July 29, 2019

2593 words 13 mins read

Paper Group ANR 126

Thinking, Fast and Slow: Combining Vector Spaces and Knowledge Graphs. Automatic Recognition of Coal and Gangue based on Convolution Neural Network. Multi-modal Aggregation for Video Classification. Output Reachable Set Estimation and Verification for Multi-Layer Neural Networks. Reinforced Video Captioning with Entailment Rewards. On the Relations …

Thinking, Fast and Slow: Combining Vector Spaces and Knowledge Graphs


Title	Thinking, Fast and Slow: Combining Vector Spaces and Knowledge Graphs
Authors	Sudip Mittal, Anupam Joshi, Tim Finin
Abstract	Knowledge graphs and vector space models are robust knowledge representation techniques with individual strengths and weaknesses. Vector space models excel at determining similarity between concepts, but are severely constrained when evaluating complex dependency relations and other logic-based operations that are a strength of knowledge graphs. We describe the VKG structure that helps unify knowledge graphs and vector representation of entities, and enables powerful inference methods and search capabilities that combine their complementary strengths. We analogize this to thinking `fast' in vector space along with thinking 'slow' and` deeply’ by reasoning over the knowledge graph. We have created a query processing engine that takes complex queries and decomposes them into subqueries optimized to run on the respective knowledge graph or vector view of a VKG. We show that the VKG structure can process specific queries that are not efficiently handled by vector spaces or knowledge graphs alone. We also demonstrate and evaluate the VKG structure and the query processing engine by developing a system called Cyber-All-Intel for knowledge extraction, representation and querying in an end-to-end pipeline grounded in the cybersecurity informatics domain.
Tasks	Knowledge Graphs
Published	2017-08-10
URL	http://arxiv.org/abs/1708.03310v2
PDF	http://arxiv.org/pdf/1708.03310v2.pdf
PWC	https://paperswithcode.com/paper/thinking-fast-and-slow-combining-vector
Repo
Framework

Automatic Recognition of Coal and Gangue based on Convolution Neural Network


Title	Automatic Recognition of Coal and Gangue based on Convolution Neural Network
Authors	Huichao Hong, Lixin Zheng, Jianqing Zhu, Shuwan Pan, Kaiting Zhou
Abstract	We designed a gangue sorting system,and built a convolutional neural network model based on AlexNet. Data enhancement and transfer learning are used to solve the problem which the convolution neural network has insufficient training data in the training stage. An object detection and region clipping algorithm is proposed to adjust the training image data to the optimum size. Compared with traditional neural network and SVM algorithm, this algorithm has higher recognition rate for coal and coal gangue, and provides important reference for identification and separation of coal and gangue.
Tasks	Object Detection, Transfer Learning
Published	2017-12-03
URL	http://arxiv.org/abs/1712.00720v1
PDF	http://arxiv.org/pdf/1712.00720v1.pdf
PWC	https://paperswithcode.com/paper/automatic-recognition-of-coal-and-gangue
Repo
Framework


Title	Multi-modal Aggregation for Video Classification
Authors	Chen Chen, Xiaowei Zhao, Yang Liu
Abstract	In this paper, we present a solution to Large-Scale Video Classification Challenge (LSVC2017) [1] that ranked the 1st place. We focused on a variety of modalities that cover visual, motion and audio. Also, we visualized the aggregation process to better understand how each modality takes effect. Among the extracted modalities, we found Temporal-Spatial features calculated by 3D convolution quite promising that greatly improved the performance. We attained the official metric mAP 0.8741 on the testing set with the ensemble model.
Tasks	Video Classification
Published	2017-10-27
URL	http://arxiv.org/abs/1710.10330v1
PDF	http://arxiv.org/pdf/1710.10330v1.pdf
PWC	https://paperswithcode.com/paper/multi-modal-aggregation-for-video
Repo
Framework

Output Reachable Set Estimation and Verification for Multi-Layer Neural Networks


Title	Output Reachable Set Estimation and Verification for Multi-Layer Neural Networks
Authors	Weiming Xiang, Hoang-Dung Tran, Taylor T. Johnson
Abstract	In this paper, the output reachable estimation and safety verification problems for multi-layer perceptron neural networks are addressed. First, a conception called maximum sensitivity in introduced and, for a class of multi-layer perceptrons whose activation functions are monotonic functions, the maximum sensitivity can be computed via solving convex optimization problems. Then, using a simulation-based method, the output reachable set estimation problem for neural networks is formulated into a chain of optimization problems. Finally, an automated safety verification is developed based on the output reachable set estimation result. An application to the safety verification for a robotic arm model with two joints is presented to show the effectiveness of proposed approaches.
Tasks
Published	2017-08-09
URL	http://arxiv.org/abs/1708.03322v2
PDF	http://arxiv.org/pdf/1708.03322v2.pdf
PWC	https://paperswithcode.com/paper/output-reachable-set-estimation-and
Repo
Framework

Reinforced Video Captioning with Entailment Rewards


Title	Reinforced Video Captioning with Entailment Rewards
Authors	Ramakanth Pasunuru, Mohit Bansal
Abstract	Sequence-to-sequence models have shown promising improvements on the temporal task of video captioning, but they optimize word-level cross-entropy loss during training. First, using policy gradient and mixed-loss methods for reinforcement learning, we directly optimize sentence-level task-based metrics (as rewards), achieving significant improvements over the baseline, based on both automatic metrics and human evaluation on multiple datasets. Next, we propose a novel entailment-enhanced reward (CIDEnt) that corrects phrase-matching based metrics (such as CIDEr) to only allow for logically-implied partial matches and avoid contradictions, achieving further significant improvements over the CIDEr-reward model. Overall, our CIDEnt-reward model achieves the new state-of-the-art on the MSR-VTT dataset.
Tasks	Video Captioning
Published	2017-08-07
URL	http://arxiv.org/abs/1708.02300v1
PDF	http://arxiv.org/pdf/1708.02300v1.pdf
PWC	https://paperswithcode.com/paper/reinforced-video-captioning-with-entailment
Repo
Framework

On the Relations of Correlation Filter Based Trackers and Struck


Title	On the Relations of Correlation Filter Based Trackers and Struck
Authors	Jinqiao Wang, Ming Tang, Linyu Zheng, Jiayi Feng
Abstract	In recent years, two types of trackers, namely correlation filter based tracker (CF tracker) and structured output tracker (Struck), have exhibited the state-of-the-art performance. However, there seems to be lack of analytic work on their relations in the computer vision community. In this paper, we investigate two state-of-the-art CF trackers, i.e., spatial regularization discriminative correlation filter (SRDCF) and correlation filter with limited boundaries (CFLB), and Struck, and reveal their relations. Specifically, after extending the CFLB to its multiple channel version we prove the relation between SRDCF and CFLB on the condition that the spatial regularization factor of SRDCF is replaced by the masking matrix of CFLB. We also prove the asymptotical approximate relation between SRDCF and Struck on the conditions that the spatial regularization factor of SRDCF is replaced by an indicator function of object bounding box, the weights of SRDCF in its loss item are replaced by those of Struck, the linear kernel is employed by Struck, and the search region tends to infinity. Extensive experiments on public benchmarks OTB50 and OTB100 are conducted to verify our theoretical results. Moreover, we explain how detailed differences among SRDCF, CFLB, and Struck would give rise to slightly different performances on visual sequences
Tasks
Published	2017-11-25
URL	http://arxiv.org/abs/1711.09243v1
PDF	http://arxiv.org/pdf/1711.09243v1.pdf
PWC	https://paperswithcode.com/paper/on-the-relations-of-correlation-filter-based
Repo
Framework

Diving Performance Assessment by means of Video Processing


Title	Diving Performance Assessment by means of Video Processing
Authors	Stefano Frassinelli, Alessandro Niccolai, Riccardo E. Zich
Abstract	The aim of this paper is to present a procedure for video analysis applied in an innovative way to diving performance assessment. Sport performance analysis is a trend that is growing exponentially for all level athletes. The technique here shown is based on two important requirements: flexibility and low cost. These two requirements lead to many problems in the video processing that have been faced and solved in this paper.
Tasks
Published	2017-05-09
URL	http://arxiv.org/abs/1705.03255v1
PDF	http://arxiv.org/pdf/1705.03255v1.pdf
PWC	https://paperswithcode.com/paper/diving-performance-assessment-by-means-of
Repo
Framework

On Using Linear Diophantine Equations to Tune the extent of Look Ahead while Hiding Decision Tree Rules


Title	On Using Linear Diophantine Equations to Tune the extent of Look Ahead while Hiding Decision Tree Rules
Authors	Georgios Feretzakis, Dimitris Kalles, Vassilios S. Verykios
Abstract	This paper focuses on preserving the privacy of sensitive pat-terns when inducing decision trees. We adopt a record aug-mentation approach for hiding sensitive classification rules in binary datasets. Such a hiding methodology is preferred over other heuristic solutions like output perturbation or crypto-graphic techniques - which restrict the usability of the data - since the raw data itself is readily available for public use. In this paper, we propose a look ahead approach using linear Diophantine equations in order to add the appropriate number of instances while minimally disturbing the initial entropy of the nodes.
Tasks
Published	2017-10-18
URL	http://arxiv.org/abs/1710.07214v1
PDF	http://arxiv.org/pdf/1710.07214v1.pdf
PWC	https://paperswithcode.com/paper/on-using-linear-diophantine-equations-to-tune
Repo
Framework

A Gentle Introduction to Epistemic Planning: The DEL Approach


Title	A Gentle Introduction to Epistemic Planning: The DEL Approach
Authors	Thomas Bolander
Abstract	Epistemic planning can be used for decision making in multi-agent situations with distributed knowledge and capabilities. Dynamic Epistemic Logic (DEL) has been shown to provide a very natural and expressive framework for epistemic planning. In this paper, we aim to give an accessible introduction to DEL-based epistemic planning. The paper starts with the most classical framework for planning, STRIPS, and then moves towards epistemic planning in a number of smaller steps, where each step is motivated by the need to be able to model more complex planning scenarios.
Tasks	Decision Making
Published	2017-03-07
URL	http://arxiv.org/abs/1703.02192v1
PDF	http://arxiv.org/pdf/1703.02192v1.pdf
PWC	https://paperswithcode.com/paper/a-gentle-introduction-to-epistemic-planning
Repo
Framework

Calibrated Fairness in Bandits


Title	Calibrated Fairness in Bandits
Authors	Yang Liu, Goran Radanovic, Christos Dimitrakakis, Debmalya Mandal, David C. Parkes
Abstract	We study fairness within the stochastic, \emph{multi-armed bandit} (MAB) decision making framework. We adapt the fairness framework of “treating similar individuals similarly” to this setting. Here, an `individual' corresponds to an arm and two arms are` similar’ if they have a similar quality distribution. First, we adopt a {\em smoothness constraint} that if two arms have a similar quality distribution then the probability of selecting each arm should be similar. In addition, we define the {\em fairness regret}, which corresponds to the degree to which an algorithm is not calibrated, where perfect calibration requires that the probability of selecting an arm is equal to the probability with which the arm has the best quality realization. We show that a variation on Thompson sampling satisfies smooth fairness for total variation distance, and give an $\tilde{O}((kT)^{2/3})$ bound on fairness regret. This complements prior work, which protects an on-average better arm from being less favored. We also explain how to extend our algorithm to the dueling bandit setting.
Tasks	Calibration, Decision Making
Published	2017-07-06
URL	http://arxiv.org/abs/1707.01875v1
PDF	http://arxiv.org/pdf/1707.01875v1.pdf
PWC	https://paperswithcode.com/paper/calibrated-fairness-in-bandits
Repo
Framework

Cross-Sentence N-ary Relation Extraction with Graph LSTMs


Title	Cross-Sentence N-ary Relation Extraction with Graph LSTMs
Authors	Nanyun Peng, Hoifung Poon, Chris Quirk, Kristina Toutanova, Wen-tau Yih
Abstract	Past work in relation extraction has focused on binary relations in single sentences. Recent NLP inroads in high-value domains have sparked interest in the more general setting of extracting n-ary relations that span multiple sentences. In this paper, we explore a general relation extraction framework based on graph long short-term memory networks (graph LSTMs) that can be easily extended to cross-sentence n-ary relation extraction. The graph formulation provides a unified way of exploring different LSTM approaches and incorporating various intra-sentential and inter-sentential dependencies, such as sequential, syntactic, and discourse relations. A robust contextual representation is learned for the entities, which serves as input to the relation classifier. This simplifies handling of relations with arbitrary arity, and enables multi-task learning with related relations. We evaluate this framework in two important precision medicine settings, demonstrating its effectiveness with both conventional supervised learning and distant supervision. Cross-sentence extraction produced larger knowledge bases. and multi-task learning significantly improved extraction accuracy. A thorough analysis of various LSTM approaches yielded useful insight the impact of linguistic analysis on extraction accuracy.
Tasks	Multi-Task Learning, Relation Extraction
Published	2017-08-12
URL	http://arxiv.org/abs/1708.03743v1
PDF	http://arxiv.org/pdf/1708.03743v1.pdf
PWC	https://paperswithcode.com/paper/cross-sentence-n-ary-relation-extraction-with
Repo
Framework

Learn to Model Motion from Blurry Footages


Title	Learn to Model Motion from Blurry Footages
Authors	Wenbin Li, Da Chen, Zhihan Lv, Yan Yan, Darren Cosker
Abstract	It is difficult to recover the motion field from a real-world footage given a mixture of camera shake and other photometric effects. In this paper we propose a hybrid framework by interleaving a Convolutional Neural Network (CNN) and a traditional optical flow energy. We first conduct a CNN architecture using a novel learnable directional filtering layer. Such layer encodes the angle and distance similarity matrix between blur and camera motion, which is able to enhance the blur features of the camera-shake footages. The proposed CNNs are then integrated into an iterative optical flow framework, which enable the capability of modelling and solving both the blind deconvolution and the optical flow estimation problems simultaneously. Our framework is trained end-to-end on a synthetic dataset and yields competitive precision and performance against the state-of-the-art approaches.
Tasks	Optical Flow Estimation
Published	2017-04-19
URL	http://arxiv.org/abs/1704.05817v1
PDF	http://arxiv.org/pdf/1704.05817v1.pdf
PWC	https://paperswithcode.com/paper/learn-to-model-motion-from-blurry-footages
Repo
Framework

Computer Vision for Autonomous Vehicles: Problems, Datasets and State of the Art


Title	Computer Vision for Autonomous Vehicles: Problems, Datasets and State of the Art
Authors	Joel Janai, Fatma Güney, Aseem Behl, Andreas Geiger
Abstract	Recent years have witnessed enormous progress in AI-related fields such as computer vision, machine learning, and autonomous vehicles. As with any rapidly growing field, it becomes increasingly difficult to stay up-to-date or enter the field as a beginner. While several survey papers on particular sub-problems have appeared, no comprehensive survey on problems, datasets, and methods in computer vision for autonomous vehicles has been published. This book attempts to narrow this gap by providing a survey on the state-of-the-art datasets and techniques. Our survey includes both the historically most relevant literature as well as the current state of the art on several specific topics, including recognition, reconstruction, motion estimation, tracking, scene understanding, and end-to-end learning for autonomous driving. Towards this goal, we analyze the performance of the state of the art on several challenging benchmarking datasets, including KITTI, MOT, and Cityscapes. Besides, we discuss open problems and current research challenges. To ease accessibility and accommodate missing references, we also provide a website that allows navigating topics as well as methods and provides additional information.
Tasks	Autonomous Driving, Autonomous Vehicles, Motion Estimation, Scene Understanding
Published	2017-04-18
URL	https://arxiv.org/abs/1704.05519v2
PDF	https://arxiv.org/pdf/1704.05519v2.pdf
PWC	https://paperswithcode.com/paper/computer-vision-for-autonomous-vehicles
Repo
Framework

Parcellation of Visual Cortex on high-resolution histological Brain Sections using Convolutional Neural Networks


Title	Parcellation of Visual Cortex on high-resolution histological Brain Sections using Convolutional Neural Networks
Authors	Hannah Spitzer, Katrin Amunts, Stefan Harmeling, Timo Dickscheid
Abstract	Microscopic analysis of histological sections is considered the “gold standard” to verify structural parcellations in the human brain. Its high resolution allows the study of laminar and columnar patterns of cell distributions, which build an important basis for the simulation of cortical areas and networks. However, such cytoarchitectonic mapping is a semiautomatic, time consuming process that does not scale with high throughput imaging. We present an automatic approach for parcellating histological sections at 2um resolution. It is based on a convolutional neural network that combines topological information from probabilistic atlases with the texture features learned from high-resolution cell-body stained images. The model is applied to visual areas and trained on a sparse set of partial annotations. We show how predictions are transferable to new brains and spatially consistent across sections.
Tasks
Published	2017-05-30
URL	http://arxiv.org/abs/1705.10545v1
PDF	http://arxiv.org/pdf/1705.10545v1.pdf
PWC	https://paperswithcode.com/paper/parcellation-of-visual-cortex-on-high
Repo
Framework

Few-Shot Learning Through an Information Retrieval Lens


Title	Few-Shot Learning Through an Information Retrieval Lens
Authors	Eleni Triantafillou, Richard Zemel, Raquel Urtasun
Abstract	Few-shot learning refers to understanding new concepts from only a few examples. We propose an information retrieval-inspired approach for this problem that is motivated by the increased importance of maximally leveraging all the available information in this low-data regime. We define a training objective that aims to extract as much information as possible from each training batch by effectively optimizing over all relative orderings of the batch points simultaneously. In particular, we view each batch point as a `query’ that ranks the remaining ones based on its predicted relevance to them and we define a model within the framework of structured prediction to optimize mean Average Precision over these rankings. Our method achieves impressive results on the standard few-shot classification benchmarks while is also capable of few-shot retrieval. \|
Tasks	Few-Shot Learning, Information Retrieval, Structured Prediction
Published	2017-07-09
URL	http://arxiv.org/abs/1707.02610v2
PDF	http://arxiv.org/pdf/1707.02610v2.pdf
PWC	https://paperswithcode.com/paper/few-shot-learning-through-an-information
Repo
Framework