Paper Group NANR 27
Improving Distantly-Supervised Relation Extraction with Joint Label Embedding. Rand-NSG: Fast Accurate Billion-point Nearest Neighbor Search on a Single Node. Ranking of Potential Questions. PIEs: Pose Invariant Embeddings. MY-AKKHARA: A Romanization-based Burmese (Myanmar) Input Method. Asymmetric Cross-Guided Attention Network for Actor and Actio …
Improving Distantly-Supervised Relation Extraction with Joint Label Embedding
| Title | Improving Distantly-Supervised Relation Extraction with Joint Label Embedding |
| Authors | Linmei Hu, Luhao Zhang, Chuan Shi, Liqiang Nie, Weili Guan, Cheng Yang |
| Abstract | Distantly-supervised relation extraction has proven to be effective to find relational facts from texts. However, the existing approaches treat labels as independent and meaningless one-hot vectors, which cause a loss of potential label information for selecting valid instances. In this paper, we propose a novel multi-layer attention-based model to improve relation extraction with joint label embedding. The model makes full use of both structural information from Knowledge Graphs and textual information from entity descriptions to learn label embeddings through gating integration while avoiding the imposed noise with an attention mechanism. Then the learned label embeddings are used as another atten- tion over the instances (whose embeddings are also enhanced with the entity descriptions) for improving relation extraction. Extensive experiments demonstrate that our model significantly outperforms state-of-the-art methods. |
| Tasks | Knowledge Graphs, Relation Extraction |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1395/ |
| https://www.aclweb.org/anthology/D19-1395 | |
| PWC | https://paperswithcode.com/paper/improving-distantly-supervised-relation-2 |
| Repo | |
| Framework | |
Rand-NSG: Fast Accurate Billion-point Nearest Neighbor Search on a Single Node
| Title | Rand-NSG: Fast Accurate Billion-point Nearest Neighbor Search on a Single Node |
| Authors | Suhas Jayaram Subramanya, Fnu Devvrit, Harsha Vardhan Simhadri, Ravishankar Krishnawamy, Rohan Kadekodi |
| Abstract | Current state-of-the-art approximate nearest neighbor search (ANNS) algorithms generate indices that must be stored in main memory for fast high-recall search. This makes them expensive and limits the size of the dataset. We present a new graph-based indexing and search system called DiskANN that can index, store, and search a billion point database on a single workstation with just 64GB RAM and an inexpensive solid-state drive (SSD). Contrary to current wisdom, we demonstrate that the SSD-based indices built by DiskANN can meet all three desiderata for large-scale ANNS: high-recall, low query latency and high density (points indexed per node). On the billion point SIFT1B bigann dataset, DiskANN serves > 5000 queries a second with < 3ms mean latency and 95%+ 1-recall@1 on a 16 core machine, where state-of-the-art billion-point ANNS algorithms with similar memory footprint like FAISS and IVFOADC+G+P plateau at around 50% 1-recall@1. Alternately, in the high recall regime, DiskANN can index and serve 5 − 10x more points per node compared to state-of-the-art graph- based methods such as HNSW and NSG. Finally, as part of our overall DiskANN system, we introduce Vamana, a new graph-based ANNS index that is more versatile than the graph indices even for in-memory indices. |
| Tasks | |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/9527-rand-nsg-fast-accurate-billion-point-nearest-neighbor-search-on-a-single-node |
| http://papers.nips.cc/paper/9527-rand-nsg-fast-accurate-billion-point-nearest-neighbor-search-on-a-single-node.pdf | |
| PWC | https://paperswithcode.com/paper/rand-nsg-fast-accurate-billion-point-nearest |
| Repo | |
| Framework | |
Ranking of Potential Questions
| Title | Ranking of Potential Questions |
| Authors | Luise Schricker, Tatjana Scheffler |
| Abstract | Questions are an integral part of discourse. They provide structure and support the exchange of information. One linguistic theory, the Questions Under Discussion model, takes question structures as integral to the functioning of a coherent discourse. This theory has not been tested on the count of its validity for predicting observations in real dialogue data, however. In this submission, a system for ranking explicit and implicit questions by their appropriateness in a dialogue is presented. This system implements constraints and principles put forward in the linguistic literature. |
| Tasks | |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-2019/ |
| https://www.aclweb.org/anthology/P19-2019 | |
| PWC | https://paperswithcode.com/paper/ranking-of-potential-questions |
| Repo | |
| Framework | |
PIEs: Pose Invariant Embeddings
| Title | PIEs: Pose Invariant Embeddings |
| Authors | Chih-Hui Ho, Pedro Morgado, Amir Persekian, Nuno Vasconcelos |
| Abstract | The role of pose invariance in image recognition and retrieval is studied. A taxonomic classification of embeddings, according to their level of invariance, is introduced and used to clarify connections between existing embeddings, identify missing approaches, and propose invariant generalizations. This leads to a new family of pose invariant embeddings (PIEs), derived from existing approaches by a combination of two models, which follow from the interpretation of CNNs as estimators of class posterior probabilities: a view-to-object model and an object-to-class model. The new pose-invariant models are shown to have interesting properties, both theoretically and through experiments, where they outperform existing multiview approaches. Most notably, they achieve good performance for both 1) classification and retrieval, and 2) single and multiview inference. These are important properties for the design of real vision systems, where universal embeddings are preferable to task specific ones, and multiple images are usually not available at inference time. Finally, a new multiview dataset of real objects, imaged in the wild against complex backgrounds, is introduced. We believe that this is a much needed complement to the synthetic datasets in wide use and will contribute to the advancement of multiview recognition and retrieval. |
| Tasks | |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Ho_PIEs_Pose_Invariant_Embeddings_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Ho_PIEs_Pose_Invariant_Embeddings_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/pies-pose-invariant-embeddings |
| Repo | |
| Framework | |
MY-AKKHARA: A Romanization-based Burmese (Myanmar) Input Method
| Title | MY-AKKHARA: A Romanization-based Burmese (Myanmar) Input Method |
| Authors | Chenchen Ding, Masao Utiyama, Eiichiro Sumita |
| Abstract | MY-AKKHARA is a method used to input Burmese texts encoded in the Unicode standard, based on commonly accepted Latin transcription. By using this method, arbitrary Burmese strings can be accurately inputted with 26 lowercase Latin letters. Meanwhile, the 26 uppercase Latin letters are designed as shortcuts of lowercase letter sequences. The frequency of Burmese characters is considered in MY-AKKHARA to realize an efficient keystroke distribution on a QWERTY keyboard. Given that the Unicode standard has not been extensively used in digitization of Burmese, we hope that MY-AKKHARA can contribute to the widespread use of Unicode in Myanmar and can provide a platform for smart input methods for Burmese in the future. An implementation of MY-AKKHARA running in Windows is released at http://www2.nict.go.jp/astrec-att/member/ding/my-akkhara.html |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-3027/ |
| https://www.aclweb.org/anthology/D19-3027 | |
| PWC | https://paperswithcode.com/paper/my-akkhara-a-romanization-based-burmese |
| Repo | |
| Framework | |
Asymmetric Cross-Guided Attention Network for Actor and Action Video Segmentation From Natural Language Query
| Title | Asymmetric Cross-Guided Attention Network for Actor and Action Video Segmentation From Natural Language Query |
| Authors | Hao Wang, Cheng Deng, Junchi Yan, Dacheng Tao |
| Abstract | Actor and action video segmentation from natural language query aims to selectively segment the actor and its action in a video based on an input textual description. Previous works mostly focus on learning simple correlation between two heterogeneous features of vision and language via dynamic convolution or fully convolutional classification. However, they ignore the linguistic variation of natural language query and have difficulty in modeling global visual context, which leads to unsatisfactory segmentation performance. To address these issues, we propose an asymmetric cross-guided attention network for actor and action video segmentation from natural language query. Specifically, we frame an asymmetric cross-guided attention network, which consists of vision guided language attention to reduce the linguistic variation of input query and language guided vision attention to incorporate query-focused global visual context simultaneously. Moreover, we adopt multi-resolution fusion scheme and weighted loss for foreground and background pixels to obtain further performance improvement. Extensive experiments on Actor-Action Dataset Sentences and J-HMDB Sentences show that our proposed approach notably outperforms state-of-the-art methods. |
| Tasks | Video Semantic Segmentation |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Wang_Asymmetric_Cross-Guided_Attention_Network_for_Actor_and_Action_Video_Segmentation_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Wang_Asymmetric_Cross-Guided_Attention_Network_for_Actor_and_Action_Video_Segmentation_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/asymmetric-cross-guided-attention-network-for |
| Repo | |
| Framework | |
ClaimPortal: Integrated Monitoring, Searching, Checking, and Analytics of Factual Claims on Twitter
| Title | ClaimPortal: Integrated Monitoring, Searching, Checking, and Analytics of Factual Claims on Twitter |
| Authors | Sarthak Majithia, Fatma Arslan, Sumeet Lubal, Damian Jimenez, Priyank Arora, Josue Caraballo, Chengkai Li |
| Abstract | We present ClaimPortal, a web-based platform for monitoring, searching, checking, and analyzing English factual claims on Twitter from the American political domain. We explain the architecture of ClaimPortal, its components and functions, and the user interface. While the last several years have witnessed a substantial growth in interests and efforts in the area of computational fact-checking, ClaimPortal is a novel infrastructure in that fact-checkers have largely skipped factual claims in tweets. It can be a highly powerful tool to both general web users and fact-checkers. It will also be an educational resource in helping cultivate a society that is less susceptible to falsehoods. |
| Tasks | |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-3026/ |
| https://www.aclweb.org/anthology/P19-3026 | |
| PWC | https://paperswithcode.com/paper/claimportal-integrated-monitoring-searching |
| Repo | |
| Framework | |
AdvIT: Adversarial Frames Identifier Based on Temporal Consistency in Videos
| Title | AdvIT: Adversarial Frames Identifier Based on Temporal Consistency in Videos |
| Authors | Chaowei Xiao, Ruizhi Deng, Bo Li, Taesung Lee, Benjamin Edwards, Jinfeng Yi, Dawn Song, Mingyan Liu, Ian Molloy |
| Abstract | Deep neural networks (DNNs) have been widely applied in various applications, including autonomous driving and surveillance systems. However, DNNs are found to be vulnerable to adversarial examples, which are carefully crafted inputs aiming to mislead a learner to make incorrect predictions. While several defense and detection approaches are proposed for static image classification, many security-critical tasks use videos as their input and require efficient processing. In this paper, we propose an efficient and effective method advIT to detect adversarial frames within videos against different types of attacks based on temporal consistency property of videos. In particular, we apply optical flow estimation to the target and previous frames to generate pseudo frames and evaluate the consistency of the learner output between these pseudo frames and target. High inconsistency indicates that the target frame is adversarial. We conduct extensive experiments on various learning tasks including video semantic segmentation, human pose estimation, object detection, and action recognition, and demonstrate that we can achieve above 95% adversarial frame detection rate. To consider adaptive attackers, we show that even if an adversary has access to the detector and performs a strong adaptive attack based on the state of the art expectation of transformation method, the detection rate stays almost the same. We also tested the transferability among different optical flow estimators and show that it is hard for attackers to attack one and transfer the perturbation to others. In addition, as efficiency is important in video analysis, we show that advIT can achieve real-time detection in about 0.03–0.4 seconds. |
| Tasks | Autonomous Driving, Image Classification, Object Detection, Optical Flow Estimation, Pose Estimation, Semantic Segmentation, Video Semantic Segmentation |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Xiao_AdvIT_Adversarial_Frames_Identifier_Based_on_Temporal_Consistency_in_Videos_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Xiao_AdvIT_Adversarial_Frames_Identifier_Based_on_Temporal_Consistency_in_Videos_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/advit-adversarial-frames-identifier-based-on |
| Repo | |
| Framework | |
Residual Networks for Light Field Image Super-Resolution
| Title | Residual Networks for Light Field Image Super-Resolution |
| Authors | Shuo Zhang, Youfang Lin, Hao Sheng |
| Abstract | Light field cameras are considered to have many potential applications since angular and spatial information is captured simultaneously. However, the limited spatial resolution has brought lots of difficulties in developing related applications and becomes the main bottleneck of light field cameras. In this paper, a learning-based method using residual convolutional networks is proposed to reconstruct light fields with higher spatial resolution. The view images in one light field are first grouped into different image stacks with consistent sub-pixel offsets and fed into different network branches to implicitly learn inherent corresponding relations. The residual information in different spatial directions is then calculated from each branch and further integrated to supplement high-frequency details for the view image. Finally, a flexible solution is proposed to super-resolve entire light field images with various angular resolutions. Experimental results on synthetic and real-world datasets demonstrate that the proposed method outperforms other state-of-the-art methods by a large margin in both visual and numerical evaluations. Furthermore, the proposed method shows good performances in preserving the inherent epipolar property in light field images. |
| Tasks | Image Super-Resolution, Super-Resolution |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Zhang_Residual_Networks_for_Light_Field_Image_Super-Resolution_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Zhang_Residual_Networks_for_Light_Field_Image_Super-Resolution_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/residual-networks-for-light-field-image-super |
| Repo | |
| Framework | |
Fast Video Object Segmentation via Dynamic Targeting Network
| Title | Fast Video Object Segmentation via Dynamic Targeting Network |
| Authors | Lu Zhang, Zhe Lin, Jianming Zhang, Huchuan Lu, You He |
| Abstract | We propose a new model for fast and accurate video object segmentation. It consists of two convolutional neural networks, a Dynamic Targeting Network (DTN) and a Mask Refinement Network (MRN). DTN locates the object by dynamically focusing on regions of interest surrounding the target object. The target region is predicted by DTN via two sub-streams, Box Propagation (BP) and Box Re-identification (BR). The BP stream is faster but less effective at objects with large deformation or occlusion. The BR stream performs better in difficult scenarios at a higher computation cost. We propose a Decision Module (DM) to adaptively determine which sub-stream to use for each frame. Finally, MRN is exploited to predict segmentation within the target region. Experimental results on two public datasets demonstrate that the proposed model significantly outperforms existing methods without online training in both accuracy and efficiency, and is comparable to online training-based methods in accuracy with an order of magnitude faster speed. |
| Tasks | Semantic Segmentation, Video Object Segmentation, Video Semantic Segmentation |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Zhang_Fast_Video_Object_Segmentation_via_Dynamic_Targeting_Network_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Zhang_Fast_Video_Object_Segmentation_via_Dynamic_Targeting_Network_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/fast-video-object-segmentation-via-dynamic |
| Repo | |
| Framework | |
Face Video Deblurring Using 3D Facial Priors
| Title | Face Video Deblurring Using 3D Facial Priors |
| Authors | Wenqi Ren, Jiaolong Yang, Senyou Deng, David Wipf, Xiaochun Cao, Xin Tong |
| Abstract | Existing face deblurring methods only consider single frames and do not account for facial structure and identity information. These methods struggle to deblur face videos that exhibit significant pose variations and misalignment. In this paper we propose a novel face video deblurring network capitalizing on 3D facial priors. The model consists of two main branches: i) a face video deblurring sub-network based on an encoder-decoder architecture, and ii) a 3D face reconstruction and rendering branch for predicting 3D priors of salient facial structures and identity knowledge. These structures encourage the deblurring branch to generate sharp faces with detailed structures. Our method not only uses low-level information (i.e., image intensity), but also middle-level information (i.e., 3D facial structure) and high-level knowledge (i.e., identity content) to further explore spatial constraints of facial components from blurry face frames. Extensive experimental results demonstrate that the proposed algorithm performs favorably against the state-of-the-art methods. |
| Tasks | 3D Face Reconstruction, Deblurring, Face Reconstruction |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Ren_Face_Video_Deblurring_Using_3D_Facial_Priors_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Ren_Face_Video_Deblurring_Using_3D_Facial_Priors_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/face-video-deblurring-using-3d-facial-priors |
| Repo | |
| Framework | |
Proceedings of The 5th Workshop on BioNLP Open Shared Tasks
| Title | Proceedings of The 5th Workshop on BioNLP Open Shared Tasks |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5700/ |
| https://www.aclweb.org/anthology/D19-5700 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-5th-workshop-on-bionlp |
| Repo | |
| Framework | |
Dense Transformer Networks for Brain Electron Microscopy Image Segmentation
| Title | Dense Transformer Networks for Brain Electron Microscopy Image Segmentation |
| Authors | Jun Li, Yongjun Chen, Lei Cai, Ian Davidson, Shuiwang Ji |
| Abstract | The key idea of current deep learning methods for dense prediction is to apply a model on a regular patch centered on each pixel to make pixel-wise predictions. These methods are limited in the sense that the patches are determined by network architecture instead of learned from data. In this work, we propose the dense transformer networks, which can learn the shapes and sizes of patches from data. The dense transformer networks employ an encoder-decoder architecture, and a pair of dense transformer modules are inserted into each of the encoder and decoder paths. The novelty of this work is that we provide technical solutions for learning the shapes and sizes of patches from data and efficiently restoring the spatial correspondence required for dense prediction. The proposed dense transformer modules are differentiable, thus the entire network can be trained. We apply the proposed networks on biological image segmentation tasks and show superior performance is achieved in comparison to baseline methods. |
| Tasks | Electron Microscopy Image Segmentation, Semantic Segmentation |
| Published | 2019-08-10 |
| URL | https://doi.org/10.24963/ijcai.2019/401 |
| https://www.ijcai.org/proceedings/2019/0401.pdf | |
| PWC | https://paperswithcode.com/paper/dense-transformer-networks-for-brain-electron |
| Repo | |
| Framework | |
Coherence-based Modeling of Clinical Concepts Inferred from Heterogeneous Clinical Notes for ICU Patient Risk Stratification
| Title | Coherence-based Modeling of Clinical Concepts Inferred from Heterogeneous Clinical Notes for ICU Patient Risk Stratification |
| Authors | Tushaar Gangavarapu, Gokul S Krishnan, Sowmya Kamath S |
| Abstract | In hospitals, critical care patients are often susceptible to various complications that adversely affect their morbidity and mortality. Digitized patient data from Electronic Health Records (EHRs) can be utilized to facilitate risk stratification accurately and provide prioritized care. Existing clinical decision support systems are heavily reliant on the structured nature of the EHRs. However, the valuable patient-specific data contained in unstructured clinical notes are often manually transcribed into EHRs. The prolific use of extensive medical jargon, heterogeneity, sparsity, rawness, inconsistent abbreviations, and complex structure of the clinical notes poses significant challenges, and also results in a loss of information during the manual conversion process. In this work, we employ two coherence-based topic modeling approaches to model the free-text in the unstructured clinical nursing notes and capture its semantic textual features with the emphasis on human interpretability. Furthermore, we present FarSight, a long-term aggregation mechanism intended to detect the onset of disease with the earliest recorded symptoms and infections. We utilize the predictive capabilities of deep neural models for the clinical task of risk stratification through ICD-9 code group prediction. Our experimental validation on MIMIC-III (v1.4) database underlined the efficacy of FarSight with coherence-based topic modeling, in extracting discriminative clinical features from the unstructured nursing notes. The proposed approach achieved a superior predictive performance when benchmarked against the structured EHR data based state-of-the-art model, with an improvement of 11.50{%} in AUPRC and 1.16{%} in AUROC. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/K19-1095/ |
| https://www.aclweb.org/anthology/K19-1095 | |
| PWC | https://paperswithcode.com/paper/coherence-based-modeling-of-clinical-concepts |
| Repo | |
| Framework | |
The Relationship between Foreign Portfolio Investment, Foreign Direct Investment and Economic Performance of Nigerian Economy: (1980-2017): An Empirical Analysis
| Title | The Relationship between Foreign Portfolio Investment, Foreign Direct Investment and Economic Performance of Nigerian Economy: (1980-2017): An Empirical Analysis |
| Authors | Ekine, D.I, Ewubare, Dennis Brown, Ajie, Charity |
| Abstract | The study examined the impact of foreign portfolio investment and Foreign Direct Investment on the performance of the Nigerian Economy over a period of 1980-2017. The data used were purely secondary sourced from the central Bank of Nigeria statistical Bulletin and World Bank Development indicator. The ordinary least square (OLS) regression analysis was used. The findings revealed that the performance of the Nigerian Economy is directly related to inflow of foreign portfolio investment and foreign direct investment and it is also statistically significant at 5% level. This means that a good performance of the economy depends on the inflow of these variables, or that the variables serve as an engine of economic growth. The study therefore recommends that policy makers should work on improvement of economic incentives capable of mobilizing external resources to the country to engender macroeconomic stability. A stable economy will attract foreign investment and this result to increased inflow of foreign capital. |
| Tasks | |
| Published | 2019-07-30 |
| URL | https://ijbassnet.com/publication/249/details |
| https://ijbassnet.com/storage/app/publications/5d40188392a4211564481667.pdf | |
| PWC | https://paperswithcode.com/paper/the-relationship-between-foreign-portfolio |
| Repo | |
| Framework | |
