Paper Group ANR 307
Scaling Video Analytics Systems to Large Camera Deployments. Neural Machine Translation of Logographic Languages Using Sub-character Level Information. Adaptive Polar Active Contour for Segmentation and Tracking in Ultrasound Videos. Research on the Brain-inspired Cross-modal Neural Cognitive Computing Framework. Constraining the Dynamics of Deep P …
Scaling Video Analytics Systems to Large Camera Deployments
| Title | Scaling Video Analytics Systems to Large Camera Deployments |
| Authors | Samvit Jain, Ganesh Ananthanarayanan, Junchen Jiang, Yuanchao Shu, Joseph E. Gonzalez |
| Abstract | Driven by advances in computer vision and the falling costs of camera hardware, organizations are deploying video cameras en masse for the spatial monitoring of their physical premises. Scaling video analytics to massive camera deployments, however, presents a new and mounting challenge, as compute cost grows proportionally to the number of camera feeds. This paper is driven by a simple question: can we scale video analytics in such a way that cost grows sublinearly, or even remains constant, as we deploy more cameras, while inference accuracy remains stable, or even improves. We believe the answer is yes. Our key observation is that video feeds from wide-area camera deployments demonstrate significant content correlations (e.g. to other geographically proximate feeds), both in space and over time. These spatio-temporal correlations can be harnessed to dramatically reduce the size of the inference search space, decreasing both workload and false positive rates in multi-camera video analytics. By discussing use-cases and technical challenges, we propose a roadmap for scaling video analytics to large camera networks, and outline a plan for its realization. |
| Tasks | |
| Published | 2018-09-07 |
| URL | https://arxiv.org/abs/1809.02318v4 |
| https://arxiv.org/pdf/1809.02318v4.pdf | |
| PWC | https://paperswithcode.com/paper/scaling-video-analytics-systems-to-large |
| Repo | |
| Framework | |
Neural Machine Translation of Logographic Languages Using Sub-character Level Information
| Title | Neural Machine Translation of Logographic Languages Using Sub-character Level Information |
| Authors | Longtu Zhang, Mamoru Komachi |
| Abstract | Recent neural machine translation (NMT) systems have been greatly improved by encoder-decoder models with attention mechanisms and sub-word units. However, important differences between languages with logographic and alphabetic writing systems have long been overlooked. This study focuses on these differences and uses a simple approach to improve the performance of NMT systems utilizing decomposed sub-character level information for logographic languages. Our results indicate that our approach not only improves the translation capabilities of NMT systems between Chinese and English, but also further improves NMT systems between Chinese and Japanese, because it utilizes the shared information brought by similar sub-character units. |
| Tasks | Machine Translation |
| Published | 2018-09-07 |
| URL | http://arxiv.org/abs/1809.02694v1 |
| http://arxiv.org/pdf/1809.02694v1.pdf | |
| PWC | https://paperswithcode.com/paper/neural-machine-translation-of-logographic |
| Repo | |
| Framework | |
Adaptive Polar Active Contour for Segmentation and Tracking in Ultrasound Videos
| Title | Adaptive Polar Active Contour for Segmentation and Tracking in Ultrasound Videos |
| Authors | Ebrahim Karami, Mohamed Shehata, Andrew Smith |
| Abstract | Detection of relative changes in circulating blood volume is important to guide resuscitation and manage a variety of medical conditions including sepsis, trauma, dialysis and congestive heart failure. Recent studies have shown that estimates of circulating blood volume can be obtained from the cross-sectional area (CSA) of the internal jugular vein (IJV) from ultrasound images. However, accurate segmentation and tracking of the IJV in ultrasound imaging is a challenging task and is significantly influenced by a number of parameters such as the image quality, shape, and temporal variation. In this paper, we propose a novel adaptive polar active contour (Ad-PAC) algorithm for the segmentation and tracking of the IJV in ultrasound videos. In the proposed algorithm, the parameters of the Ad-PAC algorithm are adapted based on the results of segmentation in previous frames. The Ad-PAC algorithm is applied to 65 ultrasound videos captured from 13 healthy subjects, with each video containing 450 frames. The results show that spatial and temporal adaptation of the energy function significantly improves segmentation performance when compared to current state-of-the-art active contour algorithms. |
| Tasks | |
| Published | 2018-03-19 |
| URL | http://arxiv.org/abs/1803.07195v1 |
| http://arxiv.org/pdf/1803.07195v1.pdf | |
| PWC | https://paperswithcode.com/paper/adaptive-polar-active-contour-for |
| Repo | |
| Framework | |
Research on the Brain-inspired Cross-modal Neural Cognitive Computing Framework
| Title | Research on the Brain-inspired Cross-modal Neural Cognitive Computing Framework |
| Authors | Yang Liu |
| Abstract | To address modeling problems of brain-inspired intelligence, this thesis is focused on researching in the semantic-oriented framework design for multimedia and multimodal information. The Multimedia Neural Cognitive Computing (MNCC) model was designed based on the nervous mechanism and cognitive architecture. Furthermore, the semantic-oriented hierarchical Cross-modal Neural Cognitive Computing (CNCC) framework was proposed based on MNCC model, and formal description and analysis for CNCC framework was given. It would effectively improve the performance of semantic processing for multimedia and cross-modal information, and has far-reaching significance for exploration and realization brain-inspired computing. |
| Tasks | |
| Published | 2018-05-03 |
| URL | http://arxiv.org/abs/1805.01385v2 |
| http://arxiv.org/pdf/1805.01385v2.pdf | |
| PWC | https://paperswithcode.com/paper/research-on-the-brain-inspired-cross-modal |
| Repo | |
| Framework | |
Constraining the Dynamics of Deep Probabilistic Models
| Title | Constraining the Dynamics of Deep Probabilistic Models |
| Authors | Marco Lorenzi, Maurizio Filippone |
| Abstract | We introduce a novel generative formulation of deep probabilistic models implementing “soft” constraints on their function dynamics. In particular, we develop a flexible methodological framework where the modeled functions and derivatives of a given order are subject to inequality or equality constraints. We then characterize the posterior distribution over model and constraint parameters through stochastic variational inference. As a result, the proposed approach allows for accurate and scalable uncertainty quantification on the predictions and on all parameters. We demonstrate the application of equality constraints in the challenging problem of parameter inference in ordinary differential equation models, while we showcase the application of inequality constraints on the problem of monotonic regression of count data. The proposed approach is extensively tested in several experimental settings, leading to highly competitive results in challenging modeling applications, while offering high expressiveness, flexibility and scalability. |
| Tasks | |
| Published | 2018-02-15 |
| URL | http://arxiv.org/abs/1802.05680v2 |
| http://arxiv.org/pdf/1802.05680v2.pdf | |
| PWC | https://paperswithcode.com/paper/constraining-the-dynamics-of-deep |
| Repo | |
| Framework | |
Degree-$d$ Chow Parameters Robustly Determine Degree-$d$ PTFs (and Algorithmic Applications)
| Title | Degree-$d$ Chow Parameters Robustly Determine Degree-$d$ PTFs (and Algorithmic Applications) |
| Authors | Ilias Diakonikolas, Daniel M. Kane |
| Abstract | The degree-$d$ Chow parameters of a Boolean function $f: {-1,1}^n \to \mathbb{R}$ are its degree at most $d$ Fourier coefficients. It is well-known that degree-$d$ Chow parameters uniquely characterize degree-$d$ polynomial threshold functions (PTFs) within the space of all bounded functions. In this paper, we prove a robust version of this theorem: For $f$ any Boolean degree-$d$ PTF and $g$ any bounded function, if the degree-$d$ Chow parameters of $f$ are close to the degree-$d$ Chow parameters of $g$ in $\ell_2$-norm, then $f$ is close to $g$ in $\ell_1$-distance. Notably, our bound relating the two distances is completely independent of the dimension $n$. That is, we show that Boolean degree-$d$ PTFs are {\em robustly identifiable} from their degree-$d$ Chow parameters. Results of this form had been shown for the $d=1$ case~\cite{OS11:chow, DeDFS14}, but no non-trivial bound was previously known for $d >1$. Our robust identifiability result gives the following algorithmic applications: First, we show that Boolean degree-$d$ PTFs can be efficiently approximately reconstructed from approximations to their degree-$d$ Chow parameters. This immediately implies that degree-$d$ PTFs are efficiently learnable in the uniform distribution $d$-RFA model~\cite{BenDavidDichterman:98}. As a byproduct of our approach, we also obtain the first low integer-weight approximations of degree-$d$ PTFs, for $d>1$. As our second application, our robust identifiability result gives the first efficient algorithm, with dimension-independent error guarantees, for malicious learning of Boolean degree-$d$ PTFs under the uniform distribution. |
| Tasks | |
| Published | 2018-11-07 |
| URL | http://arxiv.org/abs/1811.03491v1 |
| http://arxiv.org/pdf/1811.03491v1.pdf | |
| PWC | https://paperswithcode.com/paper/degree-d-chow-parameters-robustly-determine |
| Repo | |
| Framework | |
Shortcut Matrix Product States and its applications
| Title | Shortcut Matrix Product States and its applications |
| Authors | Zhuan Li, Pan Zhang |
| Abstract | Matrix Product States (MPS), also known as Tensor Train (TT) decomposition in mathematics, has been proposed originally for describing an (especially one-dimensional) quantum system, and recently has found applications in various applications such as compressing high-dimensional data, supervised kernel linear classifier, and unsupervised generative modeling. However, when applied to systems which are not defined on one-dimensional lattices, a serious drawback of the MPS is the exponential decay of the correlations, which limits its power in capturing long-range dependences among variables in the system. To alleviate this problem, we propose to introduce long-range interactions, which act as shortcuts, to MPS, resulting in a new model \textit{ Shortcut Matrix Product States} (SMPS). When chosen properly, the shortcuts can decrease significantly the correlation length of the MPS, while preserving the computational efficiency. We develop efficient training methods of SMPS for various tasks, establish some of their mathematical properties, and show how to find a good location to add shortcuts. Finally, using extensive numerical experiments we evaluate its performance in a variety of applications, including function fitting, partition function calculation of $2-$d Ising model, and unsupervised generative modeling of handwritten digits, to illustrate its advantages over vanilla matrix product states. |
| Tasks | |
| Published | 2018-12-13 |
| URL | http://arxiv.org/abs/1812.05248v1 |
| http://arxiv.org/pdf/1812.05248v1.pdf | |
| PWC | https://paperswithcode.com/paper/shortcut-matrix-product-states-and-its |
| Repo | |
| Framework | |
A Syntactically Constrained Bidirectional-Asynchronous Approach for Emotional Conversation Generation
| Title | A Syntactically Constrained Bidirectional-Asynchronous Approach for Emotional Conversation Generation |
| Authors | Jingyuan Li, Xiao Sun |
| Abstract | Traditional neural language models tend to generate generic replies with poor logic and no emotion. In this paper, a syntactically constrained bidirectional-asynchronous approach for emotional conversation generation (E-SCBA) is proposed to address this issue. In our model, pre-generated emotion keywords and topic keywords are asynchronously introduced into the process of decoding. It is much different from most existing methods which generate replies from the first word to the last. Through experiments, the results indicate that our approach not only improves the diversity of replies, but gains a boost on both logic and emotion compared with baselines. |
| Tasks | |
| Published | 2018-06-19 |
| URL | http://arxiv.org/abs/1806.07000v4 |
| http://arxiv.org/pdf/1806.07000v4.pdf | |
| PWC | https://paperswithcode.com/paper/a-syntactically-constrained-bidirectional |
| Repo | |
| Framework | |
Natural Language Statistical Features of LSTM-generated Texts
| Title | Natural Language Statistical Features of LSTM-generated Texts |
| Authors | Marco Lippi, Marcelo A Montemurro, Mirko Degli Esposti, Giampaolo Cristadoro |
| Abstract | Long Short-Term Memory (LSTM) networks have recently shown remarkable performance in several tasks dealing with natural language generation, such as image captioning or poetry composition. Yet, only few works have analyzed text generated by LSTMs in order to quantitatively evaluate to which extent such artificial texts resemble those generated by humans. We compared the statistical structure of LSTM-generated language to that of written natural language, and to those produced by Markov models of various orders. In particular, we characterized the statistical structure of language by assessing word-frequency statistics, long-range correlations, and entropy measures. Our main finding is that while both LSTM and Markov-generated texts can exhibit features similar to real ones in their word-frequency statistics and entropy measures, LSTM-texts are shown to reproduce long-range correlations at scales comparable to those found in natural language. Moreover, for LSTM networks a temperature-like parameter controlling the generation process shows an optimal value—for which the produced texts are closest to real language—consistent across all the different statistical features investigated. |
| Tasks | Image Captioning, Text Generation |
| Published | 2018-04-10 |
| URL | http://arxiv.org/abs/1804.04087v2 |
| http://arxiv.org/pdf/1804.04087v2.pdf | |
| PWC | https://paperswithcode.com/paper/natural-language-statistical-features-of-lstm |
| Repo | |
| Framework | |
Improving brain computer interface performance by data augmentation with conditional Deep Convolutional Generative Adversarial Networks
| Title | Improving brain computer interface performance by data augmentation with conditional Deep Convolutional Generative Adversarial Networks |
| Authors | Qiqi Zhang, Ying Liu |
| Abstract | One of the big restrictions in brain computer interface field is the very limited training samples, it is difficult to build a reliable and usable system with such limited data. Inspired by generative adversarial networks, we propose a conditional Deep Convolutional Generative Adversarial (cDCGAN) Networks method to generate more artificial EEG signal automatically for data augmentation to improve the performance of convolutional neural networks in brain computer interface field and overcome the small training dataset problems. We evaluate the proposed cDCGAN method on BCI competition dataset of motor imagery. The results show that the generated artificial EEG data from Gaussian noise can learn the features from raw EEG data and has no less than the classification accuracy of raw EEG data in the testing dataset. Also by using generated artificial data can effectively improve classification accuracy at the same model with limited training data. |
| Tasks | Data Augmentation, EEG |
| Published | 2018-06-19 |
| URL | http://arxiv.org/abs/1806.07108v2 |
| http://arxiv.org/pdf/1806.07108v2.pdf | |
| PWC | https://paperswithcode.com/paper/improving-brain-computer-interface |
| Repo | |
| Framework | |
Back to square one: probabilistic trajectory forecasting without bells and whistles
| Title | Back to square one: probabilistic trajectory forecasting without bells and whistles |
| Authors | Ehsan Pajouheshgar, Christoph H. Lampert |
| Abstract | We introduce a spatio-temporal convolutional neural network model for trajectory forecasting from visual sources. Applied in an auto-regressive way it provides an explicit probability distribution over continuations of a given initial trajectory segment. We discuss it in relation to (more complicated) existing work and report on experiments on two standard datasets for trajectory forecasting: MNISTseq and Stanford Drones, achieving results on-par with or better than previous methods. |
| Tasks | |
| Published | 2018-12-07 |
| URL | http://arxiv.org/abs/1812.02984v1 |
| http://arxiv.org/pdf/1812.02984v1.pdf | |
| PWC | https://paperswithcode.com/paper/back-to-square-one-probabilistic-trajectory |
| Repo | |
| Framework | |
Fake News: A Survey of Research, Detection Methods, and Opportunities
| Title | Fake News: A Survey of Research, Detection Methods, and Opportunities |
| Authors | Xinyi Zhou, Reza Zafarani |
| Abstract | The explosive growth in fake news and its erosion to democracy, justice, and public trust has increased the demand for fake news analysis, detection and intervention. This survey comprehensively and systematically reviews fake news research. The survey identifies and specifies fundamental theories across various disciplines, e.g., psychology and social science, to facilitate and enhance the interdisciplinary research of fake news. Current fake news research is reviewed, summarized and evaluated. These studies focus on fake news from four perspective: (1) the false knowledge it carries, (2) its writing style, (3) its propagation patterns, and (4) the credibility of its creators and spreaders. We characterize each perspective with various analyzable and utilizable information provided by news and its spreaders, various strategies and frameworks that are adaptable, and techniques that are applicable. By reviewing the characteristics of fake news and open issues in fake news studies, we highlight some potential research tasks at the end of this survey. |
| Tasks | |
| Published | 2018-12-02 |
| URL | http://arxiv.org/abs/1812.00315v1 |
| http://arxiv.org/pdf/1812.00315v1.pdf | |
| PWC | https://paperswithcode.com/paper/fake-news-a-survey-of-research-detection |
| Repo | |
| Framework | |
Tensorial and bipartite block models for link prediction in layered networks and temporal networks
| Title | Tensorial and bipartite block models for link prediction in layered networks and temporal networks |
| Authors | Marc Tarres-Deulofeu, Antonia Godoy-Lorite, Roger Guimera, Marta Sales-Pardo |
| Abstract | Many real-world complex systems are well represented as multilayer networks; predicting interactions in those systems is one of the most pressing problems in predictive network science. To address this challenge, we introduce two stochastic block models for multilayer and temporal networks; one of them uses nodes as its fundamental unit, whereas the other focuses on links. We also develop scalable algorithms for inferring the parameters of these models. Because our models describe all layers simultaneously, our approach takes full advantage of the information contained in the whole network when making predictions about any particular layer. We illustrate the potential of our approach by analyzing two empirical datasets—a temporal network of email communications, and a network of drug interactions for treating different cancer types. We find that modeling all layers simultaneously does result, in general, in more accurate link prediction. However, the most predictive model depends on the dataset under consideration; whereas the node-based model is more appropriate for predicting drug interactions, the link-based model is more appropriate for predicting email communication. |
| Tasks | Link Prediction |
| Published | 2018-03-05 |
| URL | http://arxiv.org/abs/1803.01616v1 |
| http://arxiv.org/pdf/1803.01616v1.pdf | |
| PWC | https://paperswithcode.com/paper/tensorial-and-bipartite-block-models-for-link |
| Repo | |
| Framework | |
Evolutionary Diversity Optimization Using Multi-Objective Indicators
| Title | Evolutionary Diversity Optimization Using Multi-Objective Indicators |
| Authors | Aneta Neumann, Wanru Gao, Markus Wagner, Frank Neumann |
| Abstract | Evolutionary diversity optimization aims to compute a diverse set of solutions where all solutions meet a given quality criterion. With this paper, we bridge the areas of evolutionary diversity optimization and evolutionary multi-objective optimization. We show how popular indicators frequently used in the area of multi-objective optimization can be used for evolutionary diversity optimization. Our experimental investigations for evolving diverse sets of TSP instances and images according to various features show that two of the most prominent multi-objective indicators, namely the hypervolume indicator and the inverted generational distance, provide excellent results in terms of visualization and various diversity indicators. |
| Tasks | |
| Published | 2018-11-16 |
| URL | http://arxiv.org/abs/1811.06804v1 |
| http://arxiv.org/pdf/1811.06804v1.pdf | |
| PWC | https://paperswithcode.com/paper/evolutionary-diversity-optimization-using |
| Repo | |
| Framework | |
Unsupervised Learning and Segmentation of Complex Activities from Video
| Title | Unsupervised Learning and Segmentation of Complex Activities from Video |
| Authors | Fadime Sener, Angela Yao |
| Abstract | This paper presents a new method for unsupervised segmentation of complex activities from video into multiple steps, or sub-activities, without any textual input. We propose an iterative discriminative-generative approach which alternates between discriminatively learning the appearance of sub-activities from the videos’ visual features to sub-activity labels and generatively modelling the temporal structure of sub-activities using a Generalized Mallows Model. In addition, we introduce a model for background to account for frames unrelated to the actual activities. Our approach is validated on the challenging Breakfast Actions and Inria Instructional Videos datasets and outperforms both unsupervised and weakly-supervised state of the art. |
| Tasks | |
| Published | 2018-03-26 |
| URL | http://arxiv.org/abs/1803.09490v1 |
| http://arxiv.org/pdf/1803.09490v1.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-learning-and-segmentation-of |
| Repo | |
| Framework | |
