January 27, 2020

3276 words 16 mins read

Paper Group ANR 1185

Testing Scenario Library Generation for Connected and Automated Vehicles, Part II: Case Studies. Multiview-Consistent Semi-Supervised Learning for 3D Human Pose Estimation. Real-time Memory Efficient Large-pose Face Alignment via Deep Evolutionary Network. Financial series prediction using Attention LSTM. Robust Data-driven Profile-based Pricing Sc …

Testing Scenario Library Generation for Connected and Automated Vehicles, Part II: Case Studies


Title	Testing Scenario Library Generation for Connected and Automated Vehicles, Part II: Case Studies
Authors	Shuo Feng, Yiheng Feng, Haowei Sun, Shao Bao, Yi Zhang, Henry X. Liu
Abstract	Testing scenario library generation (TSLG) is a critical step for the development and deployment of connected and automated vehicles (CAVs). In Part I of this study, a general methodology for TSLG is proposed, and theoretical properties are investigated regarding the accuracy and efficiency of CAV evaluation. This paper aims to provide implementation examples and guidelines, and to enhance the proposed methodology under high-dimensional scenarios. Three typical cases, including cut-in, highway-exit, and car-following, are designed and studied in this paper. For each case, the process of library generation and CAV evaluation is elaborated. To address the challenges brought by high dimensions, the proposed methodology is further enhanced by reinforcement learning technique. For all three cases, results show that the proposed methods can accelerate the CAV evaluation process by multiple magnitudes with same evaluation accuracy, if compared with the on-road test method.
Tasks
Published	2019-05-09
URL	https://arxiv.org/abs/1905.03428v3
PDF	https://arxiv.org/pdf/1905.03428v3.pdf
PWC	https://paperswithcode.com/paper/190503428
Repo
Framework

Multiview-Consistent Semi-Supervised Learning for 3D Human Pose Estimation


Title	Multiview-Consistent Semi-Supervised Learning for 3D Human Pose Estimation
Authors	Rahul Mitra, Nitesh B. Gundavarapu, Abhishek Sharma, Arjun Jain
Abstract	The best performing methods for 3D human pose estimation from monocular images require large amounts of in-the-wild 2D and controlled 3D pose annotated datasets which are costly and require sophisticated systems to acquire. To reduce this annotation dependency, we propose Multiview-Consistent Semi Supervised Learning (MCSS) framework that utilizes similarity in pose information from unannotated, uncalibrated but synchronized multi-view videos of human motions as additional weak supervision signal to guide 3D human pose regression. Our framework applies hard-negative mining based on temporal relations in multi-view videos to arrive at a multi-view consistent pose embedding. When jointly trained with limited 3D pose annotations, our approach improves the baseline by 25% and state-of-the-art by 8.7%, whilst using substantially smaller networks. Lastly, but importantly, we demonstrate the advantages of the learned embedding and establish view-invariant pose retrieval benchmarks on two popular, publicly available multi-view human pose datasets, Human 3.6M and MPI-INF-3DHP, to facilitate future research.
Tasks	3D Human Pose Estimation, Metric Learning, Pose Estimation
Published	2019-08-14
URL	https://arxiv.org/abs/1908.05293v3
PDF	https://arxiv.org/pdf/1908.05293v3.pdf
PWC	https://paperswithcode.com/paper/3d-human-pose-estimation-under-limited
Repo
Framework

Real-time Memory Efficient Large-pose Face Alignment via Deep Evolutionary Network


Title	Real-time Memory Efficient Large-pose Face Alignment via Deep Evolutionary Network
Authors	Bin Sun, Ming Shao, Siyu Xia, Yun Fu
Abstract	There is an urgent need to apply face alignment in a memory-efficient and real-time manner due to the recent explosion of face recognition applications. However, impact factors such as large pose variation and computational inefficiency, still hinder its broad implementation. To this end, we propose a computationally efficient deep evolutionary model integrated with 3D Diffusion Heap Maps (DHM). First, we introduce a sparse 3D DHM to assist the initial modeling process under extreme pose conditions. Afterward, a simple and effective CNN feature is extracted and fed to Recurrent Neural Network (RNN) for evolutionary learning. To accelerate the model, we propose an efficient network structure to accelerate the evolutionary learning process through a factorization strategy. Extensive experiments on three popular alignment databases demonstrate the advantage of the proposed models over the state-of-the-art, especially under large-pose conditions. Notably, the computational speed of our model is 6 times faster than the state-of-the-art on CPU and 14 times on GPU. We also discuss and analyze the limitations of our models and future research work.
Tasks	Face Alignment, Face Recognition
Published	2019-10-25
URL	https://arxiv.org/abs/1910.11818v2
PDF	https://arxiv.org/pdf/1910.11818v2.pdf
PWC	https://paperswithcode.com/paper/real-time-memory-efficient-large-pose-face
Repo
Framework

Financial series prediction using Attention LSTM


Title	Financial series prediction using Attention LSTM
Authors	Sangyeon Kim, Myungjoo Kang
Abstract	Financial time series prediction, especially with machine learning techniques, is an extensive field of study. In recent times, deep learning methods (especially time series analysis) have performed outstandingly for various industrial problems, with better prediction than machine learning methods. Moreover, many researchers have used deep learning methods to predict financial time series with various models in recent years. In this paper, we will compare various deep learning models, such as multilayer perceptron (MLP), one-dimensional convolutional neural networks (1D CNN), stacked long short-term memory (stacked LSTM), attention networks, and weighted attention networks for financial time series prediction. In particular, attention LSTM is not only used for prediction, but also for visualizing intermediate outputs to analyze the reason of prediction; therefore, we will show an example for understanding the model prediction intuitively with attention vectors. In addition, we focus on time and factors, which lead to an easy understanding of why certain trends are predicted when accessing a given time series table. We also modify the loss functions of the attention models with weighted categorical cross entropy; our proposed model produces a 0.76 hit ratio, which is superior to those of other methods for predicting the trends of the KOSPI 200.
Tasks	Time Series, Time Series Analysis, Time Series Prediction
Published	2019-02-28
URL	http://arxiv.org/abs/1902.10877v1
PDF	http://arxiv.org/pdf/1902.10877v1.pdf
PWC	https://paperswithcode.com/paper/financial-series-prediction-using-attention
Repo
Framework

Robust Data-driven Profile-based Pricing Schemes


Title	Robust Data-driven Profile-based Pricing Schemes
Authors	Jingshi Cui, Haoxiang Wang, Chenye Wu, Yang Yu
Abstract	To enable an efficient electricity market, a good pricing scheme is of vital importance. Among many practical schemes, customized pricing is commonly believed to be able to best exploit the flexibility in the demand side. However, due to the large volume of consumers in the electricity sector, such task is simply too overwhelming. In this paper, we first compare two data driven schemes: one based on load profile and the other based on user’s marginal system cost. Vulnerability analysis shows that the former approach may lead to loopholes in the electricity market while the latter one is able to guarantee the robustness, which yields our robust data-driven pricing scheme. Although k-means clustering is in general NP-hard, surprisingly, by exploiting the structure of our problem, we design an efficient yet optimal k-means clustering algorithm to implement our proposed scheme.
Tasks
Published	2019-12-12
URL	https://arxiv.org/abs/1912.05731v1
PDF	https://arxiv.org/pdf/1912.05731v1.pdf
PWC	https://paperswithcode.com/paper/robust-data-driven-profile-based-pricing
Repo
Framework

Short-term Road Traffic Prediction based on Deep Cluster at Large-scale Networks


Title	Short-term Road Traffic Prediction based on Deep Cluster at Large-scale Networks
Authors	Lingyi Han, Kan Zheng, Long Zhao, Xianbin Wang, Xuemin Shen
Abstract	Short-term road traffic prediction (STTP) is one of the most important modules in Intelligent Transportation Systems (ITS). However, network-level STTP still remains challenging due to the difficulties both in modeling the diverse traffic patterns and tacking high-dimensional time series with low latency. Therefore, a framework combining with a deep clustering (DeepCluster) module is developed for STTP at largescale networks in this paper. The DeepCluster module is proposed to supervise the representation learning in a visualized way from the large unlabeled dataset. More specifically, to fully exploit the traffic periodicity, the raw series is first split into a number of sub-series for triplets generation. The convolutional neural networks (CNNs) with triplet loss are utilized to extract the features of shape by transferring the series into visual images. The shape-based representations are then used for road segments clustering. Thereafter, motivated by the fact that the road segments in a group have similar patterns, a model sharing strategy is further proposed to build recurrent NNs (RNNs)-based predictions through a group-based model (GM), instead of individual-based model (IM) in which one model are built for one road exclusively. Our framework can not only significantly reduce the number of models and cost, but also increase the number of training data and the diversity of samples. In the end, we evaluate the proposed framework over the network of Liuli Bridge in Beijing. Experimental results show that the DeepCluster can effectively cluster the road segments and GM can achieve comparable performance against the IM with less number of models.
Tasks	Representation Learning, Time Series, Traffic Prediction
Published	2019-02-25
URL	http://arxiv.org/abs/1902.09601v1
PDF	http://arxiv.org/pdf/1902.09601v1.pdf
PWC	https://paperswithcode.com/paper/short-term-road-traffic-prediction-based-on
Repo
Framework

Leverage Implicit Feedback for Context-aware Product Search


Title	Leverage Implicit Feedback for Context-aware Product Search
Authors	Keping Bi, Choon Hui Teo, Yesh Dattatreya, Vijai Mohan, W. Bruce Croft
Abstract	Product search serves as an important entry point for online shopping. In contrast to web search, the retrieved results in product search not only need to be relevant but also should satisfy customers’ preferences in order to elicit purchases. Previous work has shown the efficacy of purchase history in personalized product search. However, customers with little or no purchase history do not benefit from personalized product search. Furthermore, preferences extracted from a customer’s purchase history are usually long-term and may not always align with her short-term interests. Hence, in this paper, we leverage clicks within a query session, as implicit feedback, to represent users’ hidden intents, which further act as the basis for re-ranking subsequent result pages for the query. It has been studied extensively to model user preference with implicit feedback in recommendation tasks. However, there has been little research on modeling users’ short-term interest in product search. We study whether short-term context could help promote users’ ideal item in the following result pages for a query. Furthermore, we propose an end-to-end context-aware embedding model which can capture long-term and short-term context dependencies. Our experimental results on the datasets collected from the search log of a commercial product search engine show that short-term context leads to much better performance compared with long-term and no context. Our results also show that our proposed model is more effective than word-based context-aware models.
Tasks
Published	2019-09-04
URL	https://arxiv.org/abs/1909.02065v2
PDF	https://arxiv.org/pdf/1909.02065v2.pdf
PWC	https://paperswithcode.com/paper/leverage-implicit-feedback-for-context-aware
Repo
Framework

Wireless Traffic Prediction with Scalable Gaussian Process: Framework, Algorithms, and Verification


Title	Wireless Traffic Prediction with Scalable Gaussian Process: Framework, Algorithms, and Verification
Authors	Yue Xu, Feng Yin, Wenjun Xu, Jiaru Lin, Shuguang Cui
Abstract	The cloud radio access network (C-RAN) is a promising paradigm to meet the stringent requirements of the fifth generation (5G) wireless systems. Meanwhile, wireless traffic prediction is a key enabler for C-RANs to improve both the spectrum efficiency and energy efficiency through load-aware network managements. This paper proposes a scalable Gaussian process (GP) framework as a promising solution to achieve large-scale wireless traffic prediction in a cost-efficient manner. Our contribution is three-fold. First, to the best of our knowledge, this paper is the first to empower GP regression with the alternating direction method of multipliers (ADMM) for parallel hyper-parameter optimization in the training phase, where such a scalable training framework well balances the local estimation in baseband units (BBUs) and information consensus among BBUs in a principled way for large-scale executions. Second, in the prediction phase, we fuse local predictions obtained from the BBUs via a cross-validation based optimal strategy, which demonstrates itself to be reliable and robust for general regression tasks. Moreover, such a cross-validation based optimal fusion strategy is built upon a well acknowledged probabilistic model to retain the valuable closed-form GP inference properties. Third, we propose a C-RAN based scalable wireless prediction architecture, where the prediction accuracy and the time consumption can be balanced by tuning the number of the BBUs according to the real-time system demands. Experimental results show that our proposed scalable GP model can outperform the state-of-the-art approaches considerably, in terms of wireless traffic prediction performance.
Tasks	Traffic Prediction
Published	2019-02-13
URL	http://arxiv.org/abs/1902.04763v1
PDF	http://arxiv.org/pdf/1902.04763v1.pdf
PWC	https://paperswithcode.com/paper/wireless-traffic-prediction-with-scalable
Repo
Framework

Robust Change Captioning


Title	Robust Change Captioning
Authors	Dong Huk Park, Trevor Darrell, Anna Rohrbach
Abstract	Describing what has changed in a scene can be useful to a user, but only if generated text focuses on what is semantically relevant. It is thus important to distinguish distractors (e.g. a viewpoint change) from relevant changes (e.g. an object has moved). We present a novel Dual Dynamic Attention Model (DUDA) to perform robust Change Captioning. Our model learns to distinguish distractors from semantic changes, localize the changes via Dual Attention over “before” and “after” images, and accurately describe them in natural language via Dynamic Speaker, by adaptively focusing on the necessary visual inputs (e.g. “before” or “after” image). To study the problem in depth, we collect a CLEVR-Change dataset, built off the CLEVR engine, with 5 types of scene changes. We benchmark a number of baselines on our dataset, and systematically study different change types and robustness to distractors. We show the superiority of our DUDA model in terms of both change captioning and localization. We also show that our approach is general, obtaining state-of-the-art results on the recent realistic Spot-the-Diff dataset which has no distractors.
Tasks	Natural Language Visual Grounding
Published	2019-01-08
URL	http://arxiv.org/abs/1901.02527v2
PDF	http://arxiv.org/pdf/1901.02527v2.pdf
PWC	https://paperswithcode.com/paper/viewpoint-invariant-change-captioning
Repo
Framework

Knowledge Guided Named Entity Recognition


Title	Knowledge Guided Named Entity Recognition
Authors	Pratyay Banerjee, Kuntal Kumar Pal, Murthy Devarakonda, Chitta Baral
Abstract	In this work, we try to perform Named Entity Recognition (NER) with external knowledge. We formulate the NER task as a multi-answer question answering (MAQA) task and provide different knowledge contexts, such as entity types, questions, definitions, and definitions with examples. Moreover, the formulation of the task as a MAQA task helps to reduce other errors. This formulation (a) enables systems to jointly learn from varied NER datasets, enabling systems to learn more NER specific features, (b) can use knowledge-text attention to identify words having higher similarity to ‘entity type’ mentioned in the knowledge, improving performance, (c) reduces confusion in systems by reducing the classes to be predicted, limited to only three (B, I, O), (d) Makes detection of Nested Entities easier. We perform extensive experiments of this Knowledge Guided NER (KGNER) formulation on 15 Biomedical NER datasets, and through these experiments, we see external knowledge helps. We will release the code for dataset conversion and our trained models for replicating experiments.
Tasks	Named Entity Recognition, Question Answering
Published	2019-11-10
URL	https://arxiv.org/abs/1911.03869v1
PDF	https://arxiv.org/pdf/1911.03869v1.pdf
PWC	https://paperswithcode.com/paper/knowledge-guided-named-entity-recognition
Repo
Framework

Visual Physics: Discovering Physical Laws from Videos


Title	Visual Physics: Discovering Physical Laws from Videos
Authors	Pradyumna Chari, Chinmay Talegaonkar, Yunhao Ba, Achuta Kadambi
Abstract	In this paper, we teach a machine to discover the laws of physics from video streams. We assume no prior knowledge of physics, beyond a temporal stream of bounding boxes. The problem is very difficult because a machine must learn not only a governing equation (e.g. projectile motion) but also the existence of governing parameters (e.g. velocities). We evaluate our ability to discover physical laws on videos of elementary physical phenomena, such as projectile motion or circular motion. These elementary tasks have textbook governing equations and enable ground truth verification of our approach.
Tasks
Published	2019-11-27
URL	https://arxiv.org/abs/1911.11893v1
PDF	https://arxiv.org/pdf/1911.11893v1.pdf
PWC	https://paperswithcode.com/paper/visual-physics-discovering-physical-laws-from
Repo
Framework

Error Analysis for Vietnamese Named Entity Recognition on Deep Neural Network Models


Title	Error Analysis for Vietnamese Named Entity Recognition on Deep Neural Network Models
Authors	Binh An Nguyen, Kiet Van Nguyen, Ngan Luu-Thuy Nguyen
Abstract	In recent years, Vietnamese Named Entity Recognition (NER) systems have had a great breakthrough when using Deep Neural Network methods. This paper describes the primary errors of the state-of-the-art NER systems on Vietnamese language. After conducting experiments on BLSTM-CNN-CRF and BLSTM-CRF models with different word embeddings on the Vietnamese NER dataset. This dataset is provided by VLSP in 2016 and used to evaluate most of the current Vietnamese NER systems. We noticed that BLSTM-CNN-CRF gives better results, therefore, we analyze the errors on this model in detail. Our error-analysis results provide us thorough insights in order to increase the performance of NER for the Vietnamese language and improve the quality of the corpus in the future works.
Tasks	Named Entity Recognition, Word Embeddings
Published	2019-11-17
URL	https://arxiv.org/abs/1911.07228v2
PDF	https://arxiv.org/pdf/1911.07228v2.pdf
PWC	https://paperswithcode.com/paper/error-analysis-for-vietnamese-named-entity
Repo
Framework

Latent Distribution Assumption for Unbiased and Consistent Consensus Modelling


Title	Latent Distribution Assumption for Unbiased and Consistent Consensus Modelling
Authors	Valentina Fedorova, Gleb Gusev, Pavel Serdyukov
Abstract	We study the problem of aggregation noisy labels. Usually, it is solved by proposing a stochastic model for the process of generating noisy labels and then estimating the model parameters using the observed noisy labels. A traditional assumption underlying previously introduced generative models is that each object has one latent true label. In contrast, we introduce a novel latent distribution assumption, implying that a unique true label for an object might not exist, but rather each object might have a specific distribution generating a latent subjective label each time the object is observed. Our experiments showed that the novel assumption is more suitable for difficult tasks, when there is an ambiguity in choosing a “true” label for certain objects.
Tasks
Published	2019-06-20
URL	https://arxiv.org/abs/1906.08776v1
PDF	https://arxiv.org/pdf/1906.08776v1.pdf
PWC	https://paperswithcode.com/paper/latent-distribution-assumption-for-unbiased
Repo
Framework

Evaluating Recommender System Algorithms for Generating Local Music Playlists


Title	Evaluating Recommender System Algorithms for Generating Local Music Playlists
Authors	Daniel Akimchuk, Timothy Clerico, Douglas Turnbull
Abstract	We explore the task of local music recommendation: provide listeners with personalized playlists of relevant tracks by artists who play most of their live events within a small geographic area. Most local artists tend to be obscure, long-tail artists and generally have little or no available user preference data associated with them. This creates a cold-start problem for collaborative filtering-based recommendation algorithms that depend on large amounts of such information to make accurate recommendations. In this paper, we compare the performance of three standard recommender system algorithms (Item-Item Neighborhood (IIN), Alternating Least Squares for Implicit Feedback (ALS), and Bayesian Personalized Ranking (BPR)) on the task of local music recommendation using the Million Playlist Dataset. To do this, we modify the standard evaluation procedure such that the algorithms only rank tracks by local artists for each of the eight different cities. Despite the fact that techniques based on matrix factorization (ALS, BPR) typically perform best on large recommendation tasks, we find that the neighborhood-based approach (IIN) performs best for long-tail local music recommendation.
Tasks	Recommendation Systems
Published	2019-07-17
URL	https://arxiv.org/abs/1907.08687v1
PDF	https://arxiv.org/pdf/1907.08687v1.pdf
PWC	https://paperswithcode.com/paper/evaluating-recommender-system-algorithms-for
Repo
Framework

Dynamic Anonymized Evaluation for Behavioral Continuous Authentication


Title	Dynamic Anonymized Evaluation for Behavioral Continuous Authentication
Authors	Rasana Manandhar, Shaya Wolf, Mike Borowczak
Abstract	Emerging technology demands reliable authentication mechanisms, particularly in interconnected systems. Current systems rely on a single moment of authentication, however continuous authentication systems assess a users identity utilizing a constant biometric analysis. Spy Hunter, a continuous authentication mechanism uses keystroke dynamics to validate users over blocks of data. This easily-incorporated periodic biometric authentication system validates genuine users and detects intruders quickly. Because it verifies users in the background, Spy Hunter is not constrained to a password box. Instead, it is flexible and can be layered with other mechanisms to provide high-level security. Where other continuous authentication techniques rely on scripted typing, Spy Hunter validates over free text in authentic environments. This is accomplished in two phases, one where the user is provided a prompt and another where the user is allowed free access to their computer. Additionally, Spy Hunter focuses on the timing of different keystrokes rather than the specific key being pressed. This allows for anonymous data to authenticate users and avoids holding personal data. Utilizing a couple K-fold cross-validation techniques, Spy Hunter is assessed based on how often the system falsely accepts an intruder, how often the system falsely rejects a genuine user, and the time it takes to validate a users identity. Spy Hunter maintains error rates below 6% and identifies users in minimal numbers of keystrokes. Continuous authentication provides higher level security than one-time verification processes and Spy Hunter expands on the possibilities for behavioral analysis based on keystroke dynamics.
Tasks
Published	2019-03-07
URL	http://arxiv.org/abs/1903.03132v1
PDF	http://arxiv.org/pdf/1903.03132v1.pdf
PWC	https://paperswithcode.com/paper/dynamic-anonymized-evaluation-for-behavioral
Repo
Framework