Paper Group ANR 1019
The Computational Complexity of Fire Emblem Series and similar Tactical Role-Playing Games. 6D Object Pose Estimation without PnP. Weighed Domain-Invariant Representation Learning for Cross-domain Sentiment Analysis. Penalized regression via the restricted bridge estimator. Some machine learning schemes for high-dimensional nonlinear PDEs. Predicti …
The Computational Complexity of Fire Emblem Series and similar Tactical Role-Playing Games
| Title | The Computational Complexity of Fire Emblem Series and similar Tactical Role-Playing Games |
| Authors | Jiawei Gao |
| Abstract | Fire Emblem (FE) is a popular turn-based tactical role-playing game (TRPG) series on the Nintendo gaming consoles. This paper studies the computational complexity of a simplified version of FE (only floor tiles and wall tiles, the HP and other attributes of characters are constants at most 8, the movement distance per character each turn is fixed to 6 tiles), and proves that: 1. Simplified FE is PSPACE-complete (Thus actual FE is at least as hard). 2. Poly-round FE is NP-complete, even when the map is cycle-free, without healing units, and the weapon durability is a small constant. Poly-round FE is to decide whether the player can win the game in a certain number of rounds that is polynomial to the map size. A map is called cycle-free if its corresponding planar graph is cycle-free. These hardness results also hold for other similar TRPG series, such as Final Fantasy Tactics, Tactics Ogre and Disgaea. |
| Tasks | |
| Published | 2019-09-16 |
| URL | https://arxiv.org/abs/1909.07816v2 |
| https://arxiv.org/pdf/1909.07816v2.pdf | |
| PWC | https://paperswithcode.com/paper/the-computational-complexity-of-fire-emblem |
| Repo | |
| Framework | |
6D Object Pose Estimation without PnP
| Title | 6D Object Pose Estimation without PnP |
| Authors | Jin Liu, Sheng He |
| Abstract | In this paper, we propose an efficient end-to-end algorithm to tackle the problem of estimating the 6D pose of objects from a single RGB image. Our system trains a fully convolutional network to regress the 3D rotation and the 3D translation in region layer. On this basis, a special layer, Collinear Equation Layer, is added next to region layer to output the 2D projections of the 3D bounding boxs corners. In the back propagation stage, the 6D pose network are adjusted according to the error of the 2D projections. In the detection phase, we directly output the position and pose through the region layer. Besides, we introduce a novel and concise representation of 3D rotation to make the regression more precise and easier. Experiments show that our method outperforms base-line and state of the art methods both at accuracy and efficiency. In the LineMod dataset, our algorithm achieves less than 18 ms/object on a GeForce GTX 1080Ti GPU, while the translational error and rotational error are less than 1.67 cm and 2.5 degree. |
| Tasks | 6D Pose Estimation using RGB, Pose Estimation |
| Published | 2019-02-05 |
| URL | http://arxiv.org/abs/1902.01728v2 |
| http://arxiv.org/pdf/1902.01728v2.pdf | |
| PWC | https://paperswithcode.com/paper/6d-object-pose-estimation-without-pnp |
| Repo | |
| Framework | |
Weighed Domain-Invariant Representation Learning for Cross-domain Sentiment Analysis
| Title | Weighed Domain-Invariant Representation Learning for Cross-domain Sentiment Analysis |
| Authors | Minlong Peng, Qi Zhang, Xuanjing Huang |
| Abstract | Cross-domain sentiment analysis is currently a hot topic in the research and engineering areas. One of the most popular frameworks in this field is the domain-invariant representation learning (DIRL) paradigm, which aims to learn a distribution-invariant feature representation across domains. However, in this work, we find out that applying DIRL may harm domain adaptation when the label distribution $\rm{P}(\rm{Y})$ changes across domains. To address this problem, we propose a modification to DIRL, obtaining a novel weighted domain-invariant representation learning (WDIRL) framework. We show that it is easy to transfer existing SOTA DIRL models to WDIRL. Empirical studies on extensive cross-domain sentiment analysis tasks verified our statements and showed the effectiveness of our proposed solution. |
| Tasks | Domain Adaptation, Representation Learning, Sentiment Analysis |
| Published | 2019-09-18 |
| URL | https://arxiv.org/abs/1909.08167v1 |
| https://arxiv.org/pdf/1909.08167v1.pdf | |
| PWC | https://paperswithcode.com/paper/weighed-domain-invariant-representation |
| Repo | |
| Framework | |
Penalized regression via the restricted bridge estimator
| Title | Penalized regression via the restricted bridge estimator |
| Authors | Bahadır Yüzbaşı, Mohammad Arashi, Fikri Akdeniz |
| Abstract | This article is concerned with the Bridge Regression, which is a special family in penalized regression with penalty function $\sum_{j=1}^{p}\beta_j^q$ with $q>0$, in a linear model with linear restrictions. The proposed restricted bridge (RBRIDGE) estimator simultaneously estimates parameters and selects important variables when a prior information about parameters are available in either low dimensional or high dimensional case. Using local quadratic approximation, the penalty term can be approximated around a local initial values vector and the RBRIDGE estimator enjoys a closed-form expression which can be solved when $q>0$. Special cases of our proposal are the restricted LASSO ($q=1$), restricted RIDGE ($q=2$), and restricted Elastic Net ($1< q < 2$) estimators. We provide some theoretical properties of the RBRIDGE estimator under for the low dimensional case, whereas the computational aspects are given for both low and high dimensional cases. An extensive Monte Carlo simulation study is conducted based on different prior pieces of information and the performance of the RBRIDGE estiamtor is compared with some competitive penalty estimators as well as the ORACLE. We also consider four real data examples analysis for comparison sake. The numerical results show that the suggested RBRIDGE estimator outperforms outstandingly when the prior is true or near exact |
| Tasks | |
| Published | 2019-10-08 |
| URL | https://arxiv.org/abs/1910.03660v1 |
| https://arxiv.org/pdf/1910.03660v1.pdf | |
| PWC | https://paperswithcode.com/paper/penalized-regression-via-the-restricted |
| Repo | |
| Framework | |
Some machine learning schemes for high-dimensional nonlinear PDEs
| Title | Some machine learning schemes for high-dimensional nonlinear PDEs |
| Authors | Côme Huré, Huyên Pham, Xavier Warin |
| Abstract | We propose new machine learning schemes for solving high dimensional nonlinear partial differential equations (PDEs). Relying on the classical backward stochastic differential equation (BSDE) representation of PDEs, our algorithms estimate simultaneously the solution and its gradient by deep neural networks. These approximations are performed at each time step from the minimization of loss functions defined recursively by backward induction. The methodology is extended to variational inequalities arising in optimal stopping problems. We analyze the convergence of the deep learning schemes and provide error estimates in terms of the universal approximation of neural networks. Numerical results show that our algorithms give very good results till dimension 50 (and certainly above), for both PDEs and variational inequalities problems. For the PDEs resolution, our results are very similar to those obtained by the recent method in \cite{weinan2017deep} when the latter converges to the right solution or does not diverge. Numerical tests indicate that the proposed methods are not stuck in poor local minimaas it can be the case with the algorithm designed in \cite{weinan2017deep}, and no divergence is experienced. The only limitation seems to be due to the inability of the considered deep neural networks to represent a solution with a too complex structure in high dimension. |
| Tasks | |
| Published | 2019-02-05 |
| URL | http://arxiv.org/abs/1902.01599v1 |
| http://arxiv.org/pdf/1902.01599v1.pdf | |
| PWC | https://paperswithcode.com/paper/some-machine-learning-schemes-for-high |
| Repo | |
| Framework | |
Predictive Maintenance in Photovoltaic Plants with a Big Data Approach
| Title | Predictive Maintenance in Photovoltaic Plants with a Big Data Approach |
| Authors | Alessandro Betti, Maria Luisa Lo Trovato, Fabio Salvatore Leonardi, Giuseppe Leotta, Fabrizio Ruffini, Ciro Lanzetta |
| Abstract | This paper presents a novel and flexible solution for fault prediction based on data collected from SCADA system. Fault prediction is offered at two different levels based on a data-driven approach: (a) generic fault/status prediction and (b) specific fault class prediction, implemented by means of two different machine learning based modules built on an unsupervised clustering algorithm and a Pattern Recognition Neural Network, respectively. Model has been assessed on a park of six photovoltaic (PV) plants up to 10 MW and on more than one hundred inverter modules of three different technology brands. The results indicate that the proposed method is effective in (a) predicting incipient generic faults up to 7 days in advance with sensitivity up to 95% and (b) anticipating damage of specific fault classes with times ranging from few hours up to 7 days. The model is easily deployable for on-line monitoring of anomalies on new PV plants and technologies, requiring only the availability of historical SCADA and fault data, fault taxonomy and inverter electrical datasheet. Keywords: Data Mining, Fault Prediction, Inverter Module, Key Performance Indicator, Lost Production |
| Tasks | |
| Published | 2019-01-29 |
| URL | http://arxiv.org/abs/1901.10855v1 |
| http://arxiv.org/pdf/1901.10855v1.pdf | |
| PWC | https://paperswithcode.com/paper/predictive-maintenance-in-photovoltaic-plants |
| Repo | |
| Framework | |
REQ-YOLO: A Resource-Aware, Efficient Quantization Framework for Object Detection on FPGAs
| Title | REQ-YOLO: A Resource-Aware, Efficient Quantization Framework for Object Detection on FPGAs |
| Authors | Caiwen Ding, Shuo Wang, Ning Liu, Kaidi Xu, Yanzhi Wang, Yun Liang |
| Abstract | Deep neural networks (DNNs), as the basis of object detection, will play a key role in the development of future autonomous systems with full autonomy. The autonomous systems have special requirements of real-time, energy-efficient implementations of DNNs on a power-constrained system. Two research thrusts are dedicated to performance and energy efficiency enhancement of the inference phase of DNNs. The first one is model compression techniques while the second is efficient hardware implementation. Recent works on extremely-low-bit CNNs such as the binary neural network (BNN) and XNOR-Net replace the traditional floating-point operations with binary bit operations which significantly reduces the memory bandwidth and storage requirement. However, it suffers from non-negligible accuracy loss and underutilized digital signal processing (DSP) blocks of FPGAs. To overcome these limitations, this paper proposes REQ-YOLO, a resource-aware, systematic weight quantization framework for object detection, considering both algorithm and hardware resource aspects in object detection. We adopt the block-circulant matrix method and propose a heterogeneous weight quantization using the Alternating Direction Method of Multipliers (ADMM), an effective optimization technique for general, non-convex optimization problems. To achieve real-time, highly-efficient implementations on FPGA, we present the detailed hardware implementation of block circulant matrices on CONV layers and develop an efficient processing element (PE) structure supporting the heterogeneous weight quantization, CONV dataflow and pipelining techniques, design optimization, and a template-based automatic synthesis framework to optimally exploit hardware resource. Experimental results show that our proposed REQ-YOLO framework can significantly compress the YOLO model while introducing very small accuracy degradation. |
| Tasks | Model Compression, Object Detection, Quantization |
| Published | 2019-09-29 |
| URL | https://arxiv.org/abs/1909.13396v1 |
| https://arxiv.org/pdf/1909.13396v1.pdf | |
| PWC | https://paperswithcode.com/paper/req-yolo-a-resource-aware-efficient |
| Repo | |
| Framework | |
Deep Reinforcement-Learning-based Driving Policy for Autonomous Road Vehicles
| Title | Deep Reinforcement-Learning-based Driving Policy for Autonomous Road Vehicles |
| Authors | Konstantinos Makantasis, Maria Kontorinaki, Ioannis Nikolos |
| Abstract | In this work the problem of path planning for an autonomous vehicle that moves on a freeway is considered. The most common approaches that are used to address this problem are based on optimal control methods, which make assumptions about the model of the environment and the system dynamics. On the contrary, this work proposes the development of a driving policy based on reinforcement learning. In this way, the proposed driving policy makes minimal or no assumptions about the environment, since a priori knowledge about the system dynamics is not required. Driving scenarios where the road is occupied both by autonomous and manual driving vehicles are considered. To the best of our knowledge, this is one of the first approaches that propose a reinforcement learning driving policy for mixed driving environments. The derived reinforcement learning policy, firstly, is compared against an optimal policy derived via dynamic programming, and, secondly, its efficiency is evaluated under realistic scenarios generated by the established SUMO microscopic traffic flow simulator. Finally, some initial results regarding the effect of autonomous vehicles’ behavior on the overall traffic flow are presented. |
| Tasks | Autonomous Vehicles |
| Published | 2019-07-10 |
| URL | https://arxiv.org/abs/1907.05246v2 |
| https://arxiv.org/pdf/1907.05246v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-deep-reinforcement-learning-based-driving |
| Repo | |
| Framework | |
Towards Multimodal Understanding of Passenger-Vehicle Interactions in Autonomous Vehicles: Intent/Slot Recognition Utilizing Audio-Visual Data
| Title | Towards Multimodal Understanding of Passenger-Vehicle Interactions in Autonomous Vehicles: Intent/Slot Recognition Utilizing Audio-Visual Data |
| Authors | Eda Okur, Shachi H Kumar, Saurav Sahay, Lama Nachman |
| Abstract | Understanding passenger intents from spoken interactions and car’s vision (both inside and outside the vehicle) are important building blocks towards developing contextual dialog systems for natural interactions in autonomous vehicles (AV). In this study, we continued exploring AMIE (Automated-vehicle Multimodal In-cabin Experience), the in-cabin agent responsible for handling certain multimodal passenger-vehicle interactions. When the passengers give instructions to AMIE, the agent should parse such commands properly considering available three modalities (language/text, audio, video) and trigger the appropriate functionality of the AV system. We had collected a multimodal in-cabin dataset with multi-turn dialogues between the passengers and AMIE using a Wizard-of-Oz scheme via realistic scavenger hunt game. In our previous explorations, we experimented with various RNN-based models to detect utterance-level intents (set destination, change route, go faster, go slower, stop, park, pull over, drop off, open door, and others) along with intent keywords and relevant slots (location, position/direction, object, gesture/gaze, time-guidance, person) associated with the action to be performed in our AV scenarios. In this recent work, we propose to discuss the benefits of multimodal understanding of in-cabin utterances by incorporating verbal/language input (text and speech embeddings) together with the non-verbal/acoustic and visual input from inside and outside the vehicle (i.e., passenger gestures and gaze from in-cabin video stream, referred objects outside of the vehicle from the road view camera stream). Our experimental results outperformed text-only baselines and with multimodality, we achieved improved performances for utterance-level intent detection and slot filling. |
| Tasks | Autonomous Vehicles, Intent Detection, Slot Filling |
| Published | 2019-09-20 |
| URL | https://arxiv.org/abs/1909.13714v1 |
| https://arxiv.org/pdf/1909.13714v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-multimodal-understanding-of-passenger |
| Repo | |
| Framework | |
DynaNet: Neural Kalman Dynamical Model for Motion Estimation and Prediction
| Title | DynaNet: Neural Kalman Dynamical Model for Motion Estimation and Prediction |
| Authors | Changhao Chen, Chris Xiaoxuan Lu, Bing Wang, Niki Trigoni, Andrew Markham |
| Abstract | Dynamical models estimate and predict the temporal evolution of physical systems. State Space Models (SSMs) in particular represent the system dynamics with many desirable properties, such as being able to model uncertainty in both the model and measurements, and optimal (in the Bayesian sense) recursive formulations e.g. the Kalman Filter. However, they require significant domain knowledge to derive the parametric form and considerable hand-tuning to correctly set all the parameters. Data driven techniques e.g. Recurrent Neural Networks have emerged as compelling alternatives to SSMs with wide success across a number of challenging tasks, in part due to their ability to extract relevant features from rich inputs. They however lack interpretability and robustness to unseen conditions. In this work, we present DynaNet, a hybrid deep learning and time-varying state-space model which can be trained end-to-end. Our neural Kalman dynamical model allows us to exploit the relative merits of each approach. We demonstrate state-of-the-art estimation and prediction on a number of physically challenging tasks, including visual odometry, sensor fusion for visual-inertial navigation and pendulum control. In addition we show how DynaNet can indicate failures through investigation of properties such as the rate of innovation (Kalman Gain). |
| Tasks | Motion Estimation, Sensor Fusion, Visual Odometry |
| Published | 2019-08-11 |
| URL | https://arxiv.org/abs/1908.03918v1 |
| https://arxiv.org/pdf/1908.03918v1.pdf | |
| PWC | https://paperswithcode.com/paper/dynanet-neural-kalman-dynamical-model-for |
| Repo | |
| Framework | |
Local Supports Global: Deep Camera Relocalization with Sequence Enhancement
| Title | Local Supports Global: Deep Camera Relocalization with Sequence Enhancement |
| Authors | Fei Xue, Xin Wang, Zike Yan, Qiuyuan Wang, Junqiu Wang, Hongbin Zha |
| Abstract | We propose to leverage the local information in image sequences to support global camera relocalization. In contrast to previous methods that regress global poses from single images, we exploit the spatial-temporal consistency in sequential images to alleviate uncertainty due to visual ambiguities by incorporating a visual odometry (VO) component. Specifically, we introduce two effective steps called content-augmented pose estimation and motion-based refinement. The content-augmentation step focuses on alleviating the uncertainty of pose estimation by augmenting the observation based on the co-visibility in local maps built by the VO stream. Besides, the motion-based refinement is formulated as a pose graph, where the camera poses are further optimized by adopting relative poses provided by the VO component as additional motion constraints. Thus, the global consistency can be guaranteed. Experiments on the public indoor 7-Scenes and outdoor Oxford RobotCar benchmark datasets demonstrate that benefited from local information inherent in the sequence, our approach outperforms state-of-the-art methods, especially in some challenging cases, e.g., insufficient texture, highly repetitive textures, similar appearances, and over-exposure. |
| Tasks | Camera Relocalization, Pose Estimation, Visual Odometry |
| Published | 2019-08-06 |
| URL | https://arxiv.org/abs/1908.04391v1 |
| https://arxiv.org/pdf/1908.04391v1.pdf | |
| PWC | https://paperswithcode.com/paper/local-supports-global-deep-camera |
| Repo | |
| Framework | |
Sensor-Based Estimation of Dim Light Melatonin Onset (DLMO) Using Features of Two Time Scales
| Title | Sensor-Based Estimation of Dim Light Melatonin Onset (DLMO) Using Features of Two Time Scales |
| Authors | Cheng Wan, Andrew W. McHill, Elizabeth Klerman, Akane Sano |
| Abstract | Circadian rhythms influence multiple essential biological activities including sleep, performance, and mood. The dim light melatonin onset (DLMO) is the gold standard for measuring human circadian phase. The collection of DLMO is expensive and time-consuming since multiple saliva or blood samples are required overnight in special conditions, and the samples must then be assayed for melatonin. Recently, several non-invasive approaches have been designed for estimating DLMO. These methods collect daily sampled data (e.g., sleep onset/offset times) or frequently sampled data (e.g., light exposure/skin temperature/physical activity collected every minute) to train learning models for estimating DLMO. One limitation of these studies was that they only leveraged one time-scale data. We propose a two-step framework for estimating DLMO using data from both time scales. The first step summarizes data from before the current day, while the second step combines this summary with frequently sampled data of the current day. We evaluate three moving average models that input sleep timing data as the first step and use recurrent neural network models as the second step. The results using data from 207 undergraduates show that our two-step model with two time-scale features has statistically significantly lower root-mean-square errors than models that use either daily sampled data or frequently sampled data. |
| Tasks | |
| Published | 2019-08-20 |
| URL | https://arxiv.org/abs/1908.07483v2 |
| https://arxiv.org/pdf/1908.07483v2.pdf | |
| PWC | https://paperswithcode.com/paper/sensor-based-estimation-of-dim-light |
| Repo | |
| Framework | |
Empirical Study on Detecting Controversy in Social Media
| Title | Empirical Study on Detecting Controversy in Social Media |
| Authors | Azadeh Nematzadeh, Grace Bang, Xiaomo Liu, Zhiqiang Ma |
| Abstract | Companies and financial investors are paying increasing attention to social consciousness in developing their corporate strategies and making investment decisions to support a sustainable economy for the future. Public discussion on incidents and events–controversies –of companies can provide valuable insights on how well the company operates with regards to social consciousness and indicate the company’s overall operational capability. However, there are challenges in evaluating the degree of a company’s social consciousness and environmental sustainability due to the lack of systematic data. We introduce a system that utilizes Twitter data to detect and monitor controversial events and show their impact on market volatility. In our study, controversial events are identified from clustered tweets that share the same 5W terms and sentiment polarities of these clusters. Credible news links inside the event tweets are used to validate the truth of the event. A case study on the Starbucks Philadelphia arrests shows that this method can provide the desired functionality. |
| Tasks | |
| Published | 2019-08-25 |
| URL | https://arxiv.org/abs/1909.01093v1 |
| https://arxiv.org/pdf/1909.01093v1.pdf | |
| PWC | https://paperswithcode.com/paper/empirical-study-on-detecting-controversy-in |
| Repo | |
| Framework | |
Transfer Learning with Dynamic Distribution Adaptation
| Title | Transfer Learning with Dynamic Distribution Adaptation |
| Authors | Jindong Wang, Yiqiang Chen, Wenjie Feng, Han Yu, Meiyu Huang, Qiang Yang |
| Abstract | Transfer learning aims to learn robust classifiers for the target domain by leveraging knowledge from a source domain. Since the source and the target domains are usually from different distributions, existing methods mainly focus on adapting the cross-domain marginal or conditional distributions. However, in real applications, the marginal and conditional distributions usually have different contributions to the domain discrepancy. Existing methods fail to quantitatively evaluate the different importance of these two distributions, which will result in unsatisfactory transfer performance. In this paper, we propose a novel concept called Dynamic Distribution Adaptation (DDA), which is capable of quantitatively evaluating the relative importance of each distribution. DDA can be easily incorporated into the framework of structural risk minimization to solve transfer learning problems. On the basis of DDA, we propose two novel learning algorithms: (1) Manifold Dynamic Distribution Adaptation (MDDA) for traditional transfer learning, and (2) Dynamic Distribution Adaptation Network (DDAN) for deep transfer learning. Extensive experiments demonstrate that MDDA and DDAN significantly improve the transfer learning performance and setup a strong baseline over the latest deep and adversarial methods on digits recognition, sentiment analysis, and image classification. More importantly, it is shown that marginal and conditional distributions have different contributions to the domain divergence, and our DDA is able to provide good quantitative evaluation of their relative importance which leads to better performance. We believe this observation can be helpful for future research in transfer learning. |
| Tasks | Image Classification, Sentiment Analysis, Transfer Learning |
| Published | 2019-09-17 |
| URL | https://arxiv.org/abs/1909.08531v1 |
| https://arxiv.org/pdf/1909.08531v1.pdf | |
| PWC | https://paperswithcode.com/paper/transfer-learning-with-dynamic-distribution |
| Repo | |
| Framework | |
Neural Poetry: Learning to Generate Poems using Syllables
| Title | Neural Poetry: Learning to Generate Poems using Syllables |
| Authors | Andrea Zugarini, Stefano Melacci, Marco Maggini |
| Abstract | Motivated by the recent progresses on machine learning-based models that learn artistic styles, in this paper we focus on the problem of poem generation. This is a challenging task in which the machine has to capture the linguistic features that strongly characterize a certain poet, as well as the semantics of the poet’s production, that are influenced by his personal experiences and by his literary background. Since poetry is constructed using syllables, that regulate the form and structure of poems, we propose a syllable-based neural language model, and we describe a poem generation mechanism that is designed around the poet style, automatically selecting the most representative generations. The poetic work of a target author is usually not enough to successfully train modern deep neural networks, so we propose a multi-stage procedure that exploits non-poetic works of the same author, and also other publicly available huge corpora to learn syntax and grammar of the target language. We focus on the Italian poet Dante Alighieri, widely famous for his Divine Comedy. A quantitative and qualitative experimental analysis of the generated tercets is reported, where we included expert judges with strong background in humanistic studies. The generated tercets are frequently considered to be real by a generic population of judges, with relative difference of 56.25% with respect to the ones really authored by Dante, and expert judges perceived Dante’s style and rhymes in the generated text. |
| Tasks | Language Modelling |
| Published | 2019-08-23 |
| URL | https://arxiv.org/abs/1908.08861v2 |
| https://arxiv.org/pdf/1908.08861v2.pdf | |
| PWC | https://paperswithcode.com/paper/neural-poetry-learning-to-generate-poems |
| Repo | |
| Framework | |
