Paper Group ANR 208
Joint Background Reconstruction and Foreground Segmentation via A Two-stage Convolutional Neural Network. A filter based approach for inbetweening. Argumentation-based Security for Social Good. Is Natural Language a Perigraphic Process? The Theorem about Facts and Words Revisited. Hierarchical Representations for Efficient Architecture Search. Can …
Joint Background Reconstruction and Foreground Segmentation via A Two-stage Convolutional Neural Network
| Title | Joint Background Reconstruction and Foreground Segmentation via A Two-stage Convolutional Neural Network |
| Authors | Xu Zhao, Yingying Chen, Ming Tang, Jinqiao Wang |
| Abstract | Foreground segmentation in video sequences is a classic topic in computer vision. Due to the lack of semantic and prior knowledge, it is difficult for existing methods to deal with sophisticated scenes well. Therefore, in this paper, we propose an end-to-end two-stage deep convolutional neural network (CNN) framework for foreground segmentation in video sequences. In the first stage, a convolutional encoder-decoder sub-network is employed to reconstruct the background images and encode rich prior knowledge of background scenes. In the second stage, the reconstructed background and current frame are input into a multi-channel fully-convolutional sub-network (MCFCN) for accurate foreground segmentation. In the two-stage CNN, the reconstruction loss and segmentation loss are jointly optimized. The background images and foreground objects are output simultaneously in an end-to-end way. Moreover, by incorporating the prior semantic knowledge of foreground and background in the pre-training process, our method could restrain the background noise and keep the integrity of foreground objects at the same time. Experiments on CDNet 2014 show that our method outperforms the state-of-the-art by 4.9%. |
| Tasks | |
| Published | 2017-07-24 |
| URL | http://arxiv.org/abs/1707.07584v1 |
| http://arxiv.org/pdf/1707.07584v1.pdf | |
| PWC | https://paperswithcode.com/paper/joint-background-reconstruction-and |
| Repo | |
| Framework | |
A filter based approach for inbetweening
| Title | A filter based approach for inbetweening |
| Authors | Yuichi Yagi |
| Abstract | We present a filter based approach for inbetweening. We train a convolutional neural network to generate intermediate frames. This network aim to generate smooth animation of line drawings. Our method can process scanned images directly. Our method does not need to compute correspondence of lines and topological changes explicitly. We experiment our method with real animation production data. The results show that our method can generate intermediate frames partially. |
| Tasks | |
| Published | 2017-06-12 |
| URL | http://arxiv.org/abs/1706.03497v1 |
| http://arxiv.org/pdf/1706.03497v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-filter-based-approach-for-inbetweening |
| Repo | |
| Framework | |
Argumentation-based Security for Social Good
| Title | Argumentation-based Security for Social Good |
| Authors | Erisa Karafili, Antonis C. Kakas, Nikolaos I. Spanoudakis, Emil C. Lupu |
| Abstract | The increase of connectivity and the impact it has in every day life is raising new and existing security problems that are becoming important for social good. We introduce two particular problems: cyber attack attribution and regulatory data sharing. For both problems, decisions about which rules to apply, should be taken under incomplete and context dependent information. The solution we propose is based on argumentation reasoning, that is a well suited technique for implementing decision making mechanisms under conflicting and incomplete information. Our proposal permits us to identify the attacker of a cyber attack and decide the regulation rule that should be used while using and sharing data. We illustrate our solution through concrete examples. |
| Tasks | Decision Making |
| Published | 2017-05-01 |
| URL | http://arxiv.org/abs/1705.00732v1 |
| http://arxiv.org/pdf/1705.00732v1.pdf | |
| PWC | https://paperswithcode.com/paper/argumentation-based-security-for-social-good |
| Repo | |
| Framework | |
Is Natural Language a Perigraphic Process? The Theorem about Facts and Words Revisited
| Title | Is Natural Language a Perigraphic Process? The Theorem about Facts and Words Revisited |
| Authors | Łukasz Dębowski |
| Abstract | As we discuss, a stationary stochastic process is nonergodic when a random persistent topic can be detected in the infinite random text sampled from the process, whereas we call the process strongly nonergodic when an infinite sequence of independent random bits, called probabilistic facts, is needed to describe this topic completely. Replacing probabilistic facts with an algorithmically random sequence of bits, called algorithmic facts, we adapt this property back to ergodic processes. Subsequently, we call a process perigraphic if the number of algorithmic facts which can be inferred from a finite text sampled from the process grows like a power of the text length. We present a simple example of such a process. Moreover, we demonstrate an assertion which we call the theorem about facts and words. This proposition states that the number of probabilistic or algorithmic facts which can be inferred from a text drawn from a process must be roughly smaller than the number of distinct word-like strings detected in this text by means of the PPM compression algorithm. We also observe that the number of the word-like strings for a sample of plays by Shakespeare follows an empirical stepwise power law, in a stark contrast to Markov processes. Hence we suppose that natural language considered as a process is not only non-Markov but also perigraphic. |
| Tasks | |
| Published | 2017-06-14 |
| URL | http://arxiv.org/abs/1706.04432v2 |
| http://arxiv.org/pdf/1706.04432v2.pdf | |
| PWC | https://paperswithcode.com/paper/is-natural-language-a-perigraphic-process-the |
| Repo | |
| Framework | |
Hierarchical Representations for Efficient Architecture Search
| Title | Hierarchical Representations for Efficient Architecture Search |
| Authors | Hanxiao Liu, Karen Simonyan, Oriol Vinyals, Chrisantha Fernando, Koray Kavukcuoglu |
| Abstract | We explore efficient neural architecture search methods and show that a simple yet powerful evolutionary algorithm can discover new architectures with excellent performance. Our approach combines a novel hierarchical genetic representation scheme that imitates the modularized design pattern commonly adopted by human experts, and an expressive search space that supports complex topologies. Our algorithm efficiently discovers architectures that outperform a large number of manually designed models for image classification, obtaining top-1 error of 3.6% on CIFAR-10 and 20.3% when transferred to ImageNet, which is competitive with the best existing neural architecture search approaches. We also present results using random search, achieving 0.3% less top-1 accuracy on CIFAR-10 and 0.1% less on ImageNet whilst reducing the search time from 36 hours down to 1 hour. |
| Tasks | Image Classification, Neural Architecture Search |
| Published | 2017-11-01 |
| URL | http://arxiv.org/abs/1711.00436v2 |
| http://arxiv.org/pdf/1711.00436v2.pdf | |
| PWC | https://paperswithcode.com/paper/hierarchical-representations-for-efficient |
| Repo | |
| Framework | |
Can We See Photosynthesis? Magnifying the Tiny Color Changes of Plant Green Leaves Using Eulerian Video Magnification
| Title | Can We See Photosynthesis? Magnifying the Tiny Color Changes of Plant Green Leaves Using Eulerian Video Magnification |
| Authors | Islam A. T. F. Taj-Eddin, Mahmoud Afifi, Mostafa Korashy, Ali H. Ahmed, Ng Yoke Cheng, Evelyng Hernandez, Salma M. Abdel-latif |
| Abstract | Plant aliveness is proven through laboratory experiments and special scientific instruments. In this paper, we aim to detect the degree of animation of plants based on the magnification of the small color changes in the plant’s green leaves using the Eulerian video magnification. Capturing the video under a controlled environment, e.g., using a tripod and direct current (DC) light sources, reduces camera movements and minimizes light fluctuations; we aim to reduce the external factors as much as possible. The acquired video is then stabilized and a proposed algorithm used to reduce the illumination variations. Lastly, the Euler magnification is utilized to magnify the color changes on the light invariant video. The proposed system does not require any special purpose instruments as it uses a digital camera with a regular frame rate. The results of magnified color changes on both natural and plastic leaves show that the live green leaves have color changes in contrast to the plastic leaves. Hence, we can argue that the color changes of the leaves are due to biological operations, such as photosynthesis. To date, this is possibly the first work that focuses on interpreting visually, some biological operations of plants without any special purpose instruments. |
| Tasks | |
| Published | 2017-06-12 |
| URL | http://arxiv.org/abs/1706.03867v3 |
| http://arxiv.org/pdf/1706.03867v3.pdf | |
| PWC | https://paperswithcode.com/paper/can-we-see-photosynthesis-magnifying-the-tiny |
| Repo | |
| Framework | |
Natural Language Guided Visual Relationship Detection
| Title | Natural Language Guided Visual Relationship Detection |
| Authors | Wentong Liao, Lin Shuai, Bodo Rosenhahn, Michael Ying Yang |
| Abstract | Reasoning about the relationships between object pairs in images is a crucial task for holistic scene understanding. Most of the existing works treat this task as a pure visual classification task: each type of relationship or phrase is classified as a relation category based on the extracted visual features. However, each kind of relationships has a wide variety of object combination and each pair of objects has diverse interactions. Obtaining sufficient training samples for all possible relationship categories is difficult and expensive. In this work, we propose a natural language guided framework to tackle this problem. We propose to use a generic bi-directional recurrent neural network to predict the semantic connection between the participating objects in the relationship from the aspect of natural language. The proposed simple method achieves the state-of-the-art on the Visual Relationship Detection (VRD) and Visual Genome datasets, especially when predicting unseen relationships (e.g. recall improved from 76.42% to 89.79% on VRD zero-shot testing set). |
| Tasks | Scene Understanding |
| Published | 2017-11-16 |
| URL | http://arxiv.org/abs/1711.06032v2 |
| http://arxiv.org/pdf/1711.06032v2.pdf | |
| PWC | https://paperswithcode.com/paper/natural-language-guided-visual-relationship |
| Repo | |
| Framework | |
Tracking Typological Traits of Uralic Languages in Distributed Language Representations
| Title | Tracking Typological Traits of Uralic Languages in Distributed Language Representations |
| Authors | Johannes Bjerva, Isabelle Augenstein |
| Abstract | Although linguistic typology has a long history, computational approaches have only recently gained popularity. The use of distributed representations in computational linguistics has also become increasingly popular. A recent development is to learn distributed representations of language, such that typologically similar languages are spatially close to one another. Although empirical successes have been shown for such language representations, they have not been subjected to much typological probing. In this paper, we first look at whether this type of language representations are empirically useful for model transfer between Uralic languages in deep neural networks. We then investigate which typological features are encoded in these representations by attempting to predict features in the World Atlas of Language Structures, at various stages of fine-tuning of the representations. We focus on Uralic languages, and find that some typological traits can be automatically inferred with accuracies well above a strong baseline. |
| Tasks | |
| Published | 2017-11-15 |
| URL | http://arxiv.org/abs/1711.05468v1 |
| http://arxiv.org/pdf/1711.05468v1.pdf | |
| PWC | https://paperswithcode.com/paper/tracking-typological-traits-of-uralic |
| Repo | |
| Framework | |
Predicting the Quality of Short Narratives from Social Media
| Title | Predicting the Quality of Short Narratives from Social Media |
| Authors | Tong Wang, Ping Chen, Boyang Li |
| Abstract | An important and difficult challenge in building computational models for narratives is the automatic evaluation of narrative quality. Quality evaluation connects narrative understanding and generation as generation systems need to evaluate their own products. To circumvent difficulties in acquiring annotations, we employ upvotes in social media as an approximate measure for story quality. We collected 54,484 answers from a crowd-powered question-and-answer website, Quora, and then used active learning to build a classifier that labeled 28,320 answers as stories. To predict the number of upvotes without the use of social network features, we create neural networks that model textual regions and the interdependence among regions, which serve as strong benchmarks for future research. To our best knowledge, this is the first large-scale study for automatic evaluation of narrative quality. |
| Tasks | Active Learning |
| Published | 2017-07-08 |
| URL | http://arxiv.org/abs/1707.02499v1 |
| http://arxiv.org/pdf/1707.02499v1.pdf | |
| PWC | https://paperswithcode.com/paper/predicting-the-quality-of-short-narratives |
| Repo | |
| Framework | |
How Important is Syntactic Parsing Accuracy? An Empirical Evaluation on Rule-Based Sentiment Analysis
| Title | How Important is Syntactic Parsing Accuracy? An Empirical Evaluation on Rule-Based Sentiment Analysis |
| Authors | Carlos Gómez-Rodríguez, Iago Alonso-Alonso, David Vilares |
| Abstract | Syntactic parsing, the process of obtaining the internal structure of sentences in natural languages, is a crucial task for artificial intelligence applications that need to extract meaning from natural language text or speech. Sentiment analysis is one example of application for which parsing has recently proven useful. In recent years, there have been significant advances in the accuracy of parsing algorithms. In this article, we perform an empirical, task-oriented evaluation to determine how parsing accuracy influences the performance of a state-of-the-art rule-based sentiment analysis system that determines the polarity of sentences from their parse trees. In particular, we evaluate the system using four well-known dependency parsers, including both current models with state-of-the-art accuracy and more innacurate models which, however, require less computational resources. The experiments show that all of the parsers produce similarly good results in the sentiment analysis task, without their accuracy having any relevant influence on the results. Since parsing is currently a task with a relatively high computational cost that varies strongly between algorithms, this suggests that sentiment analysis researchers and users should prioritize speed over accuracy when choosing a parser; and parsing researchers should investigate models that improve speed further, even at some cost to accuracy. |
| Tasks | Sentiment Analysis |
| Published | 2017-06-07 |
| URL | http://arxiv.org/abs/1706.02141v3 |
| http://arxiv.org/pdf/1706.02141v3.pdf | |
| PWC | https://paperswithcode.com/paper/how-important-is-syntactic-parsing-accuracy |
| Repo | |
| Framework | |
Discrete-Continuous ADMM for Transductive Inference in Higher-Order MRFs
| Title | Discrete-Continuous ADMM for Transductive Inference in Higher-Order MRFs |
| Authors | Emanuel Laude, Jan-Hendrik Lange, Jonas Schüpfer, Csaba Domokos, Laura Leal-Taixé, Frank R. Schmidt, Bjoern Andres, Daniel Cremers |
| Abstract | This paper introduces a novel algorithm for transductive inference in higher-order MRFs, where the unary energies are parameterized by a variable classifier. The considered task is posed as a joint optimization problem in the continuous classifier parameters and the discrete label variables. In contrast to prior approaches such as convex relaxations, we propose an advantageous decoupling of the objective function into discrete and continuous subproblems and a novel, efficient optimization method related to ADMM. This approach preserves integrality of the discrete label variables and guarantees global convergence to a critical point. We demonstrate the advantages of our approach in several experiments including video object segmentation on the DAVIS data set and interactive image segmentation. |
| Tasks | Semantic Segmentation, Video Object Segmentation, Video Semantic Segmentation |
| Published | 2017-05-14 |
| URL | http://arxiv.org/abs/1705.05020v5 |
| http://arxiv.org/pdf/1705.05020v5.pdf | |
| PWC | https://paperswithcode.com/paper/discrete-continuous-admm-for-transductive |
| Repo | |
| Framework | |
Autism Classification Using Brain Functional Connectivity Dynamics and Machine Learning
| Title | Autism Classification Using Brain Functional Connectivity Dynamics and Machine Learning |
| Authors | Ravi Tejwani, Adam Liska, Hongyuan You, Jenna Reinen, Payel Das |
| Abstract | The goal of the present study is to identify autism using machine learning techniques and resting-state brain imaging data, leveraging the temporal variability of the functional connections (FC) as the only information. We estimated and compared the FC variability across brain regions between typical, healthy subjects and autistic population by analyzing brain imaging data from a world-wide multi-site database known as ABIDE (Autism Brain Imaging Data Exchange). Our analysis revealed that patients diagnosed with autism spectrum disorder (ASD) show increased FC variability in several brain regions that are associated with low FC variability in the typical brain. We then used the enhanced FC variability of brain regions as features for training machine learning models for ASD classification and achieved 65% accuracy in identification of ASD versus control subjects within the dataset. We also used node strength estimated from number of functional connections per node averaged over the whole scan as features for ASD classification.The results reveal that the dynamic FC measures outperform or are comparable with the static FC measures in predicting ASD. |
| Tasks | |
| Published | 2017-12-21 |
| URL | http://arxiv.org/abs/1712.08041v1 |
| http://arxiv.org/pdf/1712.08041v1.pdf | |
| PWC | https://paperswithcode.com/paper/autism-classification-using-brain-functional |
| Repo | |
| Framework | |
Social welfare and profit maximization from revealed preferences
| Title | Social welfare and profit maximization from revealed preferences |
| Authors | Ziwei Ji, Ruta Mehta, Matus Telgarsky |
| Abstract | Consider the seller’s problem of finding optimal prices for her $n$ (divisible) goods when faced with a set of $m$ consumers, given that she can only observe their purchased bundles at posted prices, i.e., revealed preferences. We study both social welfare and profit maximization with revealed preferences. Although social welfare maximization is a seemingly non-convex optimization problem in prices, we show that (i) it can be reduced to a dual convex optimization problem in prices, and (ii) the revealed preferences can be interpreted as supergradients of the concave conjugate of valuation, with which subgradients of the dual function can be computed. We thereby obtain a simple subgradient-based algorithm for strongly concave valuations and convex cost, with query complexity $O(m^2/\epsilon^2)$, where $\epsilon$ is the additive difference between the social welfare induced by our algorithm and the optimum social welfare. We also study social welfare maximization under the online setting, specifically the random permutation model, where consumers arrive one-by-one in a random order. For the case where consumer valuations can be arbitrary continuous functions, we propose a price posting mechanism that achieves an expected social welfare up to an additive factor of $O(\sqrt{mn})$ from the maximum social welfare. Finally, for profit maximization (which may be non-convex in simple cases), we give nearly matching upper and lower bounds on the query complexity for separable valuations and cost (i.e., each good can be treated independently). |
| Tasks | |
| Published | 2017-11-06 |
| URL | http://arxiv.org/abs/1711.02211v2 |
| http://arxiv.org/pdf/1711.02211v2.pdf | |
| PWC | https://paperswithcode.com/paper/social-welfare-and-profit-maximization-from |
| Repo | |
| Framework | |
Six Challenges for Neural Machine Translation
| Title | Six Challenges for Neural Machine Translation |
| Authors | Philipp Koehn, Rebecca Knowles |
| Abstract | We explore six challenges for neural machine translation: domain mismatch, amount of training data, rare words, long sentences, word alignment, and beam search. We show both deficiencies and improvements over the quality of phrase-based statistical machine translation. |
| Tasks | Machine Translation, Word Alignment |
| Published | 2017-06-12 |
| URL | http://arxiv.org/abs/1706.03872v1 |
| http://arxiv.org/pdf/1706.03872v1.pdf | |
| PWC | https://paperswithcode.com/paper/six-challenges-for-neural-machine-translation |
| Repo | |
| Framework | |
A Fast Integrated Planning and Control Framework for Autonomous Driving via Imitation Learning
| Title | A Fast Integrated Planning and Control Framework for Autonomous Driving via Imitation Learning |
| Authors | Liting Sun, Cheng Peng, Wei Zhan, Masayoshi Tomizuka |
| Abstract | For safe and efficient planning and control in autonomous driving, we need a driving policy which can achieve desirable driving quality in long-term horizon with guaranteed safety and feasibility. Optimization-based approaches, such as Model Predictive Control (MPC), can provide such optimal policies, but their computational complexity is generally unacceptable for real-time implementation. To address this problem, we propose a fast integrated planning and control framework that combines learning- and optimization-based approaches in a two-layer hierarchical structure. The first layer, defined as the “policy layer”, is established by a neural network which learns the long-term optimal driving policy generated by MPC. The second layer, called the “execution layer”, is a short-term optimization-based controller that tracks the reference trajecotries given by the “policy layer” with guaranteed short-term safety and feasibility. Moreover, with efficient and highly-representative features, a small-size neural network is sufficient in the “policy layer” to handle many complicated driving scenarios. This renders online imitation learning with Dataset Aggregation (DAgger) so that the performance of the “policy layer” can be improved rapidly and continuously online. Several exampled driving scenarios are demonstrated to verify the effectiveness and efficiency of the proposed framework. |
| Tasks | Autonomous Driving, Imitation Learning |
| Published | 2017-07-09 |
| URL | http://arxiv.org/abs/1707.02515v1 |
| http://arxiv.org/pdf/1707.02515v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-fast-integrated-planning-and-control |
| Repo | |
| Framework | |
