Paper Group NANR 6
Attentional ShapeContextNet for Point Cloud Recognition. Learning a Warping Distance from Unlabeled Time Series Using Sequence Autoencoders. Proceedings of the First Workshop on Trolling, Aggression and Cyberbullying (TRAC-2018). CNN for Text-Based Multiple Choice Question Answering. Free Supervision From Video Games. A closer look at the word anal …
Attentional ShapeContextNet for Point Cloud Recognition
| Title | Attentional ShapeContextNet for Point Cloud Recognition |
| Authors | Saining Xie, Sainan Liu, Zeyu Chen, Zhuowen Tu |
| Abstract | We tackle the problem of point cloud recognition. Unlike previous approaches where a point cloud is either converted into a volume/image or represented independently in a permutation-invariant set, we develop a new representation by adopting the concept of shape context as the building block in our network design. The resulting model, called ShapeContextNet, consists of a hierarchy with modules not relying on a fixed grid while still enjoying properties similar to those in convolutional neural networks — being able to capture and propagate the object part information. In addition, we find inspiration from self-attention based models to include a simple yet effective contextual modeling mechanism — making the contextual region selection, the feature aggregation, and the feature transformation process fully automatic. ShapeContextNet is an end-to-end model that can be applied to the general point cloud classification and segmentation problems. We observe competitive results on a number of benchmark datasets. |
| Tasks | |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Xie_Attentional_ShapeContextNet_for_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Xie_Attentional_ShapeContextNet_for_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/attentional-shapecontextnet-for-point-cloud |
| Repo | |
| Framework | |
Learning a Warping Distance from Unlabeled Time Series Using Sequence Autoencoders
| Title | Learning a Warping Distance from Unlabeled Time Series Using Sequence Autoencoders |
| Authors | Abubakar Abid, James Y. Zou |
| Abstract | Measuring similarities between unlabeled time series trajectories is an important problem in many domains such as medicine, economics, and vision. It is often unclear what is the appropriate metric to use because of the complex nature of noise in the trajectories (e.g. different sampling rates or outliers). Experts typically hand-craft or manually select a specific metric, such as Dynamic Time Warping (DTW), to apply on their data. In this paper, we propose an end-to-end framework, autowarp, that optimizes and learns a good metric given unlabeled trajectories. We define a flexible and differentiable family of warping metrics, which encompasses common metrics such as DTW, Edit Distance, Euclidean, etc. Autowarp then leverages the representation power of sequence autoencoders to optimize for a member of this warping family. The output is an metric which is easy to interpret and can be robustly learned from relatively few trajectories. In systematic experiments across different domains, we show that autowarp often outperforms hand-crafted trajectory similarity metrics. |
| Tasks | Time Series |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/8254-learning-a-warping-distance-from-unlabeled-time-series-using-sequence-autoencoders |
| http://papers.nips.cc/paper/8254-learning-a-warping-distance-from-unlabeled-time-series-using-sequence-autoencoders.pdf | |
| PWC | https://paperswithcode.com/paper/learning-a-warping-distance-from-unlabeled |
| Repo | |
| Framework | |
Proceedings of the First Workshop on Trolling, Aggression and Cyberbullying (TRAC-2018)
| Title | Proceedings of the First Workshop on Trolling, Aggression and Cyberbullying (TRAC-2018) |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/W18-4400/ |
| https://www.aclweb.org/anthology/W18-4400 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-first-workshop-on-trolling |
| Repo | |
| Framework | |
CNN for Text-Based Multiple Choice Question Answering
| Title | CNN for Text-Based Multiple Choice Question Answering |
| Authors | Akshay Chaturvedi, P, Onkar it, Utpal Garain |
| Abstract | The task of Question Answering is at the very core of machine comprehension. In this paper, we propose a Convolutional Neural Network (CNN) model for text-based multiple choice question answering where questions are based on a particular article. Given an article and a multiple choice question, our model assigns a score to each question-option tuple and chooses the final option accordingly. We test our model on Textbook Question Answering (TQA) and SciQ dataset. Our model outperforms several LSTM-based baseline models on the two datasets. |
| Tasks | Question Answering, Reading Comprehension, Sentiment Analysis |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/P18-2044/ |
| https://www.aclweb.org/anthology/P18-2044 | |
| PWC | https://paperswithcode.com/paper/cnn-for-text-based-multiple-choice-question |
| Repo | |
| Framework | |
Free Supervision From Video Games
| Title | Free Supervision From Video Games |
| Authors | Philipp Krähenbühl |
| Abstract | Deep networks are extremely hungry for data. They devour hundreds of thousands of labeled images to learn robust and semantically meaningful feature representations. Current networks are so data hungry that collecting labeled data has become as important as designing the networks themselves. Unfortunately, manual data collection is both expensive and time consuming. We present an alternative, and show how ground truth labels for many vision tasks are easily extracted from video games in real time as we play them. We interface the popular Microsoft DirectX rendering API, and inject specialized rendering code into the game as it is running. This code produces ground truth labels for instance segmentation, semantic labeling, depth estimation, optical flow, intrinsic image decomposition, and instance tracking. Instead of labeling images, a researcher now simply plays video games all day long. Our method is general and works on a wide range of video games. We collected a dataset of 220k training images, and 60k test images across 3 video games, and evaluate state of the art optical flow, depth estimation and intrinsic image decomposition algorithms. Our video game data is visually closer to real world images, than other synthetic dataset. |
| Tasks | Depth Estimation, Instance Segmentation, Intrinsic Image Decomposition, Optical Flow Estimation, Semantic Segmentation |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Krahenbuhl_Free_Supervision_From_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Krahenbuhl_Free_Supervision_From_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/free-supervision-from-video-games |
| Repo | |
| Framework | |
A closer look at the word analogy problem
| Title | A closer look at the word analogy problem |
| Authors | Siddharth Krishna Kumar |
| Abstract | Although word analogy problems have become a standard tool for evaluating word vectors, little is known about why word vectors are so good at solving these problems. In this paper, I attempt to further our understanding of the subject, by developing a simple, but highly accurate generative approach to solve the word analogy problem for the case when all terms involved in the problem are nouns. My results demonstrate the ambiguities associated with learning the relationship between a word pair, and the role of the training dataset in determining the relationship which gets most highlighted. Furthermore, my results show that the ability of a model to accurately solve the word analogy problem may not be indicative of a model’s ability to learn the relationship between a word pair the way a human does. |
| Tasks | |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=ryA-jdlA- |
| https://openreview.net/pdf?id=ryA-jdlA- | |
| PWC | https://paperswithcode.com/paper/a-closer-look-at-the-word-analogy-problem |
| Repo | |
| Framework | |
JeSemE: Interleaving Semantics and Emotions in a Web Service for the Exploration of Language Change Phenomena
| Title | JeSemE: Interleaving Semantics and Emotions in a Web Service for the Exploration of Language Change Phenomena |
| Authors | Johannes Hellrich, Sven Buechel, Udo Hahn |
| Abstract | We here introduce a substantially extended version of JeSemE, an interactive website for visually exploring computationally derived time-variant information on word meanings and lexical emotions assembled from five large diachronic text corpora. JeSemE is designed for scholars in the (digital) humanities as an alternative to consulting manually compiled, printed dictionaries for such information (if available at all). This tool uniquely combines state-of-the-art distributional semantics with a nuanced model of human emotions, two information streams we deem beneficial for a data-driven interpretation of texts in the humanities. |
| Tasks | Sentiment Analysis, Word Embeddings |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-2003/ |
| https://www.aclweb.org/anthology/C18-2003 | |
| PWC | https://paperswithcode.com/paper/jeseme-interleaving-semantics-and-emotions-in |
| Repo | |
| Framework | |
Using Morphological Knowledge in Open-Vocabulary Neural Language Models
| Title | Using Morphological Knowledge in Open-Vocabulary Neural Language Models |
| Authors | Austin Matthews, Graham Neubig, Chris Dyer |
| Abstract | Languages with productive morphology pose problems for language models that generate words from a fixed vocabulary. Although character-based models allow any possible word type to be generated, they are linguistically na{"\i}ve: they must discover that words exist and are delimited by spaces{—}basic linguistic facts that are built in to the structure of word-based models. We introduce an open-vocabulary language model that incorporates more sophisticated linguistic knowledge by predicting words using a mixture of three generative processes: (1) by generating words as a sequence of characters, (2) by directly generating full word forms, and (3) by generating words as a sequence of morphemes that are combined using a hand-written morphological analyzer. Experiments on Finnish, Turkish, and Russian show that our model outperforms character sequence models and other strong baselines on intrinsic and extrinsic measures. Furthermore, we show that our model learns to exploit morphological knowledge encoded in the analyzer, and, as a byproduct, it can perform effective unsupervised morphological disambiguation. |
| Tasks | Language Modelling |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/N18-1130/ |
| https://www.aclweb.org/anthology/N18-1130 | |
| PWC | https://paperswithcode.com/paper/using-morphological-knowledge-in-open |
| Repo | |
| Framework | |
Efficient Gradient Computation for Structured Output Learning with Rational and Tropical Losses
| Title | Efficient Gradient Computation for Structured Output Learning with Rational and Tropical Losses |
| Authors | Corinna Cortes, Vitaly Kuznetsov, Mehryar Mohri, Dmitry Storcheus, Scott Yang |
| Abstract | Many structured prediction problems admit a natural loss function for evaluation such as the edit-distance or $n$-gram loss. However, existing learning algorithms are typically designed to optimize alternative objectives such as the cross-entropy. This is because a na"{i}ve implementation of the natural loss functions often results in intractable gradient computations. In this paper, we design efficient gradient computation algorithms for two broad families of structured prediction loss functions: rational and tropical losses. These families include as special cases the $n$-gram loss, the edit-distance loss, and many other loss functions commonly used in natural language processing and computational biology tasks that are based on sequence similarity measures. Our algorithms make use of weighted automata and graph operations over appropriate semirings to design efficient solutions. They facilitate efficient gradient computation and hence enable one to train learning models such as neural networks with complex structured losses. |
| Tasks | Structured Prediction |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7914-efficient-gradient-computation-for-structured-output-learning-with-rational-and-tropical-losses |
| http://papers.nips.cc/paper/7914-efficient-gradient-computation-for-structured-output-learning-with-rational-and-tropical-losses.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-gradient-computation-for-structured |
| Repo | |
| Framework | |
NTT’s Neural Machine Translation Systems for WMT 2018
| Title | NTT’s Neural Machine Translation Systems for WMT 2018 |
| Authors | Makoto Morishita, Jun Suzuki, Masaaki Nagata |
| Abstract | This paper describes NTT{'}s neural machine translation systems submitted to the WMT 2018 English-German and German-English news translation tasks. Our submission has three main components: the Transformer model, corpus cleaning, and right-to-left n-best re-ranking techniques. Through our experiments, we identified two keys for improving accuracy: filtering noisy training sentences and right-to-left re-ranking. We also found that the Transformer model requires more training data than the RNN-based model, and the RNN-based model sometimes achieves better accuracy than the Transformer model when the corpus is small. |
| Tasks | Machine Translation |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-6421/ |
| https://www.aclweb.org/anthology/W18-6421 | |
| PWC | https://paperswithcode.com/paper/ntts-neural-machine-translation-systems-for |
| Repo | |
| Framework | |
Incorporating Semantic Attention in Video Description Generation
| Title | Incorporating Semantic Attention in Video Description Generation |
| Authors | Natsuda Laokulrat, Naoaki Okazaki, Hideki Nakayama |
| Abstract | |
| Tasks | Image Captioning, Image Classification, Language Modelling, Object Recognition, Video Description |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1477/ |
| https://www.aclweb.org/anthology/L18-1477 | |
| PWC | https://paperswithcode.com/paper/incorporating-semantic-attention-in-video |
| Repo | |
| Framework | |
Geometry-Aware Scene Text Detection With Instance Transformation Network
| Title | Geometry-Aware Scene Text Detection With Instance Transformation Network |
| Authors | Fangfang Wang, Liming Zhao, Xi Li, Xinchao Wang, Dacheng Tao |
| Abstract | Localizing text in the wild is challenging in the situations of complicated geometric layout of the targets like random orientation and large aspect ratio. In this paper, we propose a geometry-aware modeling approach tailored for scene text representation with an end-to-end learning scheme. In our approach, a novel Instance Transformation Network (ITN) is presented to learn the geometry-aware representation encoding the unique geometric configurations of scene text instances with in-network transformation embedding, resulting in a robust and elegant framework to detect words or text lines at one pass. An end-to-end multi-task learning strategy with transformation regression, text/non-text classification and coordinate regression is adopted in the ITN. Experiments on the benchmark datasets demonstrate the effectiveness of the proposed approach in detecting scene text in various geometric configurations. |
| Tasks | Multi-Task Learning, Scene Text Detection, Text Classification |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Wang_Geometry-Aware_Scene_Text_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Wang_Geometry-Aware_Scene_Text_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/geometry-aware-scene-text-detection-with |
| Repo | |
| Framework | |
Clustering Redemption–Beyond the Impossibility of Kleinberg’s Axioms
| Title | Clustering Redemption–Beyond the Impossibility of Kleinberg’s Axioms |
| Authors | Vincent Cohen-Addad, Varun Kanade, Frederik Mallmann-Trenn |
| Abstract | Kleinberg (2002) stated three axioms that any clustering procedure should satisfy and showed there is no clustering procedure that simultaneously satisfies all three. One of these, called the consistency axiom, requires that when the data is modified in a helpful way, i.e. if points in the same cluster are made more similar and those in different ones made less similar, the algorithm should output the same clustering. To circumvent this impossibility result, research has focused on considering clustering procedures that have a clustering quality measure (or a cost) and showing that a modification of Kleinberg’s axioms that takes cost into account lead to feasible clustering procedures. In this work, we take a different approach, based on the observation that the consistency axiom fails to be satisfied when the “correct” number of clusters changes. We modify this axiom by making use of cost functions to determine the correct number of clusters, and require that consistency holds only if the number of clusters remains unchanged. We show that single linkage satisfies the modified axioms, and if the input is well-clusterable, some popular procedures such as k-means also satisfy the axioms, taking a step towards explaining the success of these objective functions for guiding the design of algorithms. |
| Tasks | |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/8071-clustering-redemptionbeyond-the-impossibility-of-kleinbergs-axioms |
| http://papers.nips.cc/paper/8071-clustering-redemptionbeyond-the-impossibility-of-kleinbergs-axioms.pdf | |
| PWC | https://paperswithcode.com/paper/clustering-redemptionbeyond-the-impossibility |
| Repo | |
| Framework | |
AX Semantics’ Submission to the CoNLL–SIGMORPHON 2018 Shared Task
| Title | AX Semantics’ Submission to the CoNLL–SIGMORPHON 2018 Shared Task |
| Authors | Andreas Madsack, Alessia Cavallo, Johanna Heininger, Robert Wei{\ss}graeber |
| Abstract | |
| Tasks | |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/K18-3004/ |
| https://www.aclweb.org/anthology/K18-3004 | |
| PWC | https://paperswithcode.com/paper/ax-semantics-submission-to-the-conll |
| Repo | |
| Framework | |
What do I Annotate Next? An Empirical Study of Active Learning for Action Localization
| Title | What do I Annotate Next? An Empirical Study of Active Learning for Action Localization |
| Authors | Fabian Caba Heilbron, Joon-Young Lee, Hailin Jin, Bernard Ghanem |
| Abstract | Despite tremendous progress achieved in temporal action localization, state-of-the-art methods still struggle to train accurate models when annotated data is scarce. In this paper, we introduce a novel active learning framework for temporal localization that aims to mitigate this data dependency issue. We equip our framework with active selection functions that can reuse knowledge from previously annotated datasets. We study the performance of two state-of-the-art active selection functions as well as two widely used active learning baselines. To validate the effectiveness of each one of these selection functions, we conduct simulated experiments on ActivityNet. We find that using previously acquired knowledge as a bootstrapping source is crucial for active learners aiming to localize actions. When equipped with the right selection function, our proposed framework exhibits significantly better performance than standard active learning strategies, such as uncertainty sampling. Finally, we employ our framework to augment the newly compiled Kinetics action dataset with ground-truth temporal annotations. As a result, we collect Kinetics-Localization, a novel large-scale dataset for temporal action localization, which contains more than 15K YouTube videos. |
| Tasks | Action Localization, Active Learning, Temporal Action Localization, Temporal Localization |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Fabian_Caba_What_do_I_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Fabian_Caba_What_do_I_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/what-do-i-annotate-next-an-empirical-study-of |
| Repo | |
| Framework | |
