Paper Group NANR 14
A Blind Watermarking Method for CityGML. Learning long-range spatial dependencies with horizontal gated recurrent units. Attentive Gated Lexicon Reader with Contrastive Contextual Co-Attention for Sentiment Classification. Multi-layer Annotation of the Rigveda. Multi-Dialect Arabic POS Tagging: A CRF Approach. Bf3R at SemEval-2018 Task 7: Evaluatin …
A Blind Watermarking Method for CityGML
| Title | A Blind Watermarking Method for CityGML |
| Authors | Dayou, Jiang; Jongweon, Kim |
| Abstract | We propose a blind watermarking method for CityGML in this paper. Firstly, we parse the CityGML text file and select the virtual 3D city model for watermarking. Secondly, we transform the model by using geometric invariance. Then, we transform the Cartesian coordinate to the Spherical coordinate to obtain the sphere radii of each vertex. Finally, we insert the watermark by altering the DCT coefficients of the sphere radii segment. We conduct several experiments using different parameters to explore the watermark payload. The method can embed 64 bits watermark into a CityGML model. In addition, it shows good robustness against adding noise, rotation, uniform scaling, translation, and vertices reordering attacks. However, it still has drawbacks under cropping and simplification attacks. |
| Tasks | |
| Published | 2018-07-20 |
| URL | https://www.mendeley.com/catalogue/blind-watermarking-method-citygml/ |
| http://www.iadisportal.org/digital-library/a-blind-watermarking-method-for-citygml | |
| PWC | https://paperswithcode.com/paper/a-blind-watermarking-method-for-citygml |
| Repo | |
| Framework | |
Learning long-range spatial dependencies with horizontal gated recurrent units
| Title | Learning long-range spatial dependencies with horizontal gated recurrent units |
| Authors | Drew Linsley, Junkyung Kim, Vijay Veerabadran, Charles Windolf, Thomas Serre |
| Abstract | Progress in deep learning has spawned great successes in many engineering applications. As a prime example, convolutional neural networks, a type of feedforward neural networks, are now approaching – and sometimes even surpassing – human accuracy on a variety of visual recognition tasks. Here, however, we show that these neural networks and their recent extensions struggle in recognition tasks where co-dependent visual features must be detected over long spatial ranges. We introduce a visual challenge, Pathfinder, and describe a novel recurrent neural network architecture called the horizontal gated recurrent unit (hGRU) to learn intrinsic horizontal connections – both within and across feature columns. We demonstrate that a single hGRU layer matches or outperforms all tested feedforward hierarchical baselines including state-of-the-art architectures with orders of magnitude more parameters. |
| Tasks | |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7300-learning-long-range-spatial-dependencies-with-horizontal-gated-recurrent-units |
| http://papers.nips.cc/paper/7300-learning-long-range-spatial-dependencies-with-horizontal-gated-recurrent-units.pdf | |
| PWC | https://paperswithcode.com/paper/learning-long-range-spatial-dependencies-with |
| Repo | |
| Framework | |
Attentive Gated Lexicon Reader with Contrastive Contextual Co-Attention for Sentiment Classification
| Title | Attentive Gated Lexicon Reader with Contrastive Contextual Co-Attention for Sentiment Classification |
| Authors | Yi Tay, Anh Tuan Luu, Siu Cheung Hui, Jian Su |
| Abstract | This paper proposes a new neural architecture that exploits readily available sentiment lexicon resources. The key idea is that that incorporating a word-level prior can aid in the representation learning process, eventually improving model performance. To this end, our model employs two distinctly unique components, i.e., (1) we introduce a lexicon-driven contextual attention mechanism to imbue lexicon words with long-range contextual information and (2), we introduce a contrastive co-attention mechanism that models contrasting polarities between all positive and negative words in a sentence. Via extensive experiments, we show that our approach outperforms many other neural baselines on sentiment classification tasks on multiple benchmark datasets. |
| Tasks | Opinion Mining, Representation Learning, Sentiment Analysis |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1381/ |
| https://www.aclweb.org/anthology/D18-1381 | |
| PWC | https://paperswithcode.com/paper/attentive-gated-lexicon-reader-with |
| Repo | |
| Framework | |
Multi-layer Annotation of the Rigveda
| Title | Multi-layer Annotation of the Rigveda |
| Authors | Oliver Hellwig, Heinrich Hettrich, Ashutosh Modi, Manfred Pinkal |
| Abstract | |
| Tasks | Domain Adaptation |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1011/ |
| https://www.aclweb.org/anthology/L18-1011 | |
| PWC | https://paperswithcode.com/paper/multi-layer-annotation-of-the-rigveda |
| Repo | |
| Framework | |
Multi-Dialect Arabic POS Tagging: A CRF Approach
| Title | Multi-Dialect Arabic POS Tagging: A CRF Approach |
| Authors | Kareem Darwish, Hamdy Mubarak, Ahmed Abdelali, Mohamed Eldesouki, Younes Samih, R Alharbi, ah, Mohammed Attia, Walid Magdy, Laura Kallmeyer |
| Abstract | |
| Tasks | Machine Translation, Part-Of-Speech Tagging |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1015/ |
| https://www.aclweb.org/anthology/L18-1015 | |
| PWC | https://paperswithcode.com/paper/multi-dialect-arabic-pos-tagging-a-crf |
| Repo | |
| Framework | |
Bf3R at SemEval-2018 Task 7: Evaluating Two Relation Extraction Tools for Finding Semantic Relations in Biomedical Abstracts
| Title | Bf3R at SemEval-2018 Task 7: Evaluating Two Relation Extraction Tools for Finding Semantic Relations in Biomedical Abstracts |
| Authors | Mariana Neves, Daniel Butzke, Gilbert Sch{"o}nfelder, Barbara Grune |
| Abstract | Automatic extraction of semantic relations from text can support finding relevant information from scientific publications. We describe our participation in Task 7 of SemEval-2018 for which we experimented with two relations extraction tools - jSRE and TEES - for the extraction and classification of six relation types. The results we obtained with TEES were significantly superior than those with jSRE (33.4{%} vs. 30.09{%} and 20.3{%} vs. 16{%}). Additionally, we utilized the model trained with TEES for extracting semantic relations from biomedical abstracts, for which we present a preliminary evaluation. |
| Tasks | Information Retrieval, Relation Extraction |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/S18-1130/ |
| https://www.aclweb.org/anthology/S18-1130 | |
| PWC | https://paperswithcode.com/paper/bf3r-at-semeval-2018-task-7-evaluating-two |
| Repo | |
| Framework | |
Real-Time Monocular Depth Estimation Using Synthetic Data With Domain Adaptation via Image Style Transfer
| Title | Real-Time Monocular Depth Estimation Using Synthetic Data With Domain Adaptation via Image Style Transfer |
| Authors | Amir Atapour-Abarghouei, Toby P. Breckon |
| Abstract | Monocular depth estimation using learning-based approaches has become promising in recent years. However, most monocular depth estimators either need to rely on large quantities of ground truth depth data, which is extremely expensive and difficult to obtain, or predict disparity as an intermediary step using a secondary supervisory signal leading to blurring and other artefacts. Training a depth estimation model using pixel-perfect synthetic data can resolve most of these issues but introduces the problem of domain bias. This is the inability to apply a model trained on synthetic data to real-world scenarios. With advances in image style transfer and its connections with domain adaptation (Maximum Mean Discrepancy), we take advantage of style transfer and adversarial training to predict pixel perfect depth from a single real-world color image based on training over a large corpus of synthetic environment data. Experimental results indicate the efficacy of our approach compared to contemporary state-of-the-art techniques. |
| Tasks | Depth Estimation, Domain Adaptation, Monocular Depth Estimation, Style Transfer |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Atapour-Abarghouei_Real-Time_Monocular_Depth_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Atapour-Abarghouei_Real-Time_Monocular_Depth_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/real-time-monocular-depth-estimation-using |
| Repo | |
| Framework | |
Beauty-in-averageness and its contextual modulations: A Bayesian statistical account
| Title | Beauty-in-averageness and its contextual modulations: A Bayesian statistical account |
| Authors | Chaitanya Ryali, Angela J. Yu |
| Abstract | Understanding how humans perceive the likability of high-dimensional objects'' such as faces is an important problem in both cognitive science and AI/ML. Existing models generally assume these preferences to be fixed. However, psychologists have found human assessment of facial attractiveness to be context-dependent. Specifically, the classical Beauty-in-Averageness (BiA) effect, whereby a blended face is judged to be more attractive than the originals, is significantly diminished or reversed when the original faces are recognizable, or when the blend is mixed-race/mixed-gender and the attractiveness judgment is preceded by a race/gender categorization, respectively. This "Ugliness-in-Averageness" (UiA) effect has previously been explained via a qualitative disfluency account, which posits that the negative affect associated with the difficult race or gender categorization is inadvertently interpreted by the brain as a dislike for the face itself. In contrast, we hypothesize that human preference for an object is increased when it incurs lower encoding cost, in particular when its perceived {\it statistical typicality} is high, in consonance with Barlow's seminal efficient coding hypothesis.’’ This statistical coding cost account explains both BiA, where facial blends generally have higher likelihood than ``parent faces’', and UiA, when the preceding context or task restricts face representation to a task-relevant subset of features, thus redefining statistical typicality and encoding cost within that subspace. We use simulations to show that our model provides a parsimonious, statistically grounded, and quantitative account of both BiA and UiA. We validate our model using experimental data from a gender categorization task. We also propose a novel experiment, based on model predictions, that will be able to arbitrate between the disfluency account and our statistical coding cost account of attractiveness. | |
| Tasks | |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7663-beauty-in-averageness-and-its-contextual-modulations-a-bayesian-statistical-account |
| http://papers.nips.cc/paper/7663-beauty-in-averageness-and-its-contextual-modulations-a-bayesian-statistical-account.pdf | |
| PWC | https://paperswithcode.com/paper/beauty-in-averageness-and-its-contextual |
| Repo | |
| Framework | |
Effective Use of Context in Noisy Entity Linking
| Title | Effective Use of Context in Noisy Entity Linking |
| Authors | David Mueller, Greg Durrett |
| Abstract | To disambiguate between closely related concepts, entity linking systems need to effectively distill cues from their context, which may be quite noisy. We investigate several techniques for using these cues in the context of noisy entity linking on short texts. Our starting point is a state-of-the-art attention-based model from prior work; while this model{'}s attention typically identifies context that is topically relevant, it fails to identify some of the most indicative surface strings, especially those exhibiting lexical overlap with the true title. Augmenting the model with convolutional networks over characters still leaves it largely unable to pick up on these cues compared to sparse features that target them directly, indicating that automatically learning how to identify relevant character-level context features is a hard problem. Our final system outperforms past work on the WikilinksNED test set by 2.8{%} absolute. |
| Tasks | Entity Linking |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1126/ |
| https://www.aclweb.org/anthology/D18-1126 | |
| PWC | https://paperswithcode.com/paper/effective-use-of-context-in-noisy-entity |
| Repo | |
| Framework | |
Unfolding the External Behavior and Inner Affective State of Teammates through Ensemble Learning: Experimental Evidence from a Dyadic Team Corpus
| Title | Unfolding the External Behavior and Inner Affective State of Teammates through Ensemble Learning: Experimental Evidence from a Dyadic Team Corpus |
| Authors | Aggeliki Vlachostergiou, Mark Dennison, Catherine Neubauer, Stefan Scherer, Peter Khooshabeh, Andre Harrison |
| Abstract | |
| Tasks | |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1029/ |
| https://www.aclweb.org/anthology/L18-1029 | |
| PWC | https://paperswithcode.com/paper/unfolding-the-external-behavior-and-inner |
| Repo | |
| Framework | |
A Deep Relevance Model for Zero-Shot Document Filtering
| Title | A Deep Relevance Model for Zero-Shot Document Filtering |
| Authors | Chenliang Li, Wei Zhou, Feng Ji, Yu Duan, Haiqing Chen |
| Abstract | In the era of big data, focused analysis for diverse topics with a short response time becomes an urgent demand. As a fundamental task, information filtering therefore becomes a critical necessity. In this paper, we propose a novel deep relevance model for zero-shot document filtering, named DAZER. DAZER estimates the relevance between a document and a category by taking a small set of seed words relevant to the category. With pre-trained word embeddings from a large external corpus, DAZER is devised to extract the relevance signals by modeling the hidden feature interactions in the word embedding space. The relevance signals are extracted through a gated convolutional process. The gate mechanism controls which convolution filters output the relevance signals in a category dependent manner. Experiments on two document collections of two different tasks (i.e., topic categorization and sentiment analysis) demonstrate that DAZER significantly outperforms the existing alternative solutions, including the state-of-the-art deep relevance ranking models. |
| Tasks | Sentiment Analysis, Text Classification, Word Embeddings |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/P18-1214/ |
| https://www.aclweb.org/anthology/P18-1214 | |
| PWC | https://paperswithcode.com/paper/a-deep-relevance-model-for-zero-shot-document |
| Repo | |
| Framework | |
Understanding Emotions: A Dataset of Tweets to Study Interactions between Affect Categories
| Title | Understanding Emotions: A Dataset of Tweets to Study Interactions between Affect Categories |
| Authors | Saif Mohammad, Svetlana Kiritchenko |
| Abstract | |
| Tasks | Emotion Classification, Emotion Recognition, Sentiment Analysis |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1030/ |
| https://www.aclweb.org/anthology/L18-1030 | |
| PWC | https://paperswithcode.com/paper/understanding-emotions-a-dataset-of-tweets-to |
| Repo | |
| Framework | |
Beyond Grids: Learning Graph Representations for Visual Recognition
| Title | Beyond Grids: Learning Graph Representations for Visual Recognition |
| Authors | Yin Li, Abhinav Gupta |
| Abstract | We propose learning graph representations from 2D feature maps for visual recognition. Our method draws inspiration from region based recognition, and learns to transform a 2D image into a graph structure. The vertices of the graph define clusters of pixels (“regions”), and the edges measure the similarity between these clusters in a feature space. Our method further learns to propagate information across all vertices on the graph, and is able to project the learned graph representation back into 2D grids. Our graph representation facilitates reasoning beyond regular grids and can capture long range dependencies among regions. We demonstrate that our model can be trained from end-to-end, and is easily integrated into existing networks. Finally, we evaluate our method on three challenging recognition tasks: semantic segmentation, object detection and object instance segmentation. For all tasks, our method outperforms state-of-the-art methods. |
| Tasks | Instance Segmentation, Object Detection, Semantic Segmentation |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/8135-beyond-grids-learning-graph-representations-for-visual-recognition |
| http://papers.nips.cc/paper/8135-beyond-grids-learning-graph-representations-for-visual-recognition.pdf | |
| PWC | https://paperswithcode.com/paper/beyond-grids-learning-graph-representations |
| Repo | |
| Framework | |
RESOUND: Towards Action Recognition without Representation Bias
| Title | RESOUND: Towards Action Recognition without Representation Bias |
| Authors | Yingwei Li, Yi Li, Nuno Vasconcelos |
| Abstract | While large datasets have proven to be a key enabler for progress in computer vision, they can have biases that lead to erroneous conclusions. The notion of the representation bias of a dataset is proposed to combat this problem. It captures the fact that representations other than the ground-truth representation can achieve good performance on any given dataset. When this is the case, the dataset is said not to be well calibrated. Dataset calibration is shown to be a necessary condition for the standard state-of-the-art evaluation practice to converge to the ground-truth representation. A procedure, RESOUND, is proposed to quantify and minimize representation bias. Its application to the problem of action recognition shows that current datasets are biased towards static representations (objects, scenes and people). Two versions of RESOUND are studied. An Explicit RESOUND procedure is proposed to assemble new datasets by sampling existing datasets. An implicit RESOUND procedure is used to guide the creation of a new dataset, Diving48, of over 18,000 video clips of competitive diving actions, spanning 48 ï¬ne-grained dive classes. Experimental evaluation conï¬rms the eï¬ectiveness of RESOUND to reduce the static biases of current datasets. |
| Tasks | Calibration, Temporal Action Localization |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Yingwei_Li_RESOUND_Towards_Action_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Yingwei_Li_RESOUND_Towards_Action_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/resound-towards-action-recognition-without |
| Repo | |
| Framework | |
Recurrent Auto-Encoder Model for Multidimensional Time Series Representation
| Title | Recurrent Auto-Encoder Model for Multidimensional Time Series Representation |
| Authors | Timothy Wong, Zhiyuan Luo |
| Abstract | Recurrent auto-encoder model can summarise sequential data through an encoder structure into a fixed-length vector and then reconstruct into its original sequential form through the decoder structure. The summarised information can be used to represent time series features. In this paper, we propose relaxing the dimensionality of the decoder output so that it performs partial reconstruction. The fixed-length vector can therefore represent features only in the selected dimensions. In addition, we propose using rolling fixed window approach to generate samples. The change of time series features over time can be summarised as a smooth trajectory path. The fixed-length vectors are further analysed through additional visualisation and unsupervised clustering techniques. This proposed method can be applied in large-scale industrial processes for sensors signal analysis purpose where clusters of the vector representations can be used to reflect the operating states of selected aspects of the industrial system. |
| Tasks | Time Series |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=r1cLblgCZ |
| https://openreview.net/pdf?id=r1cLblgCZ | |
| PWC | https://paperswithcode.com/paper/recurrent-auto-encoder-model-for |
| Repo | |
| Framework | |
