October 19, 2019

2839 words 14 mins read

Paper Group ANR 341

A Neurobiologically Motivated Analysis of Distributional Semantic Models. Spatiotemporal Learning of Dynamic Gestures from 3D Point Cloud Data. Breast Cancer Diagnosis via Classification Algorithms. Representational efficiency outweighs action efficiency in human program induction. Visual Memory for Robust Path Following. Decision Support System fo …

A Neurobiologically Motivated Analysis of Distributional Semantic Models


Title	A Neurobiologically Motivated Analysis of Distributional Semantic Models
Authors	Akira Utsumi
Abstract	The pervasive use of distributional semantic models or word embeddings in a variety of research fields is due to their remarkable ability to represent the meanings of words for both practical application and cognitive modeling. However, little has been known about what kind of information is encoded in text-based word vectors. This lack of understanding is particularly problematic when word vectors are regarded as a model of semantic representation for abstract concepts. This paper attempts to reveal the internal information of distributional word vectors by the analysis using Binder et al.‘s (2016) brain-based vectors, explicitly structured conceptual representations based on neurobiologically motivated attributes. In the analysis, the mapping from text-based vectors to brain-based vectors is trained and prediction performance is evaluated by comparing the estimated and original brain-based vectors. The analysis demonstrates that social and cognitive information is better encoded in text-based word vectors, but emotional information is not. This result is discussed in terms of embodied theories for abstract concepts.
Tasks	Word Embeddings
Published	2018-02-06
URL	http://arxiv.org/abs/1802.01830v1
PDF	http://arxiv.org/pdf/1802.01830v1.pdf
PWC	https://paperswithcode.com/paper/a-neurobiologically-motivated-analysis-of
Repo
Framework

Spatiotemporal Learning of Dynamic Gestures from 3D Point Cloud Data


Title	Spatiotemporal Learning of Dynamic Gestures from 3D Point Cloud Data
Authors	Joshua Owoyemi, Koichi Hashimoto
Abstract	In this paper, we demonstrate an end-to-end spatiotemporal gesture learning approach for 3D point cloud data using a new gestures dataset of point clouds acquired from a 3D sensor. Nine classes of gestures were learned from gestures sample data. We mapped point cloud data into dense occupancy grids, then time steps of the occupancy grids are used as inputs into a 3D convolutional neural network which learns the spatiotemporal features in the data without explicit modeling of gesture dynamics. We also introduced a 3D region of interest jittering approach for point cloud data augmentation. This resulted in an increased classification accuracy of up to 10% when the augmented data is added to the original training data. The developed model is able to classify gestures from the dataset with 84.44% accuracy. We propose that point cloud data will be a more viable data type for scene understanding and motion recognition, as 3D sensors become ubiquitous in years to come.
Tasks	Data Augmentation, Scene Understanding
Published	2018-04-24
URL	http://arxiv.org/abs/1804.08859v1
PDF	http://arxiv.org/pdf/1804.08859v1.pdf
PWC	https://paperswithcode.com/paper/spatiotemporal-learning-of-dynamic-gestures
Repo
Framework

Breast Cancer Diagnosis via Classification Algorithms


Title	Breast Cancer Diagnosis via Classification Algorithms
Authors	Reihaneh Entezari
Abstract	In this paper, we analyze the Wisconsin Diagnostic Breast Cancer Data using Machine Learning classification techniques, such as the SVM, Bayesian Logistic Regression (Variational Approximation), and K-Nearest-Neighbors. We describe each model, and compare their performance through different measures. We conclude that SVM has the best performance among all other classifiers, while it competes closely with the Bayesian Logistic Regression that is ranked second best method for this dataset.
Tasks
Published	2018-07-03
URL	http://arxiv.org/abs/1807.01334v1
PDF	http://arxiv.org/pdf/1807.01334v1.pdf
PWC	https://paperswithcode.com/paper/breast-cancer-diagnosis-via-classification
Repo
Framework

Representational efficiency outweighs action efficiency in human program induction


Title	Representational efficiency outweighs action efficiency in human program induction
Authors	Sophia Sanborn, David D. Bourgin, Michael Chang, Thomas L. Griffiths
Abstract	The importance of hierarchically structured representations for tractable planning has long been acknowledged. However, the questions of how people discover such abstractions and how to define a set of optimal abstractions remain open. This problem has been explored in cognitive science in the problem solving literature and in computer science in hierarchical reinforcement learning. Here, we emphasize an algorithmic perspective on learning hierarchical representations in which the objective is to efficiently encode the structure of the problem, or, equivalently, to learn an algorithm with minimal length. We introduce a novel problem-solving paradigm that links problem solving and program induction under the Markov Decision Process (MDP) framework. Using this task, we target the question of whether humans discover hierarchical solutions by maximizing efficiency in number of actions they generate or by minimizing the complexity of the resulting representation and find evidence for the primacy of representational efficiency.
Tasks	Hierarchical Reinforcement Learning
Published	2018-07-18
URL	http://arxiv.org/abs/1807.07134v1
PDF	http://arxiv.org/pdf/1807.07134v1.pdf
PWC	https://paperswithcode.com/paper/representational-efficiency-outweighs-action
Repo
Framework

Visual Memory for Robust Path Following


Title	Visual Memory for Robust Path Following
Authors	Ashish Kumar, Saurabh Gupta, David Fouhey, Sergey Levine, Jitendra Malik
Abstract	Humans routinely retrace paths in a novel environment both forwards and backwards despite uncertainty in their motion. This paper presents an approach for doing so. Given a demonstration of a path, a first network generates a path abstraction. Equipped with this abstraction, a second network observes the world and decides how to act to retrace the path under noisy actuation and a changing environment. The two networks are optimized end-to-end at training time. We evaluate the method in two realistic simulators, performing path following and homing under actuation noise and environmental changes. Our experiments show that our approach outperforms classical approaches and other learning based baselines.
Tasks
Published	2018-12-03
URL	http://arxiv.org/abs/1812.00940v1
PDF	http://arxiv.org/pdf/1812.00940v1.pdf
PWC	https://paperswithcode.com/paper/visual-memory-for-robust-path-following
Repo
Framework

Decision Support System for Renal Transplantation


Title	Decision Support System for Renal Transplantation
Authors	Ehsan Khan, Avishek Choudhury, Amy L Friedman, Daehan Won
Abstract	The burgeoning need for kidney transplantation mandates immediate attention. Mismatch of deceased donor-recipient kidney leads to post-transplant death. To ensure ideal kidney donor-recipient match and minimize post-transplant deaths, the paper develops a prediction model that identifies factors that determine the probability of success of renal transplantation, that is, if the kidney procured from the deceased donor can be transplanted or discarded. The paper conducts a study enveloping data for 584 imported kidneys collected from 12 transplant centers associated with an organ procurement organization located in New York City, NY. The predicting model yielding best performance measures can be beneficial to the healthcare industry. Transplant centers and organ procurement organizations can take advantage of the prediction model to efficiently predict the outcome of kidney transplantation. Consequently, it will reduce the mortality rate caused by mismatching of donor-recipient kidney transplantation during the surgery. Keywords
Tasks
Published	2018-12-11
URL	http://arxiv.org/abs/1812.10381v1
PDF	http://arxiv.org/pdf/1812.10381v1.pdf
PWC	https://paperswithcode.com/paper/decision-support-system-for-renal
Repo
Framework

DOCK: Detecting Objects by transferring Common-sense Knowledge


Title	DOCK: Detecting Objects by transferring Common-sense Knowledge
Authors	Krishna Kumar Singh, Santosh Divvala, Ali Farhadi, Yong Jae Lee
Abstract	We present a scalable approach for Detecting Objects by transferring Common-sense Knowledge (DOCK) from source to target categories. In our setting, the training data for the source categories have bounding box annotations, while those for the target categories only have image-level annotations. Current state-of-the-art approaches focus on image-level visual or semantic similarity to adapt a detector trained on the source categories to the new target categories. In contrast, our key idea is to (i) use similarity not at the image-level, but rather at the region-level, and (ii) leverage richer common-sense (based on attribute, spatial, etc.) to guide the algorithm towards learning the correct detections. We acquire such common-sense cues automatically from readily-available knowledge bases without any extra human effort. On the challenging MS COCO dataset, we find that common-sense knowledge can substantially improve detection performance over existing transfer-learning baselines.
Tasks	Common Sense Reasoning, Semantic Similarity, Semantic Textual Similarity, Transfer Learning
Published	2018-04-03
URL	http://arxiv.org/abs/1804.01077v2
PDF	http://arxiv.org/pdf/1804.01077v2.pdf
PWC	https://paperswithcode.com/paper/dock-detecting-objects-by-transferring-common
Repo
Framework

Multi-Dimensional, Multilayer, Nonlinear and Dynamic HITS


Title	Multi-Dimensional, Multilayer, Nonlinear and Dynamic HITS
Authors	Francesca Arrigo, Francesco Tudisco
Abstract	We introduce a ranking model for temporal multi-dimensional weighted and directed networks based on the Perron eigenvector of a multi-homogeneous order-preserving map. The model extends to the temporal multilayer setting the HITS algorithm and defines five centrality vectors: two for the nodes, two for the layers, and one for the temporal stamps. Nonlinearity is introduced in the standard HITS model in order to guarantee existence and uniqueness of these centrality vectors for any network, without any requirement on its connectivity structure. We introduce a globally convergent power iteration like algorithm for the computation of the centrality vectors. Numerical experiments on real-world networks are performed in order to assess the effectiveness of the proposed model and showcase the performance of the accompanying algorithm.
Tasks
Published	2018-09-21
URL	http://arxiv.org/abs/1809.08004v1
PDF	http://arxiv.org/pdf/1809.08004v1.pdf
PWC	https://paperswithcode.com/paper/multi-dimensional-multilayer-nonlinear-and
Repo
Framework

Large-scale Heteroscedastic Regression via Gaussian Process


Title	Large-scale Heteroscedastic Regression via Gaussian Process
Authors	Haitao Liu, Yew-Soon Ong, Jianfei Cai
Abstract	Heteroscedastic regression considering the varying noises among observations has many applications in the fields like machine learning and statistics. Here we focus on the heteroscedastic Gaussian process (HGP) regression which integrates the latent function and the noise function together in a unified non-parametric Bayesian framework. Though showing remarkable performance, HGP suffers from the cubic time complexity, which strictly limits its application to big data. To improve the scalability, we first develop a variational sparse inference algorithm, named VSHGP, to handle large-scale datasets. Furthermore, two variants are developed to improve the scalability and capability of VSHGP. The first is stochastic VSHGP (SVSHGP) which derives a factorized evidence lower bound, thus enhancing efficient stochastic variational inference. The second is distributed VSHGP (DVSHGP) which (i) follows the Bayesian committee machine formalism to distribute computations over multiple local VSHGP experts with many inducing points; and (ii) adopts hybrid parameters for experts to guard against over-fitting and capture local variety. The superiority of DVSHGP and SVSHGP as compared to existing scalable heteroscedastic/homoscedastic GPs is then extensively verified on various datasets.
Tasks
Published	2018-11-03
URL	https://arxiv.org/abs/1811.01179v3
PDF	https://arxiv.org/pdf/1811.01179v3.pdf
PWC	https://paperswithcode.com/paper/large-scale-heteroscedastic-regression-via
Repo
Framework

A Survey of Knowledge Representation in Service Robotics


Title	A Survey of Knowledge Representation in Service Robotics
Authors	David Paulius, Yu Sun
Abstract	Within the realm of service robotics, researchers have placed a great amount of effort into learning, understanding, and representing motions as manipulations for task execution by robots. The task of robot learning and problem-solving is very broad, as it integrates a variety of tasks such as object detection, activity recognition, task/motion planning, localization, knowledge representation and retrieval, and the intertwining of perception/vision and machine learning techniques. In this paper, we solely focus on knowledge representations and notably how knowledge is typically gathered, represented, and reproduced to solve problems as done by researchers in the past decades. In accordance with the definition of knowledge representations, we discuss the key distinction between such representations and useful learning models that have extensively been introduced and studied in recent years, such as machine learning, deep learning, probabilistic modelling, and semantic graphical structures. Along with an overview of such tools, we discuss the problems which have existed in robot learning and how they have been built and used as solutions, technologies or developments (if any) which have contributed to solving them. Finally, we discuss key principles that should be considered when designing an effective knowledge representation.
Tasks	Activity Recognition, Motion Planning, Object Detection, Scene Understanding, Temporal Action Localization
Published	2018-07-05
URL	http://arxiv.org/abs/1807.02192v3
PDF	http://arxiv.org/pdf/1807.02192v3.pdf
PWC	https://paperswithcode.com/paper/a-survey-of-knowledge-representation-for
Repo
Framework

Online Self-supervised Scene Segmentation for Micro Aerial Vehicles


Title	Online Self-supervised Scene Segmentation for Micro Aerial Vehicles
Authors	Shreyansh Daftry, Yashasvi Agrawal, Larry Matthies
Abstract	Recently, there have been numerous advances in the development of payload and power constrained lightweight Micro Aerial Vehicles (MAVs). As these robots aspire for high-speed autonomous flights in complex dynamic environments, robust scene understanding at long-range becomes critical. The problem is heavily characterized by either the limitations imposed by sensor capabilities for geometry-based methods, or the need for large-amounts of manually annotated training data required by data-driven methods. This motivates the need to build systems that have the capability to alleviate these problems by exploiting the complimentary strengths of both geometry and data-driven methods. In this paper, we take a step in this direction and propose a generic framework for adaptive scene segmentation using self-supervised online learning. We present this in the context of vision-based autonomous MAV flight, and demonstrate the efficacy of our proposed system through extensive experiments on benchmark datasets and real-world field tests.
Tasks	Scene Segmentation, Scene Understanding
Published	2018-06-13
URL	http://arxiv.org/abs/1806.05269v1
PDF	http://arxiv.org/pdf/1806.05269v1.pdf
PWC	https://paperswithcode.com/paper/online-self-supervised-scene-segmentation-for
Repo
Framework

Collaborative Large-Scale Dense 3D Reconstruction with Online Inter-Agent Pose Optimisation


Title	Collaborative Large-Scale Dense 3D Reconstruction with Online Inter-Agent Pose Optimisation
Authors	Stuart Golodetz, Tommaso Cavallari, Nicholas A Lord, Victor A Prisacariu, David W Murray, Philip H S Torr
Abstract	Reconstructing dense, volumetric models of real-world 3D scenes is important for many tasks, but capturing large scenes can take significant time, and the risk of transient changes to the scene goes up as the capture time increases. These are good reasons to want instead to capture several smaller sub-scenes that can be joined to make the whole scene. Achieving this has traditionally been difficult: joining sub-scenes that may never have been viewed from the same angle requires a high-quality camera relocaliser that can cope with novel poses, and tracking drift in each sub-scene can prevent them from being joined to make a consistent overall scene. Recent advances, however, have significantly improved our ability to capture medium-sized sub-scenes with little to no tracking drift: real-time globally consistent reconstruction systems can close loops and re-integrate the scene surface on the fly, whilst new visual-inertial odometry approaches can significantly reduce tracking drift during live reconstruction. Moreover, high-quality regression forest-based relocalisers have recently been made more practical by the introduction of a method to allow them to be trained and used online. In this paper, we leverage these advances to present what to our knowledge is the first system to allow multiple users to collaborate interactively to reconstruct dense, voxel-based models of whole buildings using only consumer-grade hardware, a task that has traditionally been both time-consuming and dependent on the availability of specialised hardware. Using our system, an entire house or lab can be reconstructed in under half an hour and at a far lower cost than was previously possible.
Tasks	3D Reconstruction
Published	2018-01-25
URL	https://arxiv.org/abs/1801.08361v2
PDF	https://arxiv.org/pdf/1801.08361v2.pdf
PWC	https://paperswithcode.com/paper/collaborative-large-scale-dense-3d
Repo
Framework

Contributors profile modelization in crowdsourcing platforms


Title	Contributors profile modelization in crowdsourcing platforms
Authors	Constance Thierry, Jean-Christophe Dubois, Yolande Le Gall, Arnaud Martin
Abstract	The crowdsourcing consists in the externalisation of tasks to a crowd of people remunerated to execute this ones. The crowd, usually diversified, can include users without qualification and/or motivation for the tasks. In this paper we will introduce a new method of user expertise modelization in the crowdsourcing platforms based on the theory of belief functions in order to identify serious and qualificated users.
Tasks
Published	2018-11-19
URL	http://arxiv.org/abs/1811.07536v1
PDF	http://arxiv.org/pdf/1811.07536v1.pdf
PWC	https://paperswithcode.com/paper/contributors-profile-modelization-in
Repo
Framework

Aligned to the Object, not to the Image: A Unified Pose-aligned Representation for Fine-grained Recognition


Title	Aligned to the Object, not to the Image: A Unified Pose-aligned Representation for Fine-grained Recognition
Authors	Pei Guo, Ryan Farrell
Abstract	Dramatic appearance variation due to pose constitutes a great challenge in fine-grained recognition, one which recent methods using attention mechanisms or second-order statistics fail to adequately address. Modern CNNs typically lack an explicit understanding of object pose and are instead confused by entangled pose and appearance. In this paper, we propose a unified object representation built from a hierarchy of pose-aligned regions. Rather than representing an object by regions aligned to image axes, the proposed representation characterizes appearance relative to the object’s pose using pose-aligned patches whose features are robust to variations in pose, scale and rotation. We propose an algorithm that performs pose estimation and forms the unified object representation as the concatenation of hierarchical pose-aligned regions features, which is then fed into a classification network. The proposed algorithm surpasses the performance of other approaches, increasing the state-of-the-art by nearly 2% on the widely-used CUB-200 dataset and by more than 8% on the much larger NABirds dataset. The effectiveness of this paradigm relative to competing methods suggests the critical importance of disentangling pose and appearance for continued progress in fine-grained recognition.
Tasks	Fine-Grained Image Classification, Pose Estimation
Published	2018-01-27
URL	http://arxiv.org/abs/1801.09057v4
PDF	http://arxiv.org/pdf/1801.09057v4.pdf
PWC	https://paperswithcode.com/paper/aligned-to-the-object-not-to-the-image-a
Repo
Framework

The Importance of Context When Recommending TV Content: Dataset and Algorithms


Title	The Importance of Context When Recommending TV Content: Dataset and Algorithms
Authors	Miklas S. Kristoffersen, Sven E. Shepstone, Zheng-Hua Tan
Abstract	Home entertainment systems feature in a variety of usage scenarios with one or more simultaneous users, for whom the complexity of choosing media to consume has increased rapidly over the last decade. Users’ decision processes are complex and highly influenced by contextual settings, but data supporting the development and evaluation of context-aware recommender systems are scarce. In this paper we present a dataset of self-reported TV consumption enriched with contextual information of viewing situations. We show how choice of genre associates with, among others, the number of present users and users’ attention levels. Furthermore, we evaluate the performance of predicting chosen genres given different configurations of contextual information, and compare the results to contextless predictions. The results suggest that including contextual features in the prediction cause notable improvements, and both temporal and social context show significant contributions.
Tasks	Recommendation Systems
Published	2018-07-30
URL	https://arxiv.org/abs/1808.00337v2
PDF	https://arxiv.org/pdf/1808.00337v2.pdf
PWC	https://paperswithcode.com/paper/the-importance-of-context-when-recommending
Repo
Framework