Paper Group NANR 221
Image Collection Pop-Up: 3D Reconstruction and Clustering of Rigid and Non-Rigid Categories. German Radio Interviews: The GRAIN Release of the SFB732 Silver Standard Collection. SobolevFusion: 3D Reconstruction of Scenes Undergoing Free Non-Rigid Motion. Operation-guided Neural Networks for High Fidelity Data-To-Text Generation. Multistage Adversar …
Image Collection Pop-Up: 3D Reconstruction and Clustering of Rigid and Non-Rigid Categories
| Title | Image Collection Pop-Up: 3D Reconstruction and Clustering of Rigid and Non-Rigid Categories |
| Authors | Antonio Agudo, Melcior Pijoan, Francesc Moreno-Noguer |
| Abstract | This paper introduces an approach to simultaneously estimate 3D shape, camera pose, and object and type of deformation clustering, from partial 2D annotations in a multi-instance collection of images. Furthermore, we can indistinctly process rigid and non-rigid categories. This advances existing work, which only addresses the problem for one single object or, if multiple objects are considered, they are assumed to be clustered a priori. To handle this broader version of the problem, we model object deformation using a formulation based on multiple unions of subspaces, able to span from small rigid motion to complex deformations. The parameters of this model are learned via Augmented Lagrange Multipliers, in a completely unsupervised manner that does not require any training data at all. Extensive validation is provided in a wide variety of synthetic and real scenarios, including rigid and non-rigid categories with small and large deformations. In all cases our approach outperforms state-of-the-art in terms of 3D reconstruction accuracy, while also providing clustering results that allow segmenting the images into object instances and their associated type of deformation (or action the object is performing). |
| Tasks | 3D Reconstruction |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Agudo_Image_Collection_Pop-Up_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Agudo_Image_Collection_Pop-Up_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/image-collection-pop-up-3d-reconstruction-and |
| Repo | |
| Framework | |
German Radio Interviews: The GRAIN Release of the SFB732 Silver Standard Collection
| Title | German Radio Interviews: The GRAIN Release of the SFB732 Silver Standard Collection |
| Authors | Katrin Schweitzer, Kerstin Eckart, Markus G{"a}rtner, Agnieszka Falenska, Arndt Riester, Ina R{"o}siger, Antje Schweitzer, Sabrina Stehwien, Jonas Kuhn |
| Abstract | |
| Tasks | |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1457/ |
| https://www.aclweb.org/anthology/L18-1457 | |
| PWC | https://paperswithcode.com/paper/german-radio-interviews-the-grain-release-of |
| Repo | |
| Framework | |
SobolevFusion: 3D Reconstruction of Scenes Undergoing Free Non-Rigid Motion
| Title | SobolevFusion: 3D Reconstruction of Scenes Undergoing Free Non-Rigid Motion |
| Authors | Miroslava Slavcheva, Maximilian Baust, Slobodan Ilic |
| Abstract | We present a system that builds 3D models of non-rigidly moving surfaces from scratch in real time using a single RGB-D stream. Our solution is based on the variational level set method, thus it copes with arbitrary geometry, including topological changes. It warps a given truncated signed distance field (TSDF) to a target TSDF via gradient flow. Unlike previous approaches that define the gradient using an L2 inner product, our method relies on gradient flow in Sobolev space. Its favourable regularity properties allow for a more straightforward energy formulation that is faster to compute and that achieves higher geometric detail, mitigating the over-smoothing effects introduced by other regularization schemes. In addition, the coarse-to-fine evolution behaviour of the flow is able to handle larger motions, making few frames sufficient for a high-fidelity reconstruction. Last but not least, our pipeline determines voxel correspondences between partial shapes by matching signatures in a low-dimensional embedding of their Laplacian eigenfunctions, and is thus able to reliably colour the output model. A variety of quantitative and qualitative evaluations demonstrate the advantages of our technique. |
| Tasks | 3D Reconstruction |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Slavcheva_SobolevFusion_3D_Reconstruction_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Slavcheva_SobolevFusion_3D_Reconstruction_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/sobolevfusion-3d-reconstruction-of-scenes |
| Repo | |
| Framework | |
Operation-guided Neural Networks for High Fidelity Data-To-Text Generation
| Title | Operation-guided Neural Networks for High Fidelity Data-To-Text Generation |
| Authors | Feng Nie, Jinpeng Wang, Jin-Ge Yao, Rong Pan, Chin-Yew Lin |
| Abstract | Recent neural models for data-to-text generation are mostly based on data-driven end-to-end training over encoder-decoder networks. Even though the generated texts are mostly fluent and informative, they often generate descriptions that are not consistent with the input structured data. This is a critical issue especially in domains that require inference or calculations over raw data. In this paper, we attempt to improve the fidelity of neural data-to-text generation by utilizing pre-executed symbolic operations. We propose a framework called Operation-guided Attention-based sequence-to-sequence network (OpAtt), with a specifically designed gating mechanism as well as a quantization module for operation results to utilize information from pre-executed operations. Experiments on two sports datasets show our proposed method clearly improves the fidelity of the generated texts to the input structured data. |
| Tasks | Data-to-Text Generation, Quantization, Text Generation |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1422/ |
| https://www.aclweb.org/anthology/D18-1422 | |
| PWC | https://paperswithcode.com/paper/operation-guided-neural-networks-for-high |
| Repo | |
| Framework | |
Multistage Adversarial Losses for Pose-Based Human Image Synthesis
| Title | Multistage Adversarial Losses for Pose-Based Human Image Synthesis |
| Authors | Chenyang Si, Wei Wang, Liang Wang, Tieniu Tan |
| Abstract | Human image synthesis has extensive practical applications e.g. person re-identification and data augmentation for human pose estimation. However, it is much more challenging than rigid object synthesis, e.g. cars and chairs, due to the variability of human posture. In this paper, we propose a pose-based human image synthesis method which can keep the human posture unchanged in novel viewpoints. Furthermore, we adopt multistage adversarial losses separately for the foreground and background generation, which fully exploits the multi-modal characteristics of generative loss to generate more realistic looking images. We perform extensive experiments on the Human3.6M dataset and verify the effectiveness of each stage of our method. The generated human images not only keep the same pose as the input image, but also have clear detailed foreground and background. The quantitative comparison results illustrate that our approach achieves much better results than several state-of-the-art methods. |
| Tasks | Data Augmentation, Image Generation, Person Re-Identification, Pose Estimation |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Si_Multistage_Adversarial_Losses_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Si_Multistage_Adversarial_Losses_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/multistage-adversarial-losses-for-pose-based |
| Repo | |
| Framework | |
Feature Engineering for Second Language Acquisition Modeling
| Title | Feature Engineering for Second Language Acquisition Modeling |
| Authors | Guanliang Chen, Claudia Hauff, Geert-Jan Houben |
| Abstract | Knowledge tracing serves as a keystone in delivering personalized education. However, few works attempted to model students{'} knowledge state in the setting of Second Language Acquisition. The Duolingo Shared Task on Second Language Acquisition Modeling provides students{'} trace data that we extensively analyze and engineer features from for the task of predicting whether a student will correctly solve a vocabulary exercise. Our analyses of students{'} learning traces reveal that factors like exercise format and engagement impact their exercise performance to a large extent. Overall, we extracted 23 different features as input to a Gradient Tree Boosting framework, which resulted in an AUC score of between 0.80 and 0.82 on the official test set. |
| Tasks | Feature Engineering, Knowledge Tracing, Language Acquisition |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/W18-0543/ |
| https://www.aclweb.org/anthology/W18-0543 | |
| PWC | https://paperswithcode.com/paper/feature-engineering-for-second-language |
| Repo | |
| Framework | |
When Simple n-gram Models Outperform Syntactic Approaches: Discriminating between Dutch and Flemish
| Title | When Simple n-gram Models Outperform Syntactic Approaches: Discriminating between Dutch and Flemish |
| Authors | Martin Kroon, Masha Medvedeva, Barbara Plank |
| Abstract | In this paper we present the results of our participation in the Discriminating between Dutch and Flemish in Subtitles VarDial 2018 shared task. We try techniques proven to work well for discriminating between language varieties as well as explore the potential of using syntactic features, i.e. hierarchical syntactic subtrees. We experiment with different combinations of features. Discriminating between these two languages turned out to be a very hard task, not only for a machine: human performance is only around 0.51 F1 score; our best system is still a simple Naive Bayes model with word unigrams and bigrams. The system achieved an F1 score (macro) of 0.62, which ranked us 4th in the shared task. |
| Tasks | |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/W18-3928/ |
| https://www.aclweb.org/anthology/W18-3928 | |
| PWC | https://paperswithcode.com/paper/when-simple-n-gram-models-outperform |
| Repo | |
| Framework | |
The Impact of Advances in Neural and Statistical MT on the Translation Workforce
| Title | The Impact of Advances in Neural and Statistical MT on the Translation Workforce |
| Authors | Jennifer DeCamp |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2018-03-01 |
| URL | https://www.aclweb.org/anthology/W18-1918/ |
| https://www.aclweb.org/anthology/W18-1918 | |
| PWC | https://paperswithcode.com/paper/the-impact-of-advances-in-neural-and |
| Repo | |
| Framework | |
Learning Optimal Reserve Price against Non-myopic Bidders
| Title | Learning Optimal Reserve Price against Non-myopic Bidders |
| Authors | Jinyan Liu, Zhiyi Huang, Xiangning Wang |
| Abstract | We consider the problem of learning optimal reserve price in repeated auctions against non-myopic bidders, who may bid strategically in order to gain in future rounds even if the single-round auctions are truthful. Previous algorithms, e.g., empirical pricing, do not provide non-trivial regret rounds in this setting in general. We introduce algorithms that obtain small regret against non-myopic bidders either when the market is large, i.e., no bidder appears in a constant fraction of the rounds, or when the bidders are impatient, i.e., they discount future utility by some factor mildly bounded away from one. Our approach carefully controls what information is revealed to each bidder, and builds on techniques from differentially private online learning as well as the recent line of works on jointly differentially private algorithms. |
| Tasks | |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7474-learning-optimal-reserve-price-against-non-myopic-bidders |
| http://papers.nips.cc/paper/7474-learning-optimal-reserve-price-against-non-myopic-bidders.pdf | |
| PWC | https://paperswithcode.com/paper/learning-optimal-reserve-price-against-non |
| Repo | |
| Framework | |
是非題之支持證據檢索 (Supporting Evidence Retrieval for Answering Yes/No Questions) [In Chinese]
| Title | 是非題之支持證據檢索 (Supporting Evidence Retrieval for Answering Yes/No Questions) [In Chinese] |
| Authors | Meng-Tse Wu, Yi-Chung Lin, Keh-Yih Su |
| Abstract | |
| Tasks | |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/O18-1006/ |
| https://www.aclweb.org/anthology/O18-1006 | |
| PWC | https://paperswithcode.com/paper/eea1-eac-supporting-evidence-retrieval-for |
| Repo | |
| Framework | |
Generating Stories Using Role-playing Games and Simulated Human-like Conversations
| Title | Generating Stories Using Role-playing Games and Simulated Human-like Conversations |
| Authors | Alan Tapscott, Carlos Le{'o}n, Pablo Gerv{'a}s |
| Abstract | |
| Tasks | Human Dynamics, Text Generation |
| Published | 2018-11-01 |
| URL | https://www.aclweb.org/anthology/W18-6606/ |
| https://www.aclweb.org/anthology/W18-6606 | |
| PWC | https://paperswithcode.com/paper/generating-stories-using-role-playing-games |
| Repo | |
| Framework | |
Processing MWEs: Neurocognitive Bases of Verbal MWEs and Lexical Cohesiveness within MWEs
| Title | Processing MWEs: Neurocognitive Bases of Verbal MWEs and Lexical Cohesiveness within MWEs |
| Authors | Shohini Bhattasali, Murielle Fabre, John Hale |
| Abstract | Multiword expressions have posed a challenge in the past for computational linguistics since they comprise a heterogeneous family of word clusters and are difficult to detect in natural language data. In this paper, we present a fMRI study based on language comprehension to provide neuroimaging evidence for processing MWEs. We investigate whether different MWEs have distinct neural bases, e.g. if verbal MWEs involve separate brain areas from non-verbal MWEs and if MWEs with varying levels of cohesiveness activate dissociable brain regions. Our study contributes neuroimaging evidence illustrating that different MWEs elicit spatially distinct patterns of activation. We also adapt an association measure, usually used to detect MWEs, as a cognitively plausible metric for language processing. |
| Tasks | |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/W18-4904/ |
| https://www.aclweb.org/anthology/W18-4904 | |
| PWC | https://paperswithcode.com/paper/processing-mwes-neurocognitive-bases-of |
| Repo | |
| Framework | |
Crowdsourcing Regional Variation Data and Automatic Geolocalisation of Speakers of European French
| Title | Crowdsourcing Regional Variation Data and Automatic Geolocalisation of Speakers of European French |
| Authors | Jean-Philippe Goldman, Yves Scherrer, Julie Glikman, Mathieu Avanzi, Christophe Benzitoun, Philippe Boula de Mare{"u}il |
| Abstract | |
| Tasks | |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1527/ |
| https://www.aclweb.org/anthology/L18-1527 | |
| PWC | https://paperswithcode.com/paper/crowdsourcing-regional-variation-data-and |
| Repo | |
| Framework | |
Proceedings of ACL 2018, Student Research Workshop
| Title | Proceedings of ACL 2018, Student Research Workshop |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/P18-3000/ |
| https://www.aclweb.org/anthology/P18-3000 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-acl-2018-student-research |
| Repo | |
| Framework | |
Nonparametric variable importance using an augmented neural network with multi-task learning
| Title | Nonparametric variable importance using an augmented neural network with multi-task learning |
| Authors | Jean Feng, Brian Williamson, Noah Simon, Marco Carone |
| Abstract | In predictive modeling applications, it is often of interest to determine the relative contribution of subsets of features in explaining the variability of an outcome. It is useful to consider this variable importance as a function of the unknown, underlying data-generating mechanism rather than the specific predictive algorithm used to fit the data. In this paper, we connect these ideas in nonparametric variable importance to machine learning, and provide a method for efficient estimation of variable importance when building a predictive model using a neural network. We show how a single augmented neural network with multi-task learning simultaneously estimates the importance of many feature subsets, improving on previous procedures for estimating importance. We demonstrate on simulated data that our method is both accurate and computationally efficient, and apply our method to both a study of heart disease and for predicting mortality in ICU patients. |
| Tasks | Multi-Task Learning |
| Published | 2018-07-01 |
| URL | https://icml.cc/Conferences/2018/Schedule?showEvent=2042 |
| http://proceedings.mlr.press/v80/feng18a/feng18a.pdf | |
| PWC | https://paperswithcode.com/paper/nonparametric-variable-importance-using-an |
| Repo | |
| Framework | |
