Paper Group NANR 191
Learning Pose Grammar for Monocular 3D Pose Estimation. MILAB at SemEval-2019 Task 3: Multi-View Turn-by-Turn Model for Context-Aware Sentiment Analysis. Exploring Context and Visual Pattern of Relationship for Scene Graph Generation. Global Under-Resourced Media Translation (GoURMET). ClothFlow: A Flow-Based Model for Clothed Person Generation. Di …
Learning Pose Grammar for Monocular 3D Pose Estimation
| Title | Learning Pose Grammar for Monocular 3D Pose Estimation |
| Authors | Yuanlu Xu, Wenguan Wang, Xiaobai Liu, Jianwen Xie, Song-Chun Zhu |
| Abstract | In this paper, we propose a pose grammar to tackle the problem of 3D human pose estimation from a monocular RGB image. Our model takes estimated 2D pose as the input and learns a generalized 2D-3D mapping function to leverage into 3D pose. The proposed model consists of a base network which efficiently captures pose-aligned features and a hierarchy of Bi-directional RNNs (BRNNs) on the top to explicitly incorporate a set of knowledge regarding human body configuration (i.e., kinematics, symmetry, motor coordination). The proposed model thus enforces high-level constraints over human poses. In learning, we develop a data augmentation algorithm to further improve model robustness against appearance variations and cross-view generalization ability. We validate our method on public 3D human pose benchmarks and propose a new evaluation protocol working on cross-view setting to verify the generalization capability of different methods. We empirically observe that most state-of-the-art methods encounter difficulty under such setting while our method can well handle such challenges. |
| Tasks | 3D Human Pose Estimation, 3D Pose Estimation, Data Augmentation, Pose Estimation |
| Published | 2019-06-01 |
| URL | http://www.stat.ucla.edu/~jxie/personalpage_file/publications/3dpose_pami19.pdf |
| https://pdfs.semanticscholar.org/6c19/6c24541b05d4b1352e4bc9712d0b3809a8c3.pdf | |
| PWC | https://paperswithcode.com/paper/learning-pose-grammar-for-monocular-3d-pose |
| Repo | |
| Framework | |
MILAB at SemEval-2019 Task 3: Multi-View Turn-by-Turn Model for Context-Aware Sentiment Analysis
| Title | MILAB at SemEval-2019 Task 3: Multi-View Turn-by-Turn Model for Context-Aware Sentiment Analysis |
| Authors | Yoonhyung Lee, Yanghoon Kim, Kyomin Jung |
| Abstract | This paper describes our system for SemEval-2019 Task 3: EmoContext, which aims to predict the emotion of the third utterance considering two preceding utterances in a dialogue. To address this challenge of predicting the emotion considering its context, we propose a Multi-View Turn-by-Turn (MVTT) model. Firstly, MVTT model generates vectors from each utterance using two encoders: word-level Bi-GRU encoder (WLE) and character-level CNN encoder (CLE). Then, MVTT grasps contextual information by combining the vectors and predict the emotion with the contextual information. We conduct experiments on the effect of vector encoding and vector combination. Our final MVTT model achieved 0.7634 microaveraged F1 score. |
| Tasks | Sentiment Analysis |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2043/ |
| https://www.aclweb.org/anthology/S19-2043 | |
| PWC | https://paperswithcode.com/paper/milab-at-semeval-2019-task-3-multi-view-turn |
| Repo | |
| Framework | |
Exploring Context and Visual Pattern of Relationship for Scene Graph Generation
| Title | Exploring Context and Visual Pattern of Relationship for Scene Graph Generation |
| Authors | Wenbin Wang, Ruiping Wang, Shiguang Shan, Xilin Chen |
| Abstract | Relationship is the core of scene graph, but its prediction is far from satisfying because of its complex visual diversity. To alleviate this problem, we treat relationship as an abstract object, exploring not only significative visual pattern but contextual information for it, which are two key aspects when considering object recognition. Our observation on current datasets reveals that there exists intimate association among relationships. Therefore, inspired by the successful application of context to object-oriented tasks, we especially construct context for relationships where all of them are gathered so that the recognition could benefit from their association. Moreover, accurate recognition needs discriminative visual pattern for object, and so does relationship. In order to discover effective pattern for relationship, traditional relationship feature extraction methods such as using union region or combination of subject-object feature pairs are replaced with our proposed intersection region which focuses on more essential parts. Therefore, we present our so-called Relationship Context - InterSeCtion Region (CISC) method. Experiments for scene graph generation on Visual Genome dataset and visual relationship prediction on VRD dataset indicate that both the relationship context and intersection region improve performances and realize anticipated functions. |
| Tasks | Graph Generation, Object Recognition, Scene Graph Generation |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Wang_Exploring_Context_and_Visual_Pattern_of_Relationship_for_Scene_Graph_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Wang_Exploring_Context_and_Visual_Pattern_of_Relationship_for_Scene_Graph_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/exploring-context-and-visual-pattern-of |
| Repo | |
| Framework | |
Global Under-Resourced Media Translation (GoURMET)
| Title | Global Under-Resourced Media Translation (GoURMET) |
| Authors | Alex Birch, ra, Barry Haddow, Ivan Tito, Antonio Valerio Miceli Barone, Rachel Bawden, Felipe S{'a}nchez-Mart{'\i}nez, Mikel L. Forcada, Miquel Espl{`a}-Gomis, V{'\i}ctor S{'a}nchez-Cartagena, Juan Antonio P{'e}rez-Ortiz, Wilker Aziz, Andrew Secker, Peggy van der Kreeft |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-6723/ |
| https://www.aclweb.org/anthology/W19-6723 | |
| PWC | https://paperswithcode.com/paper/global-under-resourced-media-translation |
| Repo | |
| Framework | |
ClothFlow: A Flow-Based Model for Clothed Person Generation
| Title | ClothFlow: A Flow-Based Model for Clothed Person Generation |
| Authors | Xintong Han, Xiaojun Hu, Weilin Huang, Matthew R. Scott |
| Abstract | We present ClothFlow, an appearance-flow-based generative model to synthesize clothed person for posed-guided person image generation and virtual try-on. By estimating a dense flow between source and target clothing regions, ClothFlow effectively models the geometric changes and naturally transfers the appearance to synthesize novel images as shown in Figure 1. We achieve this with a three-stage framework: 1) Conditioned on a target pose, we first estimate a person semantic layout to provide richer guidance to the generation process. 2) Built on two feature pyramid networks, a cascaded flow estimation network then accurately estimates the appearance matching between corresponding clothing regions. The resulting dense flow warps the source image to flexibly account for deformations. 3) Finally, a generative network takes the warped clothing regions as inputs and renders the target view. We conduct extensive experiments on the DeepFashion dataset for pose-guided person image generation and on the VITON dataset for the virtual try-on task. Strong qualitative and quantitative results validate the effectiveness of our method. |
| Tasks | Image Generation |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Han_ClothFlow_A_Flow-Based_Model_for_Clothed_Person_Generation_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Han_ClothFlow_A_Flow-Based_Model_for_Clothed_Person_Generation_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/clothflow-a-flow-based-model-for-clothed |
| Repo | |
| Framework | |
Dimension-Free Bounds for Low-Precision Training
| Title | Dimension-Free Bounds for Low-Precision Training |
| Authors | Zheng Li, Christopher De Sa |
| Abstract | Low-precision training is a promising way of decreasing the time and energy cost of training machine learning models. Previous work has analyzed low-precision training algorithms, such as low-precision stochastic gradient descent, and derived theoretical bounds on their convergence rates. These bounds tend to depend on the dimension of the model $d$ in that the number of bits needed to achieve a particular error bound increases as $d$ increases. This is undesirable because a motivating application for low-precision training is large-scale models, such as deep learning, where $d$ can be huge. In this paper, we prove dimension-independent bounds for low-precision training algorithms that use fixed-point arithmetic, which lets us better understand what affects the convergence of these algorithms as parameters scale. Our methods also generalize naturally to let us prove new convergence bounds on low-precision training with other quantization schemes, such as low-precision floating-point computation and logarithmic quantization. |
| Tasks | Quantization |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=ryeX-nC9YQ |
| https://openreview.net/pdf?id=ryeX-nC9YQ | |
| PWC | https://paperswithcode.com/paper/dimension-free-bounds-for-low-precision |
| Repo | |
| Framework | |
ChatEval: A Tool for Chatbot Evaluation
| Title | ChatEval: A Tool for Chatbot Evaluation |
| Authors | Jo{~a}o Sedoc, Daphne Ippolito, Arun Kirubarajan, Jai Thirani, Lyle Ungar, Chris Callison-Burch |
| Abstract | Open-domain dialog systems (i.e. chatbots) are difficult to evaluate. The current best practice for analyzing and comparing these dialog systems is the use of human judgments. However, the lack of standardization in evaluation procedures, and the fact that model parameters and code are rarely published hinder systematic human evaluation experiments. We introduce a unified framework for human evaluation of chatbots that augments existing tools and provides a web-based hub for researchers to share and compare their dialog systems. Researchers can submit their trained models to the ChatEval web interface and obtain comparisons with baselines and prior work. The evaluation code is open-source to ensure standardization and transparency. In addition, we introduce open-source baseline models and evaluation datasets. ChatEval can be found at https://chateval.org. |
| Tasks | Chatbot |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-4011/ |
| https://www.aclweb.org/anthology/N19-4011 | |
| PWC | https://paperswithcode.com/paper/chateval-a-tool-for-chatbot-evaluation |
| Repo | |
| Framework | |
Adversarial Attack on Sentiment Classification
| Title | Adversarial Attack on Sentiment Classification |
| Authors | Yi-Ting (Alicia) Tsai, Min-Chu Yang, Han-Yu Chen |
| Abstract | In this paper, we propose a white-box attack algorithm called {}Global Search{''} method and compare it with a simple misspelling noise and a more sophisticated and common white-box attack approach called {}Greedy Search{''}. The attack methods are evaluated on the Convolutional Neural Network (CNN) sentiment classifier trained on the IMDB movie review dataset. The attack success rate is used to evaluate the effectiveness of the attack methods and the perplexity of the sentences is used to measure the degree of distortion of the generated adversarial examples. The experiment results show that the proposed {``}Global Search{''} method generates more powerful adversarial examples with less distortion or less modification to the source text. | |
| Tasks | Adversarial Attack, Sentiment Analysis |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/papers/W/W19/W19-3653/ |
| https://www.aclweb.org/anthology/W19-3653 | |
| PWC | https://paperswithcode.com/paper/adversarial-attack-on-sentiment |
| Repo | |
| Framework | |
The organization of sound inventories: A study on obstruent gaps
| Title | The organization of sound inventories: A study on obstruent gaps |
| Authors | Sheng-Fu Wang |
| Abstract | |
| Tasks | |
| Published | 2019-01-01 |
| URL | https://www.aclweb.org/anthology/W19-0120/ |
| https://www.aclweb.org/anthology/W19-0120 | |
| PWC | https://paperswithcode.com/paper/the-organization-of-sound-inventories-a-study |
| Repo | |
| Framework | |
Enabling Search and Collaborative Assembly of Causal Interactions Extracted from Multilingual and Multi-domain Free Text
| Title | Enabling Search and Collaborative Assembly of Causal Interactions Extracted from Multilingual and Multi-domain Free Text |
| Authors | George C. G. Barbosa, Zechy Wong, Gus Hahn-Powell, Dane Bell, Rebecca Sharp, Marco A. Valenzuela-Esc{'a}rcega, Mihai Surdeanu |
| Abstract | Many of the most pressing current research problems (e.g., public health, food security, or climate change) require multi-disciplinary collaborations. In order to facilitate this process, we propose a system that incorporates multi-domain extractions of causal interactions into a single searchable knowledge graph. Our system enables users to search iteratively over direct and indirect connections in this knowledge graph, and collaboratively build causal models in real time. To enable the aggregation of causal information from multiple languages, we extend an open-domain machine reader to Portuguese. The new Portuguese reader extracts over 600 thousand causal statements from 120 thousand Portuguese publications with a precision of 62{%}, which demonstrates the value of mining multilingual scientific information. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-4003/ |
| https://www.aclweb.org/anthology/N19-4003 | |
| PWC | https://paperswithcode.com/paper/enabling-search-and-collaborative-assembly-of |
| Repo | |
| Framework | |
Analysis of Quantized Models
| Title | Analysis of Quantized Models |
| Authors | Lu Hou, Ruiliang Zhang, James T. Kwok |
| Abstract | Weight-quantized networks have small storage and fast inference, but training can still be time-consuming. This can be improved with distributed learning. To reduce the high communication cost due to worker-server synchronization, recently gradient quantization has also been proposed to train networks with full-precision weights. In this paper, we theoretically study how the combination of both weight and gradient quantization affects convergence. We show that (i) weight-quantized networks converge to an error related to the weight quantization resolution and weight dimension; (ii) quantizing gradients slows convergence by a factor related to the gradient quantization resolution and dimension; and (iii) clipping the gradient before quantization renders this factor dimension-free, thus allowing the use of fewer bits for gradient quantization. Empirical experiments confirm the theoretical convergence results, and demonstrate that quantized networks can speed up training and have comparable performance as full-precision networks. |
| Tasks | Quantization |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=ryM_IoAqYX |
| https://openreview.net/pdf?id=ryM_IoAqYX | |
| PWC | https://paperswithcode.com/paper/analysis-of-quantized-models |
| Repo | |
| Framework | |
Geometry aware convolutional filters for omnidirectional images representation
| Title | Geometry aware convolutional filters for omnidirectional images representation |
| Authors | Renata Khasanova, Pascal Frossard |
| Abstract | Due to their wide field of view, omnidirectional cameras are frequently used by autonomous vehicles, drones and robots for navigation and other computer vision tasks. The images captured by such cameras, are often analysed and classified with techniques designed for planar images that unfortunately fail to properly handle the native geometry of such images. That results in suboptimal performance, and lack of truly meaningful visual features. In this paper we aim at improving popular deep convolutional neural networks so that they can properly take into account the specific properties of omnidirectional data. In particular we propose an algorithm that adapts convolutional layers, which often serve as a core building block of a CNN, to the properties of omnidirectional images. Thus, our filters have a shape and size that adapts with the location on the omnidirectional image. We show that our method is not limited to spherical surfaces and is able to incorporate the knowledge about any kind of omnidirectional geometry inside the deep learning network. As depicted by our experiments, our method outperforms the existing deep neural network techniques for omnidirectional image classification and compression tasks. |
| Tasks | Autonomous Vehicles, Image Classification |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=H1fF0iR9KX |
| https://openreview.net/pdf?id=H1fF0iR9KX | |
| PWC | https://paperswithcode.com/paper/geometry-aware-convolutional-filters-for |
| Repo | |
| Framework | |
Learning shared manifold representation of images and attributes for generalized zero-shot learning
| Title | Learning shared manifold representation of images and attributes for generalized zero-shot learning |
| Authors | Masahiro Suzuki, Yusuke Iwasawa, Yutaka Matsuo |
| Abstract | Many of the zero-shot learning methods have realized predicting labels of unseen images by learning the relations between images and pre-defined class-attributes. However, recent studies show that, under the more realistic generalized zero-shot learning (GZSL) scenarios, these approaches severely suffer from the issue of biased prediction, i.e., their classifier tends to predict all the examples from both seen and unseen classes as one of the seen classes. The cause of this problem is that they cannot properly learn a mapping to the representation space generalized to the unseen classes since the training set does not include any unseen class information. To solve this, we propose a concept to learn a mapping that embeds both images and attributes to the shared representation space that can be generalized even for unseen classes by interpolating from the information of seen classes, which we refer to shared manifold learning. Furthermore, we propose modality invariant variational autoencoders, which can perform shared manifold learning by training variational autoencoders with both images and attributes as inputs. The empirical validation of well-known datasets in GZSL shows that our method achieves the significantly superior performances to the existing relation-based studies. |
| Tasks | Zero-Shot Learning |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=Hkesr205t7 |
| https://openreview.net/pdf?id=Hkesr205t7 | |
| PWC | https://paperswithcode.com/paper/learning-shared-manifold-representation-of |
| Repo | |
| Framework | |
A CASE STUDY ON OPTIMAL DEEP LEARNING MODEL FOR UAVS
| Title | A CASE STUDY ON OPTIMAL DEEP LEARNING MODEL FOR UAVS |
| Authors | Chandan Kumar, Subrahmanyam Vaddi, Aishwarya Sarkar |
| Abstract | Over the passage of time Unmanned Autonomous Vehicles (UAVs), especially Autonomous flying drones grabbed a lot of attention in Artificial Intelligence. Since electronic technology is getting smaller, cheaper and more efficient, huge advancement in the study of UAVs has been observed recently. From monitoring floods, discerning the spread of algae in water bodies to detecting forest trail, their application is far and wide. Our work is mainly focused on autonomous flying drones where we establish a case study towards efficiency, robustness and accuracy of UAVs where we showed our results well supported through experiments. We provide details of the software and hardware architecture used in the study. We further discuss about our implementation algorithms and present experiments that provide a comparison between three different state-of-the-art algorithms namely TrailNet, InceptionResnet and MobileNet in terms of accuracy, robustness, power consumption and inference time. In our study, we have shown that MobileNet has produced better results with very less computational requirement and power consumption. We have also reported the challenges we have faced during our work as well as a brief discussion on our future work to improve safety features and performance. |
| Tasks | Autonomous Vehicles |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=Syx9rnRcYm |
| https://openreview.net/pdf?id=Syx9rnRcYm | |
| PWC | https://paperswithcode.com/paper/a-case-study-on-optimal-deep-learning-model |
| Repo | |
| Framework | |
Translating Terminologies: A Comparative Examination of NMT and PBSMT Systems
| Title | Translating Terminologies: A Comparative Examination of NMT and PBSMT Systems |
| Authors | Long-Huei Chen, Kyo Kageura |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-6715/ |
| https://www.aclweb.org/anthology/W19-6715 | |
| PWC | https://paperswithcode.com/paper/translating-terminologies-a-comparative |
| Repo | |
| Framework | |
