Paper Group NANR 160
Person Search by Text Attribute Query As Zero-Shot Learning. Singleshot : a scalable Tucker tensor decomposition. Detecting Depression in Social Media using Fine-Grained Emotions. New Convex Relaxations for MRF Inference With Unknown Graphs. Dependency Parsing with your Eyes: Dependency Structure Predicts Eye Regressions During Reading. Distributed …
Person Search by Text Attribute Query As Zero-Shot Learning
| Title | Person Search by Text Attribute Query As Zero-Shot Learning |
| Authors | Qi Dong, Shaogang Gong, Xiatian Zhu |
| Abstract | Existing person search methods predominantly assume the availability of at least one-shot imagery sample of the queried person. This assumption is limited in circumstances where only a brief textual (or verbal) description of the target person is available. In this work, we present a deep learning method for attribute text description based person search without any query imagery. Whilst conventional cross-modality matching methods, such as global visual-textual embedding based zero-shot learning and local individual attribute recognition, are functionally applicable, they are limited by several assumptions invalid to person search in deployment scale, data quality, and/or category name semantics. We overcome these issues by formulating an Attribute-Image Hierarchical Matching (AIHM) model. It is able to more reliably match text attribute descriptions with noisy surveillance person images by jointly learning global category-level and local attribute-level textual-visual embedding as well as matching. Extensive evaluations demonstrate the superiority of our AIHM model over a wide variety of state-of-the-art methods on three publicly available attribute labelled surveillance person search benchmarks: Market-1501, DukeMTMC, and PA100K. |
| Tasks | Person Search, Zero-Shot Learning |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Dong_Person_Search_by_Text_Attribute_Query_As_Zero-Shot_Learning_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Dong_Person_Search_by_Text_Attribute_Query_As_Zero-Shot_Learning_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/person-search-by-text-attribute-query-as-zero |
| Repo | |
| Framework | |
Singleshot : a scalable Tucker tensor decomposition
| Title | Singleshot : a scalable Tucker tensor decomposition |
| Authors | Abraham Traore, Maxime Berar, Alain Rakotomamonjy |
| Abstract | This paper introduces a new approach for the scalable Tucker decomposition problem. Given a tensor X , the method proposed allows to infer the latent factors by processing one subtensor drawn from X at a time. The key principle of our approach is based on the recursive computations of gradient and on cyclic update of factors involving only one single step of gradient descent. We further improve the computational efficiency of this algorithm by proposing an inexact gradient version. These two algorithms are backed with theoretical guarantees of convergence and convergence rate under mild conditions. The scalabilty of the proposed approaches which can be easily extended to handle some common constraints encountered in tensor decomposition (e.g non-negativity), is proven via numerical experiments on both synthetic and real data sets. |
| Tasks | |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/8860-singleshot-a-scalable-tucker-tensor-decomposition |
| http://papers.nips.cc/paper/8860-singleshot-a-scalable-tucker-tensor-decomposition.pdf | |
| PWC | https://paperswithcode.com/paper/singleshot-a-scalable-tucker-tensor |
| Repo | |
| Framework | |
Detecting Depression in Social Media using Fine-Grained Emotions
| Title | Detecting Depression in Social Media using Fine-Grained Emotions |
| Authors | Mario Ezra Arag{'o}n, Adrian Pastor L{'o}pez-Monroy, Luis Carlos Gonz{'a}lez-Gurrola, Manuel Montes-y-G{'o}mez |
| Abstract | Nowadays social media platforms are the most popular way for people to share information, from work issues to personal matters. For example, people with health disorders tend to share their concerns for advice, support or simply to relieve suffering. This provides a great opportunity to proactively detect these users and refer them as soon as possible to professional help. We propose a new representation called Bag of Sub-Emotions (BoSE), which represents social media documents by a set of fine-grained emotions automatically generated using a lexical resource of emotions and subword embeddings. The proposed representation is evaluated in the task of depression detection. The results are encouraging; the usage of fine-grained emotions improved the results from a representation based on the core emotions and obtained competitive results in comparison to state of the art approaches. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-1151/ |
| https://www.aclweb.org/anthology/N19-1151 | |
| PWC | https://paperswithcode.com/paper/detecting-depression-in-social-media-using |
| Repo | |
| Framework | |
New Convex Relaxations for MRF Inference With Unknown Graphs
| Title | New Convex Relaxations for MRF Inference With Unknown Graphs |
| Authors | Zhenhua Wang, Tong Liu, Qinfeng Shi, M. Pawan Kumar, Jianhua Zhang |
| Abstract | Treating graph structures of Markov random fields as unknown and estimating them jointly with labels have been shown to be useful for modeling human activity recognition and other related tasks. We propose two novel relaxations for solving this problem. The first is a linear programming (LP) relaxation, which is provably tighter than the existing LP relaxation. The second is a non-convex quadratic programming (QP) relaxation, which admits an efficient concave-convex procedure (CCCP). The CCCP algorithm is initialized by solving a convex QP relaxation of the problem, which is obtained by modifying the diagonal of the matrix that specifies the non-convex QP relaxation. We show that our convex QP relaxation is optimal in the sense that it minimizes the L1 norm of the diagonal modification vector. While the convex QP relaxation is not as tight as the existing and the new LP relaxations, when used in conjunction with the CCCP algorithm for the non-convex QP relaxation, it provides accurate solutions. We demonstrate the efficacy of our new relaxations for both synthetic data and human activity recognition. |
| Tasks | Activity Recognition, Human Activity Recognition |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Wang_New_Convex_Relaxations_for_MRF_Inference_With_Unknown_Graphs_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Wang_New_Convex_Relaxations_for_MRF_Inference_With_Unknown_Graphs_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/new-convex-relaxations-for-mrf-inference-with |
| Repo | |
| Framework | |
Dependency Parsing with your Eyes: Dependency Structure Predicts Eye Regressions During Reading
| Title | Dependency Parsing with your Eyes: Dependency Structure Predicts Eye Regressions During Reading |
| Authors | Aless Lopopolo, ro, Stefan L. Frank, Antal van den Bosch, Roel Willems |
| Abstract | Backward saccades during reading have been hypothesized to be involved in structural reanalysis, or to be related to the level of text difficulty. We test the hypothesis that backward saccades are involved in online syntactic analysis. If this is the case we expect that saccades will coincide, at least partially, with the edges of the relations computed by a dependency parser. In order to test this, we analyzed a large eye-tracking dataset collected while 102 participants read three short narrative texts. Our results show a relation between backward saccades and the syntactic structure of sentences. |
| Tasks | Dependency Parsing, Eye Tracking |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-2909/ |
| https://www.aclweb.org/anthology/W19-2909 | |
| PWC | https://paperswithcode.com/paper/dependency-parsing-with-your-eyes-dependency |
| Repo | |
| Framework | |
Distributed Knowledge Based Clinical Auto-Coding System
| Title | Distributed Knowledge Based Clinical Auto-Coding System |
| Authors | Rajvir Kaur |
| Abstract | Codification of free-text clinical narratives have long been recognised to be beneficial for secondary uses such as funding, insurance claim processing and research. In recent years, many researchers have studied the use of Natural Language Processing (NLP), related Machine Learning (ML) methods and techniques to resolve the problem of manual coding of clinical narratives. Most of the studies are focused on classification systems relevant to the U.S and there is a scarcity of studies relevant to Australian classification systems such as ICD-10-AM and ACHI. Therefore, we aim to develop a knowledge-based clinical auto-coding system, that utilise appropriate NLP and ML techniques to assign ICD-10-AM and ACHI codes to clinical records, while adhering to both local coding standards (Australian Coding Standard) and international guidelines that get updated and validated continuously. |
| Tasks | |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-2001/ |
| https://www.aclweb.org/anthology/P19-2001 | |
| PWC | https://paperswithcode.com/paper/distributed-knowledge-based-clinical-auto |
| Repo | |
| Framework | |
The First Shared Task on Discourse Representation Structure Parsing
| Title | The First Shared Task on Discourse Representation Structure Parsing |
| Authors | Lasha Abzianidze, Rik van Noord, Hessel Haagsma, Johan Bos |
| Abstract | The paper presents the IWCS 2019 shared task on semantic parsing where the goal is to produce Discourse Representation Structures (DRSs) for English sentences. DRSs originate from Discourse Representation Theory and represent scoped meaning representations that capture the semantics of negation, modals, quantification, and presupposition triggers. Additionally, concepts and event-participants in DRSs are described with WordNet synsets and the thematic roles from VerbNet. To measure similarity between two DRSs, they are represented in a clausal form, i.e. as a set of tuples. Participant systems were expected to produce DRSs in this clausal form. Taking into account the rich lexical information, explicit scope marking, a high number of shared variables among clauses, and highly-constrained format of valid DRSs, all these makes the DRS parsing a challenging NLP task. The results of the shared task displayed improvements over the existing state-of-the-art parser. |
| Tasks | Semantic Parsing |
| Published | 2019-05-01 |
| URL | https://www.aclweb.org/anthology/W19-1201/ |
| https://www.aclweb.org/anthology/W19-1201 | |
| PWC | https://paperswithcode.com/paper/the-first-shared-task-on-discourse |
| Repo | |
| Framework | |
Unsupervised multi-word term recognition in Welsh
| Title | Unsupervised multi-word term recognition in Welsh |
| Authors | Irena Spasi{'c}, David Owen, Dawn Knight, Andreas Artemiou |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-6901/ |
| https://www.aclweb.org/anthology/W19-6901 | |
| PWC | https://paperswithcode.com/paper/unsupervised-multi-word-term-recognition-in |
| Repo | |
| Framework | |
Context Effects on Human Judgments of Similarity
| Title | Context Effects on Human Judgments of Similarity |
| Authors | Libby Barak, Noe Kong-Johnson, Adele Goldberg |
| Abstract | The semantic similarity of words forms the basis of many natural language processing methods. These computational similarity measures are often based on a mathematical comparison of vector representations of word meanings, while human judgments of similarity differ in lacking geometrical properties, e.g., symmetric similarity and triangular similarity. In this study, we propose a novel task design to further explore human behavior by asking whether a pair of words is deemed more similar depending on an immediately preceding judgment. Results from a crowdsourcing experiment show that people consistently judge words as more similar when primed by a judgment that evokes a relevant relationship. Our analysis further shows that word2vec similarity correlated significantly better with the out-of-context judgments, thus confirming the methodological differences in human-computer judgments, and offering a new testbed for probing the differences. |
| Tasks | Semantic Similarity, Semantic Textual Similarity |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/papers/W/W19/W19-3642/ |
| https://www.aclweb.org/anthology/W19-3642 | |
| PWC | https://paperswithcode.com/paper/context-effects-on-human-judgments-of |
| Repo | |
| Framework | |
Robust Video Stabilization by Optimization in CNN Weight Space
| Title | Robust Video Stabilization by Optimization in CNN Weight Space |
| Authors | Jiyang Yu, Ravi Ramamoorthi |
| Abstract | We propose a novel robust video stabilization method. Unlike traditional video stabilization techniques that involve complex motion models, we directly model the appearance change of the frames as the dense optical flow field of consecutive frames. We introduce a new formulation of the video stabilization task based on first principles, which leads to a large scale non-convex problem. This problem is hard to solve, so previous optical flow based approaches have resorted to heuristics. In this paper, we propose a novel optimization routine that transfers this problem into the convolutional neural network parameter domain. While we exploit the general benefits of CNNs, including standard gradient-based optimization techniques, our method is a new approach to using CNNs purely as an optimizer rather than learning from data.Our method trains the CNN from scratch on each specific input example, and intentionally overfits the CNN parameters to produce the best result on the input example. By solving the problem in the CNN weight space rather than directly for image pixels, we make it a viable formulation for video stabilization. Our method produces both visually and quantitatively better results than previous work, and is robust in situations acknowledged as limitations in current state-of-the-art methods. |
| Tasks | Optical Flow Estimation |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Yu_Robust_Video_Stabilization_by_Optimization_in_CNN_Weight_Space_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Yu_Robust_Video_Stabilization_by_Optimization_in_CNN_Weight_Space_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/robust-video-stabilization-by-optimization-in |
| Repo | |
| Framework | |
CollaGAN: Collaborative GAN for Missing Image Data Imputation
| Title | CollaGAN: Collaborative GAN for Missing Image Data Imputation |
| Authors | Dongwook Lee, Junyoung Kim, Won-Jin Moon, Jong Chul Ye |
| Abstract | In many applications requiring multiple inputs to obtain a desired output, if any of the input data is missing, it often introduces large amounts of bias. Although many techniques have been developed for imputing missing data, the image imputation is still difficult due to complicated nature of natural images. To address this problem, here we proposed a novel framework for missing image data imputation, called Collaborative Generative Adversarial Network (CollaGAN). CollaGAN convert the image imputation problem to a multi-domain images-to-image translation task so that a single generator and discriminator network can successfully estimate the missing data using the remaining clean data set. We demonstrate that CollaGAN produces the images with a higher visual quality compared to the existing competing approaches in various image imputation tasks. |
| Tasks | Image Imputation, Imputation |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Lee_CollaGAN_Collaborative_GAN_for_Missing_Image_Data_Imputation_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Lee_CollaGAN_Collaborative_GAN_for_Missing_Image_Data_Imputation_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/collagan-collaborative-gan-for-missing-image-1 |
| Repo | |
| Framework | |
Machine Translation With Weakly Paired Documents
| Title | Machine Translation With Weakly Paired Documents |
| Authors | Lijun Wu, Jinhua Zhu, Di He, Fei Gao, Tao Qin, Jianhuang Lai, Tie-Yan Liu |
| Abstract | Neural machine translation, which achieves near human-level performance in some languages, strongly relies on the large amounts of parallel sentences, which hinders its applicability to low-resource language pairs. Recent works explore the possibility of unsupervised machine translation with monolingual data only, leading to much lower accuracy compared with the supervised one. Observing that weakly paired bilingual documents are much easier to collect than bilingual sentences, e.g., from Wikipedia, news websites or books, in this paper, we investigate training translation models with weakly paired bilingual documents. Our approach contains two components. 1) We provide a simple approach to mine implicitly bilingual sentence pairs from document pairs which can then be used as supervised training signals. 2) We leverage the topic consistency of two weakly paired documents and learn the sentence translation model by constraining the word distribution-level alignments. We evaluate our method on weakly paired documents from Wikipedia on six tasks, the widely used WMT16 German$\leftrightarrow$English, WMT13 Spanish$\leftrightarrow$English and WMT16 Romanian$\leftrightarrow$English translation tasks. We obtain 24.1/30.3, 28.1/27.6 and 30.1/27.6 BLEU points separately, outperforming previous results by more than 5 BLEU points in each direction and reducing the gap between unsupervised translation and supervised translation up to 50{%}. |
| Tasks | Machine Translation, Unsupervised Machine Translation |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1446/ |
| https://www.aclweb.org/anthology/D19-1446 | |
| PWC | https://paperswithcode.com/paper/machine-translation-with-weakly-paired-1 |
| Repo | |
| Framework | |
Unraveling the Search Space of Abusive Language in Wikipedia with Dynamic Lexicon Acquisition
| Title | Unraveling the Search Space of Abusive Language in Wikipedia with Dynamic Lexicon Acquisition |
| Authors | Wei-Fan Chen, Khalid Al Khatib, Matthias Hagen, Henning Wachsmuth, Benno Stein |
| Abstract | Many discussions on online platforms suffer from users offending others by using abusive terminology, threatening each other, or being sarcastic. Since an automatic detection of abusive language can support human moderators of online discussion platforms, detecting abusiveness has recently received increased attention. However, the existing approaches simply train one classifier for the whole variety of abusiveness. In contrast, our approach is to distinguish explicitly abusive cases from the more {``}shadowed{''} ones. By dynamically extending a lexicon of abusive terms (e.g., including new obfuscations of abusive terms), our approach can support a moderator with explicit unraveled explanations for why something was flagged as abusive: due to known explicitly abusive terms, due to newly detected (obfuscated) terms, or due to shadowed cases. | |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5009/ |
| https://www.aclweb.org/anthology/D19-5009 | |
| PWC | https://paperswithcode.com/paper/unraveling-the-search-space-of-abusive |
| Repo | |
| Framework | |
DSConv: Efficient Convolution Operator
| Title | DSConv: Efficient Convolution Operator |
| Authors | Marcelo Gennari do Nascimento, Roger Fawcett, Victor Adrian Prisacariu |
| Abstract | Quantization is a popular way of increasing the speed and lowering the memory usage of Convolution Neural Networks (CNNs). When labelled training data is available, network weights and activations have successfully been quantized down to 1-bit. The same cannot be said about the scenario when labelled training data is not available, e.g. when quantizing a pre-trained model, where current approaches show, at best, no loss of accuracy at 8-bit quantizations. We introduce DSConv, a flexible quantized convolution operator that replaces single-precision operations with their far less expensive integer counterparts, while maintaining the probability distributions over both the kernel weights and the outputs. We test our model as a plug-and-play replacement for standard convolution on most popular neural network architectures, ResNet, DenseNet, GoogLeNet, AlexNet and VGG-Net and demonstrate state-of-the-art results, with less than 1% loss of accuracy, without retraining, using only 4-bit quantization. We also show how a distillation-based adaptation stage with unlabelled data can improve results even further. |
| Tasks | Quantization |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/do_Nascimento_DSConv_Efficient_Convolution_Operator_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/do_Nascimento_DSConv_Efficient_Convolution_Operator_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/dsconv-efficient-convolution-operator-1 |
| Repo | |
| Framework | |
Online Stochastic Shortest Path with Bandit Feedback and Unknown Transition Function
| Title | Online Stochastic Shortest Path with Bandit Feedback and Unknown Transition Function |
| Authors | Aviv Rosenberg, Yishay Mansour |
| Abstract | We consider online learning in episodic loop-free Markov decision processes (MDPs), where the loss function can change arbitrarily between episodes. The transition function is fixed but unknown to the learner, and the learner only observes bandit feedback (not the entire loss function). For this problem we develop no-regret algorithms that perform asymptotically as well as the best stationary policy in hindsight. Assuming that all states are reachable with probability $\beta > 0$ under any policy, we give a regret bound of $\tilde{O} ( LX\sqrt{AT} / \beta )$, where $T$ is the number of episodes, $X$ is the state space, $A$ is the action space, and $L$ is the length of each episode. When this assumption is removed we give a regret bound of $\tilde{O} ( L^{3/2} X A^{1/4} T^{3/4})$, that holds for an arbitrary transition function. To our knowledge these are the first algorithms that in our setting handle both bandit feedback and an unknown transition function. |
| Tasks | |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/8493-online-stochastic-shortest-path-with-bandit-feedback-and-unknown-transition-function |
| http://papers.nips.cc/paper/8493-online-stochastic-shortest-path-with-bandit-feedback-and-unknown-transition-function.pdf | |
| PWC | https://paperswithcode.com/paper/online-stochastic-shortest-path-with-bandit |
| Repo | |
| Framework | |
