Paper Group NANR 56
Using Object Information for Spotting Text. Semantically Aware Urban 3D Reconstruction with Plane-Based Regularization. Joint Learning for Emotion Classification and Emotion Cause Detection. Proceedings of the AMTA 2018 Workshop on Technologies for MT of Low Resource Languages (LoResMT 2018). Translation API Cases and Classes (TAPICC). Embedding Re …
Using Object Information for Spotting Text
| Title | Using Object Information for Spotting Text |
| Authors | Shitala Prasad, Adams Wai Kin Kong |
| Abstract | Text spotting, also called text detection, is a challenging computer vision task because of cluttered backgrounds, diverse imaging environments, various text sizes and similarity between some objects and characters, e.g., tyre and âoâ. However, text spotting is a vital step in numerous AI and computer vision systems, such as autonomous robots and systems for visually impaired. Due to its potential applications and commercial values, researchers have proposed various deep architectures and methods for text spotting. These methods and architectures concentrate only on text in images, but neglect other information related to text. There exists a strong relationship between certain objects and the presence of text, such as signboards or the absence of text, such as trees. In this paper, a text spotting algorithm based on text and object dependency is proposed. The proposed algorithm consists of two sub-convolutional neural networks and three training stages. For this study, a new NTU-UTOI dataset containing over 22k non-synthetic images with 277k bounding boxes for text and 42 text-related object classes is established. According to our best knowledge, it is the second largest non-synthetic text image database. Experimental results on three benchmark datasets with clutter backgrounds, COCO-Text, MSRA-TD500 and SVT show that the proposed algorithm provides comparable performance to state-of-the-art text spotting methods. Experiments are also performed on our newly established dataset to investigate the effectiveness of object information for text spotting. The experimental results indicate that the object information contributes significantly on the performance gain. |
| Tasks | Text Spotting |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Shitala_Prasad_Using_Object_Information_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Shitala_Prasad_Using_Object_Information_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/using-object-information-for-spotting-text |
| Repo | |
| Framework | |
Semantically Aware Urban 3D Reconstruction with Plane-Based Regularization
| Title | Semantically Aware Urban 3D Reconstruction with Plane-Based Regularization |
| Authors | Thomas Holzmann, Michael Maurer, Friedrich Fraundorfer, Horst Bischof |
| Abstract | We propose a method for urban 3D reconstruction, which incorporates semantic information and plane priors within the reconstruction process in order to generate visually appealing 3D models. We introduce a plane detection algorithm using 3D lines, which detects a more complete and less spurious plane set compared to point-based methods in urban environments. Further, the proposed normalized visibility-based energy formulation eases the combination of several energy terms within a tetrahedra occupancy labeling algorithm and, hence, is well suited for combining it with class specific smoothness terms. As a result, we produce visually appealing and detailed building models (i.e., straight edges and planar surfaces) and a smooth reconstruction of the surroundings. |
| Tasks | 3D Reconstruction |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Thomas_Holzmann_Semantically_Aware_Urban_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Thomas_Holzmann_Semantically_Aware_Urban_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/semantically-aware-urban-3d-reconstruction |
| Repo | |
| Framework | |
Joint Learning for Emotion Classification and Emotion Cause Detection
| Title | Joint Learning for Emotion Classification and Emotion Cause Detection |
| Authors | Ying Chen, Wenjun Hou, Xiyao Cheng, Shoushan Li |
| Abstract | We present a neural network-based joint approach for emotion classification and emotion cause detection, which attempts to capture mutual benefits across the two sub-tasks of emotion analysis. Considering that emotion classification and emotion cause detection need different kinds of features (affective and event-based separately), we propose a joint encoder which uses a unified framework to extract features for both sub-tasks and a joint model trainer which simultaneously learns two models for the two sub-tasks separately. Our experiments on Chinese microblogs show that the joint approach is very promising. |
| Tasks | Emotion Classification, Emotion Recognition |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1066/ |
| https://www.aclweb.org/anthology/D18-1066 | |
| PWC | https://paperswithcode.com/paper/joint-learning-for-emotion-classification-and |
| Repo | |
| Framework | |
Proceedings of the AMTA 2018 Workshop on Technologies for MT of Low Resource Languages (LoResMT 2018)
| Title | Proceedings of the AMTA 2018 Workshop on Technologies for MT of Low Resource Languages (LoResMT 2018) |
| Authors | |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2018-03-01 |
| URL | https://www.aclweb.org/anthology/W18-2200/ |
| https://www.aclweb.org/anthology/W18-2200 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-amta-2018-workshop-on-1 |
| Repo | |
| Framework | |
Translation API Cases and Classes (TAPICC)
| Title | Translation API Cases and Classes (TAPICC) |
| Authors | Alan Melby |
| Abstract | |
| Tasks | |
| Published | 2018-03-01 |
| URL | https://www.aclweb.org/anthology/W18-2006/ |
| https://www.aclweb.org/anthology/W18-2006 | |
| PWC | https://paperswithcode.com/paper/translation-api-cases-and-classes-tapicc |
| Repo | |
| Framework | |
Embedding Register-Aware MT into the CAT Workflow
| Title | Embedding Register-Aware MT into the CAT Workflow |
| Authors | Corey Miller, Danielle Silverman, Vanesa Jurica, Elizabeth Richerson, Rodney Morris, Elisabeth Mallard |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2018-03-01 |
| URL | https://www.aclweb.org/anthology/W18-1920/ |
| https://www.aclweb.org/anthology/W18-1920 | |
| PWC | https://paperswithcode.com/paper/embedding-register-aware-mt-into-the-cat |
| Repo | |
| Framework | |
Translation Quality Standards
| Title | Translation Quality Standards |
| Authors | Bill Rivers |
| Abstract | |
| Tasks | |
| Published | 2018-03-01 |
| URL | https://www.aclweb.org/anthology/W18-2004/ |
| https://www.aclweb.org/anthology/W18-2004 | |
| PWC | https://paperswithcode.com/paper/translation-quality-standards |
| Repo | |
| Framework | |
Proceedings of the AMTA 2018 Workshop on Translation Quality Estimation and Automatic Post-Editing
| Title | Proceedings of the AMTA 2018 Workshop on Translation Quality Estimation and Automatic Post-Editing |
| Authors | |
| Abstract | |
| Tasks | Automatic Post-Editing, Machine Translation |
| Published | 2018-03-01 |
| URL | https://www.aclweb.org/anthology/W18-2100/ |
| https://www.aclweb.org/anthology/W18-2100 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-amta-2018-workshop-on |
| Repo | |
| Framework | |
Automatic Post-Editing and Machine Translation Quality Estimation at eBay
| Title | Automatic Post-Editing and Machine Translation Quality Estimation at eBay |
| Authors | Nicola Ueffing |
| Abstract | |
| Tasks | Automatic Post-Editing, Machine Translation |
| Published | 2018-03-01 |
| URL | https://www.aclweb.org/anthology/W18-2101/ |
| https://www.aclweb.org/anthology/W18-2101 | |
| PWC | https://paperswithcode.com/paper/automatic-post-editing-and-machine |
| Repo | |
| Framework | |
Joint Camera Spectral Sensitivity Selection and Hyperspectral Image Recovery
| Title | Joint Camera Spectral Sensitivity Selection and Hyperspectral Image Recovery |
| Authors | Ying Fu, Tao Zhang, Yinqiang Zheng, Debing Zhang, Hua Huang |
| Abstract | Hyperspectral image (HSI) recovery from a single RGB image has attracted much attention, whose performance has recently been shown to be sensitive to the camera spectral sensitivity (CSS). In this paper, we present an efficient convolutional neural network (CNN) based method, which can jointly select the optimal CSS from a candidate dataset and learn a mapping to recover HSI from a single RGB image captured with this algorithmically selected camera. Given a specific CSS, we first present a HSI recovery network, which accounts for the underlying characteristics of the HSI, including spectral nonlinear mapping and spatial similarity. Later, we append a CSS selection layer onto the recovery network, and the optimal CSS can thus be automatically determined from the network weights under the nonnegative sparse constraint. Experimental results show that our HSI recovery network outperforms state-of-the-art methods in terms of both quantitative metrics and perceptive quality, and the selection layer always returns a CSS consistent to the best one determined by exhaustive search. |
| Tasks | |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Ying_Fu_Joint_Camera_Spectral_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Ying_Fu_Joint_Camera_Spectral_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/joint-camera-spectral-sensitivity-selection |
| Repo | |
| Framework | |
Saliency Detection in 360° Videos
| Title | Saliency Detection in 360° Videos |
| Authors | Ziheng Zhang, Yanyu Xu, Jingyi Yu, Shenghua Gao |
| Abstract | This paper presents a novel spherical convolutional neural network based scheme for saliency detection for 360° videos. Specifically, in our spherical convolution neural network definition, kernel is defined on a spherical crown, and the convolution involves the rotation of the kernel along the sphere. Considering that the 360° videos are usually stored with equirectangular panorama, we propose to implement the spherical convolution on panorama by stretching and rotating the kernel based on the location of patch to be convolved. Compared with existing spherical convolution, our definition has the parameter sharing property, which would greatly reduce the parameters to be learned. We further take the temporal coherence of the viewing process into consideration, and propose a sequential saliency detection by leveraging a spherical U-Net. To validate our approach, we construct a large-scale 360° videos saliency detection benchmark that consists of 104 360° videos viewed by 20+ human subjects. Comprehensive experiments validate the effectiveness of our spherical U-net for 360° video saliency detection. |
| Tasks | Saliency Detection, Video Saliency Detection |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Ziheng_Zhang_Saliency_Detection_in_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Ziheng_Zhang_Saliency_Detection_in_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/saliency-detection-in-360a-videos |
| Repo | |
| Framework | |
BASHI: A Corpus of Wall Street Journal Articles Annotated with Bridging Links
| Title | BASHI: A Corpus of Wall Street Journal Articles Annotated with Bridging Links |
| Authors | Ina R{"o}siger |
| Abstract | |
| Tasks | Coreference Resolution, Natural Language Inference |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1058/ |
| https://www.aclweb.org/anthology/L18-1058 | |
| PWC | https://paperswithcode.com/paper/bashi-a-corpus-of-wall-street-journal |
| Repo | |
| Framework | |
Increasing In-Class Similarity by Retrofitting Embeddings with Demographic Information
| Title | Increasing In-Class Similarity by Retrofitting Embeddings with Demographic Information |
| Authors | Dirk Hovy, Tommaso Fornaciari |
| Abstract | Most text-classification approaches represent the input based on textual features, either feature-based or continuous. However, this ignores strong non-linguistic similarities like homophily: people within a demographic group use language more similar to each other than to non-group members. We use homophily cues to retrofit text-based author representations with non-linguistic information, and introduce a trade-off parameter. This approach increases in-class similarity between authors, and improves classification performance by making classes more linearly separable. We evaluate the effect of our method on two author-attribute prediction tasks with various training-set sizes and parameter settings. We find that our method can significantly improve classification performance, especially when the number of labels is large and limited labeled data is available. It is potentially applicable as preprocessing step to any text-classification task. |
| Tasks | Semantic Textual Similarity, Text Classification |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1070/ |
| https://www.aclweb.org/anthology/D18-1070 | |
| PWC | https://paperswithcode.com/paper/increasing-in-class-similarity-by |
| Repo | |
| Framework | |
A Reduction for Efficient LDA Topic Reconstruction
| Title | A Reduction for Efficient LDA Topic Reconstruction |
| Authors | Matteo Almanza, Flavio Chierichetti, Alessandro Panconesi, Andrea Vattani |
| Abstract | We present a novel approach for LDA (Latent Dirichlet Allocation) topic reconstruction. The main technical idea is to show that the distribution over the documents generated by LDA can be transformed into a distribution for a much simpler generative model in which documents are generated from {\em the same set of topics} but have a much simpler structure: documents are single topic and topics are chosen uniformly at random. Furthermore, this reduction is approximation preserving, in the sense that approximate distributions– the only ones we can hope to compute in practice– are mapped into approximate distribution in the simplified world. This opens up the possibility of efficiently reconstructing LDA topics in a roundabout way. Compute an approximate document distribution from the given corpus, transform it into an approximate distribution for the single-topic world, and run a reconstruction algorithm in the uniform, single topic world– a much simpler task than direct LDA reconstruction. Indeed, we show the viability of the approach by giving very simple algorithms for a generalization of two notable cases that have been studied in the literature, $p$-separability and Gibbs sampling for matrix-like topics. |
| Tasks | |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/8012-a-reduction-for-efficient-lda-topic-reconstruction |
| http://papers.nips.cc/paper/8012-a-reduction-for-efficient-lda-topic-reconstruction.pdf | |
| PWC | https://paperswithcode.com/paper/a-reduction-for-efficient-lda-topic |
| Repo | |
| Framework | |
Improving Beam Search by Removing Monotonic Constraint for Neural Machine Translation
| Title | Improving Beam Search by Removing Monotonic Constraint for Neural Machine Translation |
| Authors | Raphael Shu, Hideki Nakayama |
| Abstract | To achieve high translation performance, neural machine translation models usually rely on the beam search algorithm for decoding sentences. The beam search finds good candidate translations by considering multiple hypotheses of translations simultaneously. However, as the algorithm produces hypotheses in a monotonic left-to-right order, a hypothesis can not be revisited once it is discarded. We found such monotonicity forces the algorithm to sacrifice some good decoding paths. To mitigate this problem, we relax the monotonic constraint of the beam search by maintaining all found hypotheses in a single priority queue and using a universal score function for hypothesis selection. The proposed algorithm allows discarded hypotheses to be recovered in a later step. Despite its simplicity, we show that the proposed decoding algorithm enhances the quality of selected hypotheses and improve the translations even for high-performance models in English-Japanese translation task. |
| Tasks | Language Modelling, Machine Translation |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/P18-2054/ |
| https://www.aclweb.org/anthology/P18-2054 | |
| PWC | https://paperswithcode.com/paper/improving-beam-search-by-removing-monotonic |
| Repo | |
| Framework | |
