Paper Group ANR 401
KeyPose: Multi-view 3D Labeling and Keypoint Estimation for Transparent Objects. A Tool for Spatio-Temporal Analysis of Social Anxiety with Twitter Data. Coarse-to-Fine Registration of Airborne LiDAR Data and Optical Imagery on Urban Scenes. BERE: An accurate distantly supervised biomedical entity relation extraction network. Antonym-Synonym Classi …
KeyPose: Multi-view 3D Labeling and Keypoint Estimation for Transparent Objects
| Title | KeyPose: Multi-view 3D Labeling and Keypoint Estimation for Transparent Objects |
| Authors | Xingyu Liu, Rico Jonschkowski, Anelia Angelova, Kurt Konolige |
| Abstract | Estimating the 3D pose of desktop objects is crucial for applications such as robotic manipulation. Finding the depth of the object is an important part of this task, both for training and prediction, and is usually accomplished with a depth sensor or markers in a motion-capture system. For transparent or highly reflective objects, such methods are not feasible without impinging on the resultant image of the object. Hence, many existing methods restrict themselves to opaque, lambertian objects that give good returns from RGBD sensors. In this paper we address two problems: first, establish an easy method for capturing and labeling 3D keypoints on desktop objects with a stereo sensor (no special depth sensor required); and second, develop a deep method, called $KeyPose$, that learns to accurately predict 3D keypoints on objects, including challenging ones such as transparent objects. To showcase the performance of the method, we create and employ a dataset of 15 clear objects in 5 classes, with 48k 3D-keypoint labeled images. We train both instance and category models, and show generalization to new textures, poses, and objects. KeyPose surpasses state-of-the-art performance in 3D pose estimation on this dataset, sometimes by a wide margin, and even in cases where the competing method is provided with registered depth. We will release a public version of the data capture and labeling pipeline, the transparent object database, and the KeyPose training and evaluation code. |
| Tasks | 3D Pose Estimation, Motion Capture, Pose Estimation |
| Published | 2019-12-05 |
| URL | https://arxiv.org/abs/1912.02805v1 |
| https://arxiv.org/pdf/1912.02805v1.pdf | |
| PWC | https://paperswithcode.com/paper/keypose-multi-view-3d-labeling-and-keypoint |
| Repo | |
| Framework | |
A Tool for Spatio-Temporal Analysis of Social Anxiety with Twitter Data
| Title | A Tool for Spatio-Temporal Analysis of Social Anxiety with Twitter Data |
| Authors | Joohong Lee, Dongyoung Son, Yong Suk Choi |
| Abstract | In this paper, we present a tool for analyzing spatio-temporal distribution of social anxiety. Twitter, one of the most popular social network services, has been chosen as data source for analysis of social anxiety. Tweets (posted on the Twitter) contain various emotions and thus these individual emotions reflect social atmosphere and public opinion, which are often dependent on spatial and temporal factors. The reason why we choose anxiety among various emotions is that anxiety is very important emotion that is useful for observing and understanding social events of communities. We develop a machine learning based tool to analyze the changes of social atmosphere spatially and temporally. Our tool classifies whether each Tweet contains anxious content or not, and also estimates degree of Tweet anxiety. Furthermore, it also visualizes spatio-temporal distribution of anxiety as a form of web application, which is incorporated with physical map, word cloud, search engine and chart viewer. Our tool is applied to a big tweet data in South Korea to illustrate its usefulness for exploring social atmosphere and public opinion spatio-temporally. |
| Tasks | |
| Published | 2019-01-23 |
| URL | http://arxiv.org/abs/1901.08158v1 |
| http://arxiv.org/pdf/1901.08158v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-tool-for-spatio-temporal-analysis-of-social |
| Repo | |
| Framework | |
Coarse-to-Fine Registration of Airborne LiDAR Data and Optical Imagery on Urban Scenes
| Title | Coarse-to-Fine Registration of Airborne LiDAR Data and Optical Imagery on Urban Scenes |
| Authors | Thanh Huy Nguyen, Sylvie Daniel, Didier Gueriot, Christophe Sintes, Jean-Marc Le Caillec |
| Abstract | Applications based on synergistic integration of optical imagery and LiDAR data are receiving a growing interest from the remote sensing community. However, a misaligned integration between these datasets may fail to fully profit the potential of both sensors. In this regard, an optimum fusion of optical imagery and LiDAR data requires an accurate registration. This is a complex problem since a versatile solution is still missing, especially when considering the context where data are collected at different times, from different platforms, under different acquisition configurations. This paper presents a coarse-to-fine registration method of aerial/satellite optical imagery with airborne LiDAR data acquired in such context. Firstly, a coarse registration involves extracting and matching of buildings from LiDAR data and optical imagery. Then, a Mutual Information-based fine registration is carried out. It involves a super-resolution approach applied to LiDAR data, and a local approach of transformation model estimation. The proposed method succeeds at overcoming the challenges associated with the aforementioned difficult context. Considering the experimented airborne LiDAR (2011) and orthorectified aerial imagery (2016) datasets, their spatial shift is reduced by 48.15% after the proposed coarse registration. Moreover, the incompatibility of size and spatial resolution is addressed by the mentioned super-resolution. Finally, a high accuracy of dataset alignment is also achieved, highlighted by a 40-cm error based on a check-point assessment and a 64-cm error based on a check-pair-line assessment. These promising results enable further research for a complete versatile fusion methodology between airborne LiDAR and optical imagery data in this challenging context. |
| Tasks | Super-Resolution |
| Published | 2019-09-30 |
| URL | https://arxiv.org/abs/1909.13817v1 |
| https://arxiv.org/pdf/1909.13817v1.pdf | |
| PWC | https://paperswithcode.com/paper/coarse-to-fine-registration-of-airborne-lidar |
| Repo | |
| Framework | |
BERE: An accurate distantly supervised biomedical entity relation extraction network
| Title | BERE: An accurate distantly supervised biomedical entity relation extraction network |
| Authors | Lixiang Hong, JinJian Lin, Jiang Tao, Jianyang Zeng |
| Abstract | Automated entity relation extraction (RE) from literature provides an important source for constructing biomedical database, which is more efficient and extensible than manual curation. However, existing RE models usually ignore the information contained in sentence structures and target entities. In this paper, we propose BERE, a deep learning based model which uses Gumbel Tree-GRU to learn sentence structures and joint embedding to incorporate entity information. It also employs word-level attention for improved relation extraction and sentence-level attention to suit the distantly supervised dataset. Because the existing dataset are relatively small, we further construct a much larger drug-target interaction extraction (DTIE) dataset by distant supervision. Experiments conducted on both DDIExtraction 2013 task and DTIE dataset show our model’s effectiveness over state-of-the-art baselines in terms of F1 measures and PR curves. |
| Tasks | Relation Extraction |
| Published | 2019-06-17 |
| URL | https://arxiv.org/abs/1906.06916v2 |
| https://arxiv.org/pdf/1906.06916v2.pdf | |
| PWC | https://paperswithcode.com/paper/bere-an-accurate-distantly-supervised |
| Repo | |
| Framework | |
Antonym-Synonym Classification Based on New Sub-space Embeddings
| Title | Antonym-Synonym Classification Based on New Sub-space Embeddings |
| Authors | Muhammad Asif Ali, Yifang Sun, Xiaoling Zhou, Wei Wang, Xiang Zhao |
| Abstract | Distinguishing antonyms from synonyms is a key challenge for many NLP applications focused on the lexical-semantic relation extraction. Existing solutions relying on large-scale corpora yield low performance because of huge contextual overlap of antonym and synonym pairs. We propose a novel approach entirely based on pre-trained embeddings. We hypothesize that the pre-trained embeddings comprehend a blend of lexical-semantic information and we may distill the task-specific information using Distiller, a model proposed in this paper. Later, a classifier is trained based on features constructed from the distilled sub-spaces along with some word level features to distinguish antonyms from synonyms. Experimental results show that the proposed model outperforms existing research on antonym synonym distinction in both speed and performance. |
| Tasks | Relation Extraction |
| Published | 2019-06-13 |
| URL | https://arxiv.org/abs/1906.05612v1 |
| https://arxiv.org/pdf/1906.05612v1.pdf | |
| PWC | https://paperswithcode.com/paper/antonym-synonym-classification-based-on-new |
| Repo | |
| Framework | |
Automated Gaming Pommerman: FFA
| Title | Automated Gaming Pommerman: FFA |
| Authors | Ms. Navya Singh, Mr. Anshul Dhull, Mr. Barath Mohan. S, Mr. Bhavish Pahwa, Ms. Komal Sharma |
| Abstract | Our game Pommerman is based on the console game Bommerman. The game starts on an 11 by 11 platform. Pommerman is a multi-agent environment and is made up of a set of different situations and contains four agents. |
| Tasks | |
| Published | 2019-07-13 |
| URL | https://arxiv.org/abs/1907.06096v1 |
| https://arxiv.org/pdf/1907.06096v1.pdf | |
| PWC | https://paperswithcode.com/paper/automated-gaming-pommerman-ffa |
| Repo | |
| Framework | |
Zero-shot Chinese Discourse Dependency Parsing via Cross-lingual Mapping
| Title | Zero-shot Chinese Discourse Dependency Parsing via Cross-lingual Mapping |
| Authors | Yi Cheng, Sujian Li |
| Abstract | Due to the absence of labeled data, discourse parsing still remains challenging in some languages. In this paper, we present a simple and efficient method to conduct zero-shot Chinese text-level dependency parsing by leveraging English discourse labeled data and parsing techniques. We first construct the Chinese-English mapping from the level of sentence and elementary discourse unit (EDU), and then exploit the parsing results of the corresponding English translations to obtain the discourse trees for the Chinese text. This method can automatically conduct Chinese discourse parsing, with no need of a large scale of Chinese labeled data. |
| Tasks | Dependency Parsing |
| Published | 2019-11-27 |
| URL | https://arxiv.org/abs/1911.12014v1 |
| https://arxiv.org/pdf/1911.12014v1.pdf | |
| PWC | https://paperswithcode.com/paper/zero-shot-chinese-discourse-dependency |
| Repo | |
| Framework | |
Selective Attention for Context-aware Neural Machine Translation
| Title | Selective Attention for Context-aware Neural Machine Translation |
| Authors | Sameen Maruf, André F. T. Martins, Gholamreza Haffari |
| Abstract | Despite the progress made in sentence-level NMT, current systems still fall short at achieving fluent, good quality translation for a full document. Recent works in context-aware NMT consider only a few previous sentences as context and may not scale to entire documents. To this end, we propose a novel and scalable top-down approach to hierarchical attention for context-aware NMT which uses sparse attention to selectively focus on relevant sentences in the document context and then attends to key words in those sentences. We also propose single-level attention approaches based on sentence or word-level information in the context. The document-level context representation, produced from these attention modules, is integrated into the encoder or decoder of the Transformer model depending on whether we use monolingual or bilingual context. Our experiments and evaluation on English-German datasets in different document MT settings show that our selective attention approach not only significantly outperforms context-agnostic baselines but also surpasses context-aware baselines in most cases. |
| Tasks | Machine Translation |
| Published | 2019-03-21 |
| URL | https://arxiv.org/abs/1903.08788v2 |
| https://arxiv.org/pdf/1903.08788v2.pdf | |
| PWC | https://paperswithcode.com/paper/selective-attention-for-context-aware-neural |
| Repo | |
| Framework | |
The JDDC Corpus: A Large-Scale Multi-Turn Chinese Dialogue Dataset for E-commerce Customer Service
| Title | The JDDC Corpus: A Large-Scale Multi-Turn Chinese Dialogue Dataset for E-commerce Customer Service |
| Authors | Meng Chen, Ruixue Liu, Lei Shen, Shaozu Yuan, Jingyan Zhou, Youzheng Wu, Xiaodong He, Bowen Zhou |
| Abstract | Human conversations are complicated and building a human-like dialogue agent is an extremely challenging task. With the rapid development of deep learning techniques, data-driven models become more and more prevalent which need a huge amount of real conversation data. In this paper, we construct a large-scale real scenario Chinese E-commerce conversation corpus, JDDC, with more than 1 million multi-turn dialogues, 20 million utterances, and 150 million words. The dataset reflects several characteristics of human-human conversations, e.g., goal-driven, and long-term dependency among the context. It also covers various dialogue types including task-oriented, chitchat and question-answering. Extra intent information and three well-annotated challenge sets are also provided. Then, we evaluate several retrieval-based and generative models to provide basic benchmark performance on the JDDC corpus. And we hope JDDC can serve as an effective testbed and benefit the development of fundamental research in dialogue task |
| Tasks | Question Answering |
| Published | 2019-11-22 |
| URL | https://arxiv.org/abs/1911.09969v4 |
| https://arxiv.org/pdf/1911.09969v4.pdf | |
| PWC | https://paperswithcode.com/paper/the-jddc-corpus-a-large-scale-multi-turn |
| Repo | |
| Framework | |
Deep Contextualized Self-training for Low Resource Dependency Parsing
| Title | Deep Contextualized Self-training for Low Resource Dependency Parsing |
| Authors | Guy Rotman, Roi Reichart |
| Abstract | Neural dependency parsing has proven very effective, achieving state-of-the-art results on numerous domains and languages. Unfortunately, it requires large amounts of labeled data, that is costly and laborious to create. In this paper we propose a self-training algorithm that alleviates this annotation bottleneck by training a parser on its own output. Our Deep Contextualized Self-training (DCST) algorithm utilizes representation models trained on sequence labeling tasks that are derived from the parser’s output when applied to unlabeled data, and integrates these models with the base parser through a gating mechanism. We conduct experiments across multiple languages, both in low resource in-domain and in cross-domain setups, and demonstrate that DCST substantially outperforms traditional self-training as well as recent semi-supervised training methods. |
| Tasks | Dependency Parsing |
| Published | 2019-11-11 |
| URL | https://arxiv.org/abs/1911.04286v1 |
| https://arxiv.org/pdf/1911.04286v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-contextualized-self-training-for-low |
| Repo | |
| Framework | |
A Novel Multi-Attention Driven System For Multi-Label Remote Sensing Image Classification
| Title | A Novel Multi-Attention Driven System For Multi-Label Remote Sensing Image Classification |
| Authors | Gencer Sumbul, Begüm Demir |
| Abstract | This paper presents a novel multi-attention driven system that jointly exploits Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN) in the context of multi-label remote sensing (RS) image classification. The proposed system consists of four main modules. The first module aims to extract preliminary local descriptors of RS image bands that can be associated to different spatial resolutions. To this end, we introduce a K-Branch CNN, in which each branch extracts descriptors of image bands that have the same spatial resolution. The second module aims to model spatial relationship among local descriptors. This is achieved by a bidirectional RNN architecture, in which Long Short-Term Memory nodes enrich local descriptors by considering spatial relationships of local areas (image patches). The third module aims to define multiple attention scores for local descriptors. This is achieved by a novel patch-based multi-attention mechanism that takes into account the joint occurrence of multiple land-cover classes and provides the attention-based local descriptors. The last module exploits these descriptors for multi-label RS image classification. Experimental results obtained on the BigEarthNet that is a large-scale Sentinel-2 benchmark archive show the effectiveness of the proposed method compared to a state of the art method. |
| Tasks | Image Classification, Remote Sensing Image Classification |
| Published | 2019-02-28 |
| URL | https://arxiv.org/abs/1902.11274v3 |
| https://arxiv.org/pdf/1902.11274v3.pdf | |
| PWC | https://paperswithcode.com/paper/a-cnn-rnn-framework-with-a-novel-patch-based |
| Repo | |
| Framework | |
MulGAN: Facial Attribute Editing by Exemplar
| Title | MulGAN: Facial Attribute Editing by Exemplar |
| Authors | Jingtao Guo, Zhenzhen Qian, Zuowei Zhou, Yi Liu |
| Abstract | Recent studies on face attribute editing by exemplars have achieved promising results due to the increasing power of deep convolutional networks and generative adversarial networks. These methods encode attribute-related information in images into the predefined region of the latent feature space by employing a pair of images with opposite attributes as input to train model, the face attribute transfer between the input image and the exemplar can be achieved by exchanging their attribute-related latent feature region. However, they suffer from three limitations: (1) the model must be trained using a pair of images with opposite attributes as input; (2) weak capability of editing multiple attributes by exemplars; (3) poor quality of generating image. Instead of imposing opposite-attribute constraints on the input image in order to make the attribute information of images be encoded in the predefined region of the latent feature space, in this work we directly apply the attribute labels constraint to the predefined region of the latent feature space. Meanwhile, an attribute classification loss is employed to make the model learn to extract the attribute-related information of images into the predefined latent feature region of the corresponding attribute, which enables our method to transfer multiple attributes of the exemplar simultaneously. Besides, a novel model structure is designed to enhance attribute transfer capabilities by exemplars while improve the quality of the generated image. Experiments demonstrate the effectiveness of our model on overcoming the above three limitations by comparing with other methods on the CelebA dataset. |
| Tasks | |
| Published | 2019-12-28 |
| URL | https://arxiv.org/abs/1912.12396v1 |
| https://arxiv.org/pdf/1912.12396v1.pdf | |
| PWC | https://paperswithcode.com/paper/mulgan-facial-attribute-editing-by-exemplar |
| Repo | |
| Framework | |
Self-Supervised Deep Active Accelerated MRI
| Title | Self-Supervised Deep Active Accelerated MRI |
| Authors | Kyong Hwan Jin, Michael Unser, Kwang Moo Yi |
| Abstract | We propose to simultaneously learn to sample and reconstruct magnetic resonance images (MRI) to maximize the reconstruction quality given a limited sample budget, in a self-supervised setup. Unlike existing deep methods that focus only on reconstructing given data, thus being passive, we go beyond the current state of the art by considering both the data acquisition and the reconstruction process within a single deep-learning framework. As our network learns to acquire data, the network is active in nature. In order to do so, we simultaneously train two neural networks, one dedicated to reconstruction and the other to progressive sampling, each with an automatically generated supervision signal that links them together. The two supervision signals are created through Monte Carlo tree search (MCTS). MCTS returns a better sampling pattern than what the current sampling network can give and, thus, a better final reconstruction. The sampling network is trained to mimic the MCTS results using the previous sampling network, thus being enhanced. The reconstruction network is trained to give the highest reconstruction quality, given the MCTS sampling pattern. Through this framework, we are able to train the two networks without providing any direct supervision on sampling. |
| Tasks | |
| Published | 2019-01-14 |
| URL | http://arxiv.org/abs/1901.04547v1 |
| http://arxiv.org/pdf/1901.04547v1.pdf | |
| PWC | https://paperswithcode.com/paper/self-supervised-deep-active-accelerated-mri |
| Repo | |
| Framework | |
Strategic Coalitions in Stochastic Games
| Title | Strategic Coalitions in Stochastic Games |
| Authors | Pavel Naumov, Kevin Ros |
| Abstract | The article introduces a notion of a stochastic game with failure states and proposes two logical systems with modality “coalition has a strategy to transition to a non-failure state with a given probability while achieving a given goal.” The logical properties of this modality depend on whether the modal language allows the empty coalition. The main technical results are a completeness theorem for a logical system with the empty coalition, a strong completeness theorem for the logical system without the empty coalition, and an incompleteness theorem which shows that there is no strongly complete logical system in the language with the empty coalition. |
| Tasks | |
| Published | 2019-10-10 |
| URL | https://arxiv.org/abs/1910.04489v1 |
| https://arxiv.org/pdf/1910.04489v1.pdf | |
| PWC | https://paperswithcode.com/paper/strategic-coalitions-in-stochastic-games |
| Repo | |
| Framework | |
Knowledge Infused Learning (K-IL): Towards Deep Incorporation of Knowledge in Deep Learning
| Title | Knowledge Infused Learning (K-IL): Towards Deep Incorporation of Knowledge in Deep Learning |
| Authors | Ugur Kursuncu, Manas Gaur, Amit Sheth |
| Abstract | Learning the underlying patterns in data goes beyond instance-based generalization to external knowledge represented in structured graphs or networks. Deep learning that primarily constitutes neural computing stream in AI has shown significant advances in probabilistically learning latent patterns using a multi-layered network of computational nodes (i.e., neurons/hidden units). Structured knowledge that underlies symbolic computing approaches and often supports reasoning, has also seen significant growth in recent years, in the form of broad-based (e.g., DBPedia, Yago) and domain, industry or application specific knowledge graphs. A common substrate with careful integration of the two will raise opportunities to develop neuro-symbolic learning approaches for AI, where conceptual and probabilistic representations are combined. As the incorporation of external knowledge will aid in supervising the learning of features for the model, deep infusion of representational knowledge from knowledge graphs within hidden layers will further enhance the learning process. Although much work remains, we believe that knowledge graphs will play an increasing role in developing hybrid neuro-symbolic intelligent systems (bottom-up deep learning with top-down symbolic computing) as well as in building explainable AI systems for which knowledge graphs will provide scaffolding for punctuating neural computing. In this position paper, we describe our motivation for such a neuro-symbolic approach and framework that combines knowledge graph and neural networks. |
| Tasks | Knowledge Graphs |
| Published | 2019-12-01 |
| URL | https://arxiv.org/abs/1912.00512v2 |
| https://arxiv.org/pdf/1912.00512v2.pdf | |
| PWC | https://paperswithcode.com/paper/knowledge-infused-learning-k-il-towards-deep |
| Repo | |
| Framework | |
