Paper Group NANR 216
Pose Partition Networks for Multi-Person Pose Estimation. Modeling Violations of Selectional Restrictions with Distributional Semantics. Overcoming Catastrophic Interference using Conceptor-Aided Backpropagation. Exploring Asymmetric Encoder-Decoder Structure for Context-based Sentence Representation Learning. 3D Recurrent Neural Networks with Cont …
Pose Partition Networks for Multi-Person Pose Estimation
| Title | Pose Partition Networks for Multi-Person Pose Estimation |
| Authors | Xuecheng Nie, Jiashi Feng, Junliang Xing, Shuicheng Yan |
| Abstract | This paper proposes a novel Pose Partition Network (PPN) to address the challenging multi-person pose estimation problem. The proposed PPN is favorably featured by low complexity and high accuracy of joint detection and partition. In particular, PPN performs dense regressions from global joint candidates within a specific embedding space, which is parameterized by centroids of persons, to efficiently generate robust person detection and joint partitions. Then, PPN infers joint configurations of person poses through conducting graph partition for each person detection locally, utilizing reliable global affinity cues. In this way, PPN reduces computation complexity and improves multi-person pose estimation significantly. We implement PPN with the Hourglass architecture as the backbone network to simultaneously learn joint detector and dense regressor. Extensive experiments on benchmarks MPII Human Pose Multi-Person, extended PASCAL-Person-Part, and WAF, show the efficiency of PPN with new state-of-the-art performance. |
| Tasks | Human Detection, Multi-Person Pose Estimation, Pose Estimation |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Xuecheng_Nie_Pose_Partition_Networks_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Xuecheng_Nie_Pose_Partition_Networks_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/pose-partition-networks-for-multi-person-pose |
| Repo | |
| Framework | |
Modeling Violations of Selectional Restrictions with Distributional Semantics
| Title | Modeling Violations of Selectional Restrictions with Distributional Semantics |
| Authors | Emmanuele Chersoni, Adri{`a} Torrens Urrutia, Philippe Blache, Aless Lenci, ro |
| Abstract | Distributional Semantic Models have been successfully used for modeling selectional preferences in a variety of scenarios, since distributional similarity naturally provides an estimate of the degree to which an argument satisfies the requirement of a given predicate. However, we argue that the performance of such models on rare verb-argument combinations has received relatively little attention: it is not clear whether they are able to distinguish the combinations that are simply atypical, or implausible, from the semantically anomalous ones, and in particular, they have never been tested on the task of modeling their differences in processing complexity. In this paper, we compare two different models of thematic fit by testing their ability of identifying violations of selectional restrictions in two datasets from the experimental studies. |
| Tasks | |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/W18-4603/ |
| https://www.aclweb.org/anthology/W18-4603 | |
| PWC | https://paperswithcode.com/paper/modeling-violations-of-selectional |
| Repo | |
| Framework | |
Overcoming Catastrophic Interference using Conceptor-Aided Backpropagation
| Title | Overcoming Catastrophic Interference using Conceptor-Aided Backpropagation |
| Authors | Xu He, Herbert Jaeger |
| Abstract | Catastrophic interference has been a major roadblock in the research of continual learning. Here we propose a variant of the back-propagation algorithm, “Conceptor-Aided Backprop” (CAB), in which gradients are shielded by conceptors against degradation of previously learned tasks. Conceptors have their origin in reservoir computing, where they have been previously shown to overcome catastrophic forgetting. CAB extends these results to deep feedforward networks. On the disjoint and permuted MNIST tasks, CAB outperforms two other methods for coping with catastrophic interference that have recently been proposed. |
| Tasks | Continual Learning |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=B1al7jg0b |
| https://openreview.net/pdf?id=B1al7jg0b | |
| PWC | https://paperswithcode.com/paper/overcoming-catastrophic-interference-using |
| Repo | |
| Framework | |
Exploring Asymmetric Encoder-Decoder Structure for Context-based Sentence Representation Learning
| Title | Exploring Asymmetric Encoder-Decoder Structure for Context-based Sentence Representation Learning |
| Authors | Shuai Tang, Hailin Jin, Chen Fang, Zhaowen Wang, Virginia R. de Sa |
| Abstract | Context information plays an important role in human language understanding, and it is also useful for machines to learn vector representations of language. In this paper, we explore an asymmetric encoder-decoder structure for unsupervised context-based sentence representation learning. As a result, we build an encoder-decoder architecture with an RNN encoder and a CNN decoder, and we show that neither an autoregressive decoder nor an RNN decoder is required. We further combine a suite of effective designs to significantly improve model efficiency while also achieving better performance. Our model is trained on two different large unlabeled corpora, and in both cases transferability is evaluated on a set of downstream language understanding tasks. We empirically show that our model is simple and fast while producing rich sentence representations that excel in downstream tasks. |
| Tasks | Representation Learning |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=Bk7wvW-C- |
| https://openreview.net/pdf?id=Bk7wvW-C- | |
| PWC | https://paperswithcode.com/paper/exploring-asymmetric-encoder-decoder |
| Repo | |
| Framework | |
3D Recurrent Neural Networks with Context Fusion for Point Cloud Semantic Segmentation
| Title | 3D Recurrent Neural Networks with Context Fusion for Point Cloud Semantic Segmentation |
| Authors | Xiaoqing Ye, Jiamao Li, Hexiao Huang, Liang Du, Xiaolin Zhang |
| Abstract | Semantic segmentation of 3D unstructured point clouds remains an open research problem. Recent works predict semantic labels of 3D points by virtue of neural networks but take limited context knowledge into consideration. In this paper, a novel end-to-end approach for unstructured point cloud semantic segmentation is proposed to exploit the inherent contextual features. First the efficient pointwise pyramid pooling module is investigated to capture local structures at various densities by taking multi-scale neighborhood into account. Then the two-dimensional hierarchical recurrent neural networks (RNNs) are utilized to explore long-range spatial dependencies. Each recurrent layer takes as input the local features derived from unrolled cells and sweeps the 3D space along two horizontal directions successively to integrate structure knowledge. On challenging indoor and outdoor 3D datasets, the proposed framework demonstrates robust performance superior to state-of-the-arts. |
| Tasks | Semantic Segmentation |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Xiaoqing_Ye_3D_Recurrent_Neural_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Xiaoqing_Ye_3D_Recurrent_Neural_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/3d-recurrent-neural-networks-with-context |
| Repo | |
| Framework | |
Learning to Specialize with Knowledge Distillation for Visual Question Answering
| Title | Learning to Specialize with Knowledge Distillation for Visual Question Answering |
| Authors | Jonghwan Mun, Kimin Lee, Jinwoo Shin, Bohyung Han |
| Abstract | Visual Question Answering (VQA) is a notoriously challenging problem because it involves various heterogeneous tasks defined by questions within a unified framework. Learning specialized models for individual types of tasks is intuitively attracting but surprisingly difficult; it is not straightforward to outperform naive independent ensemble approach. We present a principled algorithm to learn specialized models with knowledge distillation under a multiple choice learning (MCL) framework, where training examples are assigned dynamically to a subset of models for updating network parameters. The assigned and non-assigned models are learned to predict ground-truth answers and imitate their own base models before specialization, respectively. Our approach alleviates the limitation of data deficiency in existing MCL frameworks, and allows each model to learn its own specialized expertise without forgetting general knowledge. The proposed framework is model-agnostic and applicable to any tasks other than VQA, e.g., image classification with a large number of labels but few per-class examples, which is known to be difficult under existing MCL schemes. Our experimental results indeed demonstrate that our method outperforms other baselines for VQA and image classification. |
| Tasks | Image Classification, Question Answering, Visual Question Answering |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/8031-learning-to-specialize-with-knowledge-distillation-for-visual-question-answering |
| http://papers.nips.cc/paper/8031-learning-to-specialize-with-knowledge-distillation-for-visual-question-answering.pdf | |
| PWC | https://paperswithcode.com/paper/learning-to-specialize-with-knowledge |
| Repo | |
| Framework | |
Sounds Wilde. Phonetically Extended Embeddings for Author-Stylized Poetry Generation
| Title | Sounds Wilde. Phonetically Extended Embeddings for Author-Stylized Poetry Generation |
| Authors | Aleksey Tikhonov, Ivan Yamshchikov |
| Abstract | This paper addresses author-stylized text generation. Using a version of a language model with extended phonetic and semantic embeddings for poetry generation we show that phonetics has comparable contribution to the overall model performance as the information on the target author. Phonetic information is shown to be important for English and Russian language. Humans tend to attribute machine generated texts to the target author. |
| Tasks | Language Modelling, Text Generation, Word Embeddings |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-5813/ |
| https://www.aclweb.org/anthology/W18-5813 | |
| PWC | https://paperswithcode.com/paper/sounds-wilde-phonetically-extended-embeddings |
| Repo | |
| Framework | |
VSO: Visual Semantic Odometry
| Title | VSO: Visual Semantic Odometry |
| Authors | Konstantinos-Nektarios Lianos, Johannes L. Schonberger, Marc Pollefeys, Torsten Sattler |
| Abstract | Robust data association is a core problem of visual odometry, where image-to-image correspondences provide constraints for camera pose and map estimation. Current state-of-the-art direct and indirect methods use short-term tracking to obtain continuous frame-to-frame constraints, while long-term constraints are established using loop closures. In this paper, we propose a novel visual semantic odometry (VSO) framework to enable medium-term continuous tracking of points using semantics. Our proposed framework can be easily integrated into existing direct and indirect visual odometry pipelines. Experiments on challenging real-world datasets demonstrate a significant improvement over state-of-the-art baselines in the context of autonomous driving simply by integrating our semantic constraints. |
| Tasks | Autonomous Driving, Visual Odometry |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Konstantinos-Nektarios_Lianos_VSO_Visual_Semantic_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Konstantinos-Nektarios_Lianos_VSO_Visual_Semantic_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/vso-visual-semantic-odometry |
| Repo | |
| Framework | |
A Report on the 2018 VUA Metaphor Detection Shared Task
| Title | A Report on the 2018 VUA Metaphor Detection Shared Task |
| Authors | Chee Wee (Ben) Leong, Beata Beigman Klebanov, Ekaterina Shutova |
| Abstract | As the community working on computational approaches to figurative language is growing and as methods and data become increasingly diverse, it is important to create widely shared empirical knowledge of the level of system performance in a range of contexts, thus facilitating progress in this area. One way of creating such shared knowledge is through benchmarking multiple systems on a common dataset. We report on the shared task on metaphor identification on the VU Amsterdam Metaphor Corpus conducted at the NAACL 2018 Workshop on Figurative Language Processing. |
| Tasks | |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/W18-0907/ |
| https://www.aclweb.org/anthology/W18-0907 | |
| PWC | https://paperswithcode.com/paper/a-report-on-the-2018-vua-metaphor-detection |
| Repo | |
| Framework | |
Building a Knowledge Graph from Natural Language Definitions for Interpretable Text Entailment Recognition
| Title | Building a Knowledge Graph from Natural Language Definitions for Interpretable Text Entailment Recognition |
| Authors | Vivian Silva, Andr{'e} Freitas, H, Siegfried schuh |
| Abstract | |
| Tasks | Information Retrieval, Open Information Extraction, Question Answering |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1542/ |
| https://www.aclweb.org/anthology/L18-1542 | |
| PWC | https://paperswithcode.com/paper/building-a-knowledge-graph-from-natural-1 |
| Repo | |
| Framework | |
End-to-End Joint Semantic Segmentation of Actors and Actions in Video
| Title | End-to-End Joint Semantic Segmentation of Actors and Actions in Video |
| Authors | Jingwei Ji, Shyamal Buch, Alvaro Soto, Juan Carlos Niebles |
| Abstract | Traditional video understanding tasks include human action recognition and actor/object semantic segmentation. However, the combined task of providing semantic segmentation for different actor classes simultaneously with their action class remains a challenging but necessary task for many applications. In this work, we propose a new end-to-end architecture for tackling this task in videos. Our model effectively leverages multiple input modalities, contextual information, and multitask learning in the video to directly output semantic segmentations in a single unified framework. We train and benchmark our model on the Actor-Action Dataset (A2D) for joint actor-action semantic segmentation, and demonstrate state-of-the-art performance for both segmentation and detection. We also perform experiments verifying our approach improves performance for zero-shot recognition, indicating generalizability of our jointly learned feature space. |
| Tasks | Semantic Segmentation, Temporal Action Localization, Video Understanding, Zero-Shot Learning |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Jingwei_Ji_End-to-End_Joint_Semantic_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Jingwei_Ji_End-to-End_Joint_Semantic_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/end-to-end-joint-semantic-segmentation-of |
| Repo | |
| Framework | |
Deep Variational Metric Learning
| Title | Deep Variational Metric Learning |
| Authors | Xudong Lin, Yueqi Duan, Qiyuan Dong, Jiwen Lu, Jie Zhou |
| Abstract | Deep metric learning has been extensively explored recently, which trains a deep neural network to produce discriminative embedding features. Most existing methods usually enforce the model to be indiscriminating to intra-class variance, which makes the model over-fitting to the training set to minimize loss functions on these specific changes and leads to low generalization power on unseen classes. However, these methods ignore a fact that in the central latent space, the distribution of variance within classes is actually independent on classes. In this paper, we propose a deep variational metric learning (DVML) framework to explicitly model the intra-class variance and disentangle the intra-class invariance, namely, the class centers. With the learned distribution of intra-class variance, we can simultaneously generate discriminative samples to improve robustness. Our method is applicable to most of existing metric learning algorithms, and extensive experiments on three benchmark datasets including CUB-200-2011, Cars196 and Stanford Online Products show that our DVML significantly boosts the performance of currently popular deep metric learning methods. |
| Tasks | Metric Learning |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Xudong_Lin_Deep_Variational_Metric_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Xudong_Lin_Deep_Variational_Metric_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/deep-variational-metric-learning |
| Repo | |
| Framework | |
Predicting Word Embeddings Variability
| Title | Predicting Word Embeddings Variability |
| Authors | B{'e}n{'e}dicte Pierrejean, Ludovic Tanguy |
| Abstract | Neural word embeddings models (such as those built with word2vec) are known to have stability problems: when retraining a model with the exact same hyperparameters, words neighborhoods may change. We propose a method to estimate such variation, based on the overlap of neighbors of a given word in two models trained with identical hyperparameters. We show that this inherent variation is not negligible, and that it does not affect every word in the same way. We examine the influence of several features that are intrinsic to a word, corpus or embedding model and provide a methodology that can predict the variability (and as such, reliability) of a word representation in a semantic vector space. |
| Tasks | Word Embeddings |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/S18-2019/ |
| https://www.aclweb.org/anthology/S18-2019 | |
| PWC | https://paperswithcode.com/paper/predicting-word-embeddings-variability |
| Repo | |
| Framework | |
Structured Deep Factorization Machine: Towards General-Purpose Architectures
| Title | Structured Deep Factorization Machine: Towards General-Purpose Architectures |
| Authors | José P. González-Brenes, Ralph Edezhath |
| Abstract | In spite of their great success, traditional factorization algorithms typically do not support features (e.g., Matrix Factorization), or their complexity scales quadratically with the number of features (e.g, Factorization Machine). On the other hand, neural methods allow large feature sets, but are often designed for a specific application. We propose novel deep factorization methods that allow efficient and flexible feature representation. For example, we enable describing items with natural language with complexity linear to the vocabulary size—this enables prediction for unseen items and avoids the cold start problem. We show that our architecture can generalize some previously published single-purpose neural architectures. Our experiments suggest improved training times and accuracy compared to shallow methods. |
| Tasks | |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=HJsk5-Z0W |
| https://openreview.net/pdf?id=HJsk5-Z0W | |
| PWC | https://paperswithcode.com/paper/structured-deep-factorization-machine-towards |
| Repo | |
| Framework | |
Empirical Risk Minimization in Non-interactive Local Differential Privacy Revisited
| Title | Empirical Risk Minimization in Non-interactive Local Differential Privacy Revisited |
| Authors | Di Wang, Marco Gaboardi, Jinhui Xu |
| Abstract | In this paper, we revisit the Empirical Risk Minimization problem in the non-interactive local model of differential privacy. In the case of constant or low dimensions ($p\ll n$), we first show that if the loss function is $(\infty, T)$-smooth, we can avoid a dependence of the sample complexity, to achieve error $\alpha$, on the exponential of the dimensionality $p$ with base $1/\alpha$ ({\em i.e.,} $\alpha^{-p}$), which answers a question in \cite{smith2017interaction}. Our approach is based on polynomial approximation. Then, we propose player-efficient algorithms with $1$-bit communication complexity and $O(1)$ computation cost for each player. The error bound is asymptotically the same as the original one. With some additional assumptions, we also give an efficient algorithm for the server. In the case of high dimensions ($n\ll p$), we show that if the loss function is a convex generalized linear function, the error can be bounded by using the Gaussian width of the constrained set, instead of $p$, which improves the one in \cite{smith2017interaction}. |
| Tasks | |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7375-empirical-risk-minimization-in-non-interactive-local-differential-privacy-revisited |
| http://papers.nips.cc/paper/7375-empirical-risk-minimization-in-non-interactive-local-differential-privacy-revisited.pdf | |
| PWC | https://paperswithcode.com/paper/empirical-risk-minimization-in-non |
| Repo | |
| Framework | |
