Paper Group NAWR 25
Predicting Brain Activation with WordNet Embeddings. Multi-scale Residual Network for Image Super-Resolution. A Structured Syntax-Semantics Interface for English-AMR Alignment. Sequence-to-sequence Models for Cache Transition Systems. Extending Layered Models to 3D Motion. From Neural Re-Ranking to Neural Ranking: Learning a Sparse Representation f …
Predicting Brain Activation with WordNet Embeddings
| Title | Predicting Brain Activation with WordNet Embeddings |
| Authors | Jo{~a}o Ant{'o}nio Rodrigues, Ruben Branco, Jo{~a}o Silva, Chakaveh Saedi, Ant{'o}nio Branco |
| Abstract | The task of taking a semantic representation of a noun and predicting the brain activity triggered by it in terms of fMRI spatial patterns was pioneered by Mitchell et al. 2008. That seminal work used word co-occurrence features to represent the meaning of the nouns. Even though the task does not impose any specific type of semantic representation, the vast majority of subsequent approaches resort to feature-based models or to semantic spaces (aka word embeddings). We address this task, with competitive results, by using instead a semantic network to encode lexical semantics, thus providing further evidence for the cognitive plausibility of this approach to model lexical meaning. |
| Tasks | Word Embeddings |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-2801/ |
| https://www.aclweb.org/anthology/W18-2801 | |
| PWC | https://paperswithcode.com/paper/predicting-brain-activation-with-wordnet |
| Repo | https://github.com/nlx-group/BrainActivation |
| Framework | none |
Multi-scale Residual Network for Image Super-Resolution
| Title | Multi-scale Residual Network for Image Super-Resolution |
| Authors | Juncheng Li, Faming Fang, Kangfu Mei, Guixu Zhang |
| Abstract | Recent studies have shown that deep neural networks can significantly improve the quality of single-image super-resolution. Current researches tend to use deeper convolutional neural networks to enhance performance. However, blindly increasing the depth of the network cannot ameliorate the network effectively. Worse still, with the depth of the network increases, more problems occurred in the training process and more training tricks are needed. In this paper, we propose a novel multi-scale residual network (MSRN) to fully exploit the image features, which outperform most of the state-of-the-art methods. Based on the residual block, we introduce convolution kernels of different sizes to adaptively detect the image features in different scales. Meanwhile, we let these features interact with each other to get the most efficacious image information, we call this structure Multi-scale Residual Block (MSRB). Furthermore, the outputs of each MSRB are used as the hierarchical features for global feature fusion. Finally, all these features are sent to the reconstruction module for recovering the high-quality image. |
| Tasks | Image Super-Resolution, Super-Resolution |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Juncheng_Li_Multi-scale_Residual_Network_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Juncheng_Li_Multi-scale_Residual_Network_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/multi-scale-residual-network-for-image-super |
| Repo | https://github.com/MIVRC/MSRN-PyTorch |
| Framework | pytorch |
A Structured Syntax-Semantics Interface for English-AMR Alignment
| Title | A Structured Syntax-Semantics Interface for English-AMR Alignment |
| Authors | Ida Szubert, Adam Lopez, Nathan Schneider |
| Abstract | Abstract Meaning Representation (AMR) annotations are often assumed to closely mirror dependency syntax, but AMR explicitly does not require this, and the assumption has never been tested. To test it, we devise an expressive framework to align AMR graphs to dependency graphs, which we use to annotate 200 AMRs. Our annotation explains how 97{%} of AMR edges are evoked by words or syntax. Previously existing AMR alignment frameworks did not allow for mapping AMR onto syntax, and as a consequence they explained at most 23{%}. While we find that there are indeed many cases where AMR annotations closely mirror syntax, there are also pervasive differences. We use our annotations to test a baseline AMR-to-syntax aligner, finding that this task is more difficult than AMR-to-string alignment; and to pinpoint errors in an AMR parser. We make our data and code freely available for further research on AMR parsing and generation, and the relationship of AMR to syntax. |
| Tasks | Amr Parsing |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/N18-1106/ |
| https://www.aclweb.org/anthology/N18-1106 | |
| PWC | https://paperswithcode.com/paper/a-structured-syntax-semantics-interface-for |
| Repo | https://github.com/ida-szubert/amr_ud |
| Framework | none |
Sequence-to-sequence Models for Cache Transition Systems
| Title | Sequence-to-sequence Models for Cache Transition Systems |
| Authors | Xiaochang Peng, Linfeng Song, Daniel Gildea, Giorgio Satta |
| Abstract | In this paper, we present a sequence-to-sequence based approach for mapping natural language sentences to AMR semantic graphs. We transform the sequence to graph mapping problem to a word sequence to transition action sequence problem using a special transition system called a cache transition system. To address the sparsity issue of neural AMR parsing, we feed feature embeddings from the transition state to provide relevant local information for each decoder state. We present a monotonic hard attention model for the transition framework to handle the strictly left-to-right alignment between each transition state and the current buffer input focus. We evaluate our neural transition model on the AMR parsing task, and our parser outperforms other sequence-to-sequence approaches and achieves competitive results in comparison with the best-performing models. |
| Tasks | Amr Parsing, Sentence Compression, Text Summarization |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/P18-1171/ |
| https://www.aclweb.org/anthology/P18-1171 | |
| PWC | https://paperswithcode.com/paper/sequence-to-sequence-models-for-cache |
| Repo | https://github.com/xiaochang13/CacheTransition-Seq2seq |
| Framework | tf |
Extending Layered Models to 3D Motion
| Title | Extending Layered Models to 3D Motion |
| Authors | Dong Lao, Ganesh Sundaramoorthi |
| Abstract | We consider the problem of inferring a layered representa-tion, its depth ordering and motion segmentation from a video in whichobjects may undergo 3D non-planar motion relative to the camera. Wegeneralize layered inference to the aforementioned case and correspond-ing self-occlusion phenomena. We accomplish this by introducing a flat-tened 3D object representation, which is a compact representation of anobject that contains all visible portions of the object seen in the video,including parts of an object that are self-occluded (as well as occluded)in one frame but seen in another. We formulate the inference of such flat-tened representations and motion segmentation, and derive an optimiza-tion scheme. We also introduce a new depth ordering scheme, which isindependent of layered inference and addresses the case of self-occlusion.It requires almost no computation given the flattened representations.Experiments on benchmark datasets show the advantage of our methodcompared to existing layered methods, which do not model 3D motionand self-occlusion. |
| Tasks | Motion Segmentation |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Dong_Lao_Extending_Layered_Models_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Dong_Lao_Extending_Layered_Models_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/extending-layered-models-to-3d-motion |
| Repo | https://github.com/donglao/layers3Dmotion |
| Framework | none |
From Neural Re-Ranking to Neural Ranking: Learning a Sparse Representation for Inverted Indexing
| Title | From Neural Re-Ranking to Neural Ranking: Learning a Sparse Representation for Inverted Indexing |
| Authors | Hamed Zamani, Mostafa Dehghani, W. Bruce Croft, Erik Learned-Miller, and Jaap Kamps |
| Abstract | The availability of massive data and computing power allowing for effective data driven neural approaches is having a major impact on machine learning and information retrieval research, but these models have a basic problem with efficiency. Current neural ranking models are implemented as multistage rankers: for efficiency reasons, the neural model only re-ranks the top ranked documents retrieved by a first-stage efficient ranker in response to a given query. Neural ranking models learn dense representations causing essentially every query term to match every document term, making it highly inefficient or intractable to rank the whole collection. The reliance on a first stage ranker creates a dual problem: First, the interaction and combination effects are not well understood. Second, the first stage ranker serves as a “gate-keeper” or filter, effectively blocking the potential of neural models to uncover new relevant documents. In this work, we propose a standalone neural ranking model (SNRM) by introducing a sparsity property to learn a latent sparse representation for each query and document. This representation captures the semantic relationship between the query and documents, but is also sparse enough to enable constructing an inverted index for the whole collection. We parameterize the sparsity of the model to yield a retrieval model as efficient as conventional term based models. Our model gains in efficiency without loss of effectiveness: it not only outperforms the existing term matching baselines, but also performs similarly to the recent re-ranking based neural models with dense representations. Our model can also take advantage of pseudo-relevance feedback for further improvements. More generally, our results demonstrate the importance of sparsity in neuralIR models and show that dense representations can be pruned effectively, giving new insights about essential semantic features and their distributions. |
| Tasks | Ad-Hoc Information Retrieval, Information Retrieval |
| Published | 2018-10-22 |
| URL | https://dl.acm.org/citation.cfm?id=3271800 |
| https://ciir-publications.cs.umass.edu/getpdf.php?id=1302 | |
| PWC | https://paperswithcode.com/paper/from-neural-re-ranking-to-neural-ranking |
| Repo | https://github.com/hamed-zamani/snrm |
| Framework | tf |
Cross-lingual Knowledge Projection Using Machine Translation and Target-side Knowledge Base Completion
| Title | Cross-lingual Knowledge Projection Using Machine Translation and Target-side Knowledge Base Completion |
| Authors | Naoki Otani, Hirokazu Kiyomaru, Daisuke Kawahara, Sadao Kurohashi |
| Abstract | Considerable effort has been devoted to building commonsense knowledge bases. However, they are not available in many languages because the construction of KBs is expensive. To bridge the gap between languages, this paper addresses the problem of projecting the knowledge in English, a resource-rich language, into other languages, where the main challenge lies in projection ambiguity. This ambiguity is partially solved by machine translation and target-side knowledge base completion, but neither of them is adequately reliable by itself. We show their combination can project English commonsense knowledge into Japanese and Chinese with high precision. Our method also achieves a top-10 accuracy of 90{%} on the crowdsourced English{–}Japanese benchmark. Furthermore, we use our method to obtain 18,747 facts of accurate Japanese commonsense within a very short period. |
| Tasks | Knowledge Base Completion, Machine Translation |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1128/ |
| https://www.aclweb.org/anthology/C18-1128 | |
| PWC | https://paperswithcode.com/paper/cross-lingual-knowledge-projection-using |
| Repo | https://github.com/notani/CLKP-MTKBC |
| Framework | none |
Learning to Parse Wireframes in Images of Man-Made Environments
| Title | Learning to Parse Wireframes in Images of Man-Made Environments |
| Authors | Kun Huang, Yifan Wang, Zihan Zhou, Tianjiao Ding, Shenghua Gao, Yi Ma |
| Abstract | In this paper, we propose a learning-based approach to the task of automatically extracting a “wireframe” representation for images of cluttered man-made environments. The wireframe contains all salient straight lines and their junctions of the scene that encode efficiently and accurately large-scale geometry and object shapes. To this end, we have built a very large new dataset of over 5,000 images with wireframes thoroughly labelled by humans. We have proposed two convolutional neural networks that are suitable for extracting junctions and lines with large spatial support, respectively. The networks trained on our dataset have achieved significantly better performance than state-of-the-art methods for junction detection and line segment detection, respectively. We have conducted extensive experiments to evaluate quantitatively and qualitatively the wireframes obtained by our method, and have convincingly shown that effectively and efficiently parsing wireframes for images of man-made environments is a feasible goal within reach. Such wireframes could benefit many important visual tasks such as feature correspondence, 3D reconstruction, vision-based mapping, localization, and navigation. |
| Tasks | 3D Reconstruction, Line Segment Detection |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Huang_Learning_to_Parse_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Huang_Learning_to_Parse_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/learning-to-parse-wireframes-in-images-of-man |
| Repo | https://github.com/huangkuns/wireframe |
| Framework | pytorch |
ICE-BA: Incremental, Consistent and Efficient Bundle Adjustment for Visual-Inertial SLAM
| Title | ICE-BA: Incremental, Consistent and Efficient Bundle Adjustment for Visual-Inertial SLAM |
| Authors | Haomin Liu, Mingyu Chen, Guofeng Zhang, Hujun Bao, Yingze Bao |
| Abstract | Modern visual-inertial SLAM (VI-SLAM) achieves higher accuracy and robustness than pure visual SLAM, thanks to the complementariness of visual features and inertial measurements. However, jointly using visual and inertial measurements to optimize SLAM objective functions is a problem of high computational complexity. In many VI-SLAM applications, the conventional optimization solvers can only use a very limited number of recent measurements for real time pose estimation, at the cost of suboptimal localization accuracy. In this work, we renovate the numerical solver for VI-SLAM. Compared to conventional solvers, our proposal provides an exact solution with significantly higher computational efficiency. Our solver allows us to use remarkably larger number of measurements to achieve higher accuracy and robustness. Furthermore, our method resolves the global consistency problem that is unaddressed by many state-of-the-art SLAM systems: to guarantee the minimization of re-projection function and inertial constraint function during loop closure. Experiments demonstrate our novel formulation renders lower localization error and more than 10x speedup compared to alternatives. We release the source code of our implementation to benefit the community. |
| Tasks | Pose Estimation |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Liu_ICE-BA_Incremental_Consistent_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Liu_ICE-BA_Incremental_Consistent_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/ice-ba-incremental-consistent-and-efficient |
| Repo | https://github.com/baidu/ICE-BA |
| Framework | none |
Fast and Efficient Image Quality Enhancement via Desubpixel Convolutional Neural Networks
| Title | Fast and Efficient Image Quality Enhancement via Desubpixel Convolutional Neural Networks |
| Authors | Thang Vu, Cao V. Nguyen, Trung X. Pham, Tung M. Luu, Chang D. Yoo |
| Abstract | This paper considers a convolutional neural network for image quality enhancement referred to as the fast and efficient quality enhancement (FEQE) that can be trained for either image super-resolution or image enhancement to provide accurate yet visually pleasing images on mobile devices by addressing the following three main issues. First, the considered FEQE performs majority of its computation in a lowresolution space. Second, the number of channels used in the convolutional layers is small which allows FEQE to be very deep. Third, the FEQE performs downsampling referred to as desubpixel that does not lead to loss of information. Experimental results on a number of standard benchmark datasets show significant improvements in image fidelity and reduction in processing time of the proposed FEQE compared to the recent state-of-the-art methods. In the PIRM 2018 challenge, the proposed FEQE placed first on the image super-resolution task for mobile devices. |
| Tasks | Image Enhancement, Image Super-Resolution, Super-Resolution |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCVW_2018/papers/11133/Vu_Fast_and_Efficient_Image_Quality_Enhancement_via_Desubpixel_Convolutional_Neural_ECCVW_2018_paper.pdf |
| http://openaccess.thecvf.com/content_ECCVW_2018/papers/11133/Vu_Fast_and_Efficient_Image_Quality_Enhancement_via_Desubpixel_Convolutional_Neural_ECCVW_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/fast-and-efficient-image-quality-enhancement |
| Repo | https://github.com/thangvubk/FEQE |
| Framework | tf |
Start, Follow, Read: End-to-End Full-Page Handwriting Recognition
| Title | Start, Follow, Read: End-to-End Full-Page Handwriting Recognition |
| Authors | Curtis Wigington, Chris Tensmeyer, Brian Davis, William Barrett, Brian Price, Scott Cohen |
| Abstract | Despite decades of research, offline handwriting recognition (HWR) of degraded historical documents remains a challenging problem, which if solved could greatly improve the searchability of online cultural heritage archives. HWR models are often limited by the accuracy of the preceding steps of text detection and segmentation. Motivated by this, we present a deep learning model that jointly learns text detection, segmentation, and recognition using mostly images without detection or segmentation annotations. Our Start, Follow, Read (SFR) model is composed of a Region Proposal Network to find the start position of text lines, a novel line follower network that incrementally follows and preprocesses lines of (perhaps curved) text into dewarped images suitable for recognition by a CNN-LSTM network. SFR exceeds the performance of the winner of the ICDAR2017 handwriting recognition competition, even when not using the provided competition region annotations. |
| Tasks | |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Curtis_Wigington_Start_Follow_Read_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Curtis_Wigington_Start_Follow_Read_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/start-follow-read-end-to-end-full-page |
| Repo | https://github.com/cwig/start_follow_read |
| Framework | pytorch |
SS-LSTM: A Hierarchical LSTM Model for Pedestrian Trajectory Prediction
| Title | SS-LSTM: A Hierarchical LSTM Model for Pedestrian Trajectory Prediction |
| Authors | Hao Xue Du Q. Huynh Mark Reynolds |
| Abstract | Pedestrian trajectory prediction is an extremely challenging problem because of the crowdedness and clutter of the scenes. Previous deep learning LSTM-based approaches focus on the neighbourhood influence of pedestrians but ignore the scene layouts in pedestrian trajectory prediction. In this paper, a novel hierarchical LSTM-based network is proposed to consider both the influence of social neighbourhood and scene layouts. Our SS-LSTM, which stands for Social-Scene-LSTM, uses three different LSTMs to capture person, social and scene scale information. We also use a circular shape neighbourhood setting instead of the traditional rectangular shape neighbourhood in the social scale. We evaluate our proposed method against two baseline methods and a state-of-art technique on three public datasets. The results show that our method outperforms other methods and that using circular shape neighbourhood improves the prediction accuracy |
| Tasks | Trajectory Prediction |
| Published | 2018-03-12 |
| URL | https://ieeexplore.ieee.org/document/8354239 |
| https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8354239 | |
| PWC | https://paperswithcode.com/paper/ss-lstm-a-hierarchical-lstm-model-for |
| Repo | https://github.com/xuehaouwa/SS-LSTM |
| Framework | none |
DEDUCE: A pattern matching method for automatic de-identification of Dutch medical text
| Title | DEDUCE: A pattern matching method for automatic de-identification of Dutch medical text |
| Authors | Vincent Menger, Floor Scheepers, Lisette Maria van Wijk, Marco Spruit |
| Abstract | In order to use medical text for research purposes, it is necessary to de-identify the text for legal and privacy reasons. We report on a pattern matching method to automatically de-identify medical text written in Dutch, which requires a low amount of effort to be hand tailored. First, a selection of Protected Health Information (PHI) categories is determined in cooperation with medical staff. Then, we devise a method for de-identifying all information in one of these PHI categories, that relies on lookup tables, decision rules and fuzzy string matching. Our de-identification method DEDUCE is validated on a test corpus of 200 nursing notes and 200 treatment plans obtained from the University Medical Center Utrecht (UMCU) in the Netherlands, achieving a total micro-averaged precision of 0.814, a recall of 0.916 and a F1-score of 0.862. For person names, a recall of 0.964 was achieved, while no names of patients were missed. |
| Tasks | |
| Published | 2018-07-01 |
| URL | https://www.sciencedirect.com/science/article/pii/S0736585316307365 |
| https://www.sciencedirect.com/science/article/pii/S0736585316307365 | |
| PWC | https://paperswithcode.com/paper/deduce-a-pattern-matching-method-for |
| Repo | https://github.com/vmenger/deduce |
| Framework | none |
On the Information Bottleneck Theory of Deep Learning
| Title | On the Information Bottleneck Theory of Deep Learning |
| Authors | Andrew Michael Saxe, Yamini Bansal, Joel Dapello, Madhu Advani, Artemy Kolchinsky, Brendan Daniel Tracey, David Daniel Cox |
| Abstract | The practical successes of deep neural networks have not been matched by theoretical progress that satisfyingly explains their behavior. In this work, we study the information bottleneck (IB) theory of deep learning, which makes three specific claims: first, that deep networks undergo two distinct phases consisting of an initial fitting phase and a subsequent compression phase; second, that the compression phase is causally related to the excellent generalization performance of deep networks; and third, that the compression phase occurs due to the diffusion-like behavior of stochastic gradient descent. Here we show that none of these claims hold true in the general case. Through a combination of analytical results and simulation, we demonstrate that the information plane trajectory is predominantly a function of the neural nonlinearity employed: double-sided saturating nonlinearities like tanh yield a compression phase as neural activations enter the saturation regime, but linear activation functions and single-sided saturating nonlinearities like the widely used ReLU in fact do not. Moreover, we find that there is no evident causal connection between compression and generalization: networks that do not compress are still capable of generalization, and vice versa. Next, we show that the compression phase, when it exists, does not arise from stochasticity in training by demonstrating that we can replicate the IB findings using full batch gradient descent rather than stochastic gradient descent. Finally, we show that when an input domain consists of a subset of task-relevant and task-irrelevant information, hidden representations do compress the task-irrelevant information, although the overall information about the input may monotonically increase with training time, and that this compression happens concurrently with the fitting process rather than during a subsequent compression period. |
| Tasks | |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=ry_WPG-A- |
| https://openreview.net/pdf?id=ry_WPG-A- | |
| PWC | https://paperswithcode.com/paper/on-the-information-bottleneck-theory-of-deep |
| Repo | https://github.com/artemyk/ibsgd |
| Framework | none |
Batch Bayesian Optimization via Multi-objective Acquisition Ensemble for Automated Analog Circuit Design
| Title | Batch Bayesian Optimization via Multi-objective Acquisition Ensemble for Automated Analog Circuit Design |
| Authors | Wenlong Lyu, Fan Yang, Changhao Yan, Dian Zhou, Xuan Zeng |
| Abstract | Bayesian optimization methods are promising for the optimization of black-box functions that are expensive to evaluate. In this paper, a novel batch Bayesian optimization approach is proposed. The parallelization is realized via a multi-objective ensemble of multiple acquisition functions. In each iteration, the multi-objective optimization of the multiple acquisition functions is performed to search for the Pareto front of the acquisition functions. The batch of inputs are then selected from the Pareto front. The Pareto front represents the best trade-off between the multiple acquisition functions. Such a policy for batch Bayesian optimization can significantly improve the efficiency of optimization. The proposed method is compared with several state-of-the-art batch Bayesian optimization algorithms using analytical benchmark functions and real-world analog integrated circuits. The experimental results show that the proposed method is competitive compared with the state-of-the-art algorithms. |
| Tasks | |
| Published | 2018-07-01 |
| URL | https://icml.cc/Conferences/2018/Schedule?showEvent=1919 |
| http://proceedings.mlr.press/v80/lyu18a/lyu18a.pdf | |
| PWC | https://paperswithcode.com/paper/batch-bayesian-optimization-via-multi |
| Repo | https://github.com/Alaya-in-Matrix/MACE |
| Framework | none |
