommendation systems: A single-sensor EEG biomarker of subjective music preference
Authors	Dimitrios A. Adamos, Stavros I. Dimitriadis, Nikolaos A. Laskaris
Abstract	Recent advances in biosensors technology and mobile electroencephalographic (EEG) interfaces have opened new application fields for cognitive monitoring. A computable biomarker for the assessment of spontaneous aesthetic brain responses during music listening is introduced here. It derives from well-established measures of cross-frequency coupling (CFC) and quantifies the music-induced alterations in the dynamic relationships between brain rhythms. During a stage of exploratory analysis, and using the signals from a suitably designed experiment, we established the biomarker, which acts on brain activations recorded over the left prefrontal cortex and focuses on the functional coupling between high-beta and low-gamma oscillations. Based on data from an additional experimental paradigm, we validated the introduced biomarker and showed its relevance for expressing the subjective aesthetic appreciation of a piece of music. Our approach resulted in an affordable tool that can promote human-machine interaction and, by serving as a personalized music annotation strategy, can be potentially integrated into modern flexible music recommendation systems. Keywords: Cross-frequency coupling; Human-computer interaction; Brain-computer interface
Tasks	EEG, Recommendation Systems
Published	2016-09-21
URL	http://arxiv.org/abs/1609.07365v1
PDF	http://arxiv.org/pdf/1609.07365v1.pdf
PWC	https://paperswithcode.com/paper/towards-the-bio-personalization-of-music
Repo
Framework

Log-based Evaluation of Label Splits for Process Models


Title	Log-based Evaluation of Label Splits for Process Models
Authors	Niek Tax, Natalia Sidorova, Reinder Haakma, Wil M. P. van der Aalst
Abstract	Process mining techniques aim to extract insights in processes from event logs. One of the challenges in process mining is identifying interesting and meaningful event labels that contribute to a better understanding of the process. Our application area is mining data from smart homes for elderly, where the ultimate goal is to signal deviations from usual behavior and provide timely recommendations in order to extend the period of independent living. Extracting individual process models showing user behavior is an important instrument in achieving this goal. However, the interpretation of sensor data at an appropriate abstraction level is not straightforward. For example, a motion sensor in a bedroom can be triggered by tossing and turning in bed or by getting up. We try to derive the actual activity depending on the context (time, previous events, etc.). In this paper we introduce the notion of label refinements, which links more abstract event descriptions with their more refined counterparts. We present a statistical evaluation method to determine the usefulness of a label refinement for a given event log from a process perspective. Based on data from smart homes, we show how our statistical evaluation method for label refinements can be used in practice. Our method was able to select two label refinements out of a set of candidate label refinements that both had a positive effect on model precision.
Tasks
Published	2016-06-23
URL	http://arxiv.org/abs/1606.07259v1
PDF	http://arxiv.org/pdf/1606.07259v1.pdf
PWC	https://paperswithcode.com/paper/log-based-evaluation-of-label-splits-for
Repo
Framework

A Subpath Kernel for Learning Hierarchical Image Representations


Title	A Subpath Kernel for Learning Hierarchical Image Representations
Authors	Yanwei Cui, Laetitia Chapel, Sébastien Lefèvre
Abstract	Tree kernels have demonstrated their ability to deal with hierarchical data, as the intrinsic tree structure often plays a discriminative role. While such kernels have been successfully applied to various domains such as nature language processing and bioinformatics, they mostly concentrate on ordered trees and whose nodes are described by symbolic data. Meanwhile, hierarchical representations have gained increasing interest to describe image content. This is particularly true in remote sensing, where such representations allow for revealing different objects of interest at various scales through a tree structure. However, the induced trees are unordered and the nodes are equipped with numerical features. In this paper, we propose a new structured kernel for hierarchical image representations which is built on the concept of subpath kernel. Experimental results on both artificial and remote sensing datasets show that the proposed kernel manages to deal with the hierarchical nature of the data, leading to better classification rates.
Tasks
Published	2016-04-06
URL	http://arxiv.org/abs/1604.01787v1
PDF	http://arxiv.org/pdf/1604.01787v1.pdf
PWC	https://paperswithcode.com/paper/a-subpath-kernel-for-learning-hierarchical
Repo
Framework