Paper Group ANR 640
Understanding Actors and Evaluating Personae with Gaussian Embeddings. Author Commitment and Social Power: Automatic Belief Tagging to Infer the Social Context of Interactions. Local Orthogonal-Group Testing. A Framework for Video-Driven Crowd Synthesis. Relative Entropy Regularized Policy Iteration. Adversarial 3D Human Pose Estimation via Multimo …
Understanding Actors and Evaluating Personae with Gaussian Embeddings
Title | Understanding Actors and Evaluating Personae with Gaussian Embeddings |
Authors | Hannah Kim, Denys Katerenchuk, Daniel Billet, Jun Huan, Haesun Park, Boyang Li |
Abstract | Understanding narrative content has become an increasingly popular topic. Nonetheless, research on identifying common types of narrative characters, or personae, is impeded by the lack of automatic and broad-coverage evaluation methods. We argue that computationally modeling actors provides benefits, including novel evaluation mechanisms for personae. Specifically, we propose two actor-modeling tasks, cast prediction and versatility ranking, which can capture complementary aspects of the relation between actors and the characters they portray. For an actor model, we present a technique for embedding actors, movies, character roles, genres, and descriptive keywords as Gaussian distributions and translation vectors, where the Gaussian variance corresponds to actors’ versatility. Empirical results indicate that (1) the technique considerably outperforms TransE (Bordes et al. 2013) and ablation baselines and (2) automatically identified persona topics (Bamman, O’Connor, and Smith 2013) yield statistically significant improvements in both tasks, whereas simplistic persona descriptors including age and gender perform inconsistently, validating prior research. |
Tasks | |
Published | 2018-04-06 |
URL | http://arxiv.org/abs/1804.04164v2 |
http://arxiv.org/pdf/1804.04164v2.pdf | |
PWC | https://paperswithcode.com/paper/understanding-actors-and-evaluating-personae |
Repo | |
Framework | |
Author Commitment and Social Power: Automatic Belief Tagging to Infer the Social Context of Interactions
Title | Author Commitment and Social Power: Automatic Belief Tagging to Infer the Social Context of Interactions |
Authors | Vinodkumar Prabhakaran, Premkumar Ganeshkumar, Owen Rambow |
Abstract | Understanding how social power structures affect the way we interact with one another is of great interest to social scientists who want to answer fundamental questions about human behavior, as well as to computer scientists who want to build automatic methods to infer the social contexts of interactions. In this paper, we employ advancements in extra-propositional semantics extraction within NLP to study how author commitment reflects the social context of an interaction. Specifically, we investigate whether the level of commitment expressed by individuals in an organizational interaction reflects the hierarchical power structures they are part of. We find that subordinates use significantly more instances of non-commitment than superiors. More importantly, we also find that subordinates attribute propositions to other agents more often than superiors do — an aspect that has not been studied before. Finally, we show that enriching lexical features with commitment labels captures important distinctions in social meanings. |
Tasks | |
Published | 2018-05-15 |
URL | http://arxiv.org/abs/1805.06016v1 |
http://arxiv.org/pdf/1805.06016v1.pdf | |
PWC | https://paperswithcode.com/paper/author-commitment-and-social-power-automatic |
Repo | |
Framework | |
Local Orthogonal-Group Testing
Title | Local Orthogonal-Group Testing |
Authors | Ahmet Iscen, Ondrej Chum |
Abstract | This work addresses approximate nearest neighbor search applied in the domain of large-scale image retrieval. Within the group testing framework we propose an efficient off-line construction of the search structures. The linear-time complexity orthogonal grouping increases the probability that at most one element from each group is matching to a given query. Non-maxima suppression with each group efficiently reduces the number of false positive results at no extra cost. Unlike in other well-performing approaches, all processing is local, fast, and suitable to process data in batches and in parallel. We experimentally show that the proposed method achieves search accuracy of the exhaustive search with significant reduction in the search complexity. The method can be naturally combined with existing embedding methods. |
Tasks | Image Retrieval |
Published | 2018-07-25 |
URL | http://arxiv.org/abs/1807.09848v2 |
http://arxiv.org/pdf/1807.09848v2.pdf | |
PWC | https://paperswithcode.com/paper/local-orthogonal-group-testing |
Repo | |
Framework | |
A Framework for Video-Driven Crowd Synthesis
Title | A Framework for Video-Driven Crowd Synthesis |
Authors | Jordan Stadler, Faisal Z. Qureshi |
Abstract | We present a framework for video-driven crowd synthesis. Motion vectors extracted from input crowd video are processed to compute global motion paths. These paths encode the dominant motions observed in the input video. These paths are then fed into a behavior-based crowd simulation framework, which is responsible for synthesizing crowd animations that respect the motion patterns observed in the video. Our system synthesizes 3D virtual crowds by animating virtual humans along the trajectories returned by the crowd simulation framework. We also propose a new metric for comparing the “visual similarity” between the synthesized crowd and exemplar crowd. We demonstrate the proposed approach on crowd videos collected under different settings. |
Tasks | |
Published | 2018-03-13 |
URL | http://arxiv.org/abs/1803.04969v1 |
http://arxiv.org/pdf/1803.04969v1.pdf | |
PWC | https://paperswithcode.com/paper/a-framework-for-video-driven-crowd-synthesis |
Repo | |
Framework | |
Relative Entropy Regularized Policy Iteration
Title | Relative Entropy Regularized Policy Iteration |
Authors | Abbas Abdolmaleki, Jost Tobias Springenberg, Jonas Degrave, Steven Bohez, Yuval Tassa, Dan Belov, Nicolas Heess, Martin Riedmiller |
Abstract | We present an off-policy actor-critic algorithm for Reinforcement Learning (RL) that combines ideas from gradient-free optimization via stochastic search with learned action-value function. The result is a simple procedure consisting of three steps: i) policy evaluation by estimating a parametric action-value function; ii) policy improvement via the estimation of a local non-parametric policy; and iii) generalization by fitting a parametric policy. Each step can be implemented in different ways, giving rise to several algorithm variants. Our algorithm draws on connections to existing literature on black-box optimization and ‘RL as an inference’ and it can be seen either as an extension of the Maximum a Posteriori Policy Optimisation algorithm (MPO) [Abdolmaleki et al., 2018a], or as an extension of Trust Region Covariance Matrix Adaptation Evolutionary Strategy (CMA-ES) [Abdolmaleki et al., 2017b; Hansen et al., 1997] to a policy iteration scheme. Our comparison on 31 continuous control tasks from parkour suite [Heess et al., 2017], DeepMind control suite [Tassa et al., 2018] and OpenAI Gym [Brockman et al., 2016] with diverse properties, limited amount of compute and a single set of hyperparameters, demonstrate the effectiveness of our method and the state of art results. Videos, summarizing results, can be found at goo.gl/HtvJKR . |
Tasks | Continuous Control |
Published | 2018-12-05 |
URL | http://arxiv.org/abs/1812.02256v1 |
http://arxiv.org/pdf/1812.02256v1.pdf | |
PWC | https://paperswithcode.com/paper/relative-entropy-regularized-policy-iteration |
Repo | |
Framework | |
Adversarial 3D Human Pose Estimation via Multimodal Depth Supervision
Title | Adversarial 3D Human Pose Estimation via Multimodal Depth Supervision |
Authors | Kun Zhou, Jinmiao Cai, Yao Li, Yulong Shi, Xiaoguang Han, Nianjuan Jiang, Kui Jia, Jiangbo Lu |
Abstract | In this paper, a novel deep-learning based framework is proposed to infer 3D human poses from a single image. Specifically, a two-phase approach is developed. We firstly utilize a generator with two branches for the extraction of explicit and implicit depth information respectively. During the training process, an adversarial scheme is also employed to further improve the performance. The implicit and explicit depth information with the estimated 2D joints generated by a widely used estimator, in the second step, are together fed into a deep 3D pose regressor for the final pose generation. Our method achieves MPJPE of 58.68mm on the ECCV2018 3D Human Pose Estimation Challenge. |
Tasks | 3D Human Pose Estimation, Pose Estimation |
Published | 2018-09-21 |
URL | http://arxiv.org/abs/1809.07921v1 |
http://arxiv.org/pdf/1809.07921v1.pdf | |
PWC | https://paperswithcode.com/paper/adversarial-3d-human-pose-estimation-via |
Repo | |
Framework | |
Large Receptive Field Networks for High-Scale Image Super-Resolution
Title | Large Receptive Field Networks for High-Scale Image Super-Resolution |
Authors | George Seif, Dimitrios Androutsos |
Abstract | Convolutional Neural Networks have been the backbone of recent rapid progress in Single-Image Super-Resolution. However, existing networks are very deep with many network parameters, thus having a large memory footprint and being challenging to train. We propose Large Receptive Field Networks which strive to directly expand the receptive field of Super-Resolution networks without increasing depth or parameter count. In particular, we use two different methods to expand the network receptive field: 1-D separable kernels and atrous convolutions. We conduct considerable experiments to study the performance of various arrangement schemes of the 1-D separable kernels and atrous convolution in terms of accuracy (PSNR / SSIM), parameter count, and speed, while focusing on the more challenging high upscaling factors. Extensive benchmark evaluations demonstrate the effectiveness of our approach. |
Tasks | Image Super-Resolution, Super-Resolution |
Published | 2018-04-22 |
URL | http://arxiv.org/abs/1804.08181v1 |
http://arxiv.org/pdf/1804.08181v1.pdf | |
PWC | https://paperswithcode.com/paper/large-receptive-field-networks-for-high-scale |
Repo | |
Framework | |
Probabilistic Contraction Analysis of Iterated Random Operators
Title | Probabilistic Contraction Analysis of Iterated Random Operators |
Authors | Abhishek Gupta, Rahul Jain, Peter Glynn |
Abstract | Consider a contraction operator $T$ over a Polish space $\mathcal X$ with a fixed point $x^\star$. Assume that one can approximate the operator $T$ by a random operator $\hat T^n$ using $n\in\mathbb{N}$ independent and identically distributed samples of a random variable. Consider the sequence $(\hat X^n_k){k\in\mathbb{N}}$, which is generated by $\hat X^n{k+1} = \hat T^n(\hat X^n_k)$ and is a random sequence. In this paper, we prove that under certain conditions on the random operator, (i) the distribution of $\hat X^n_k$ converges to a unit mass over $x^\star$ as $k$ and $n$ goes to infinity, and (ii) the probability that $\hat X^n_k$ is far from $x^\star$ as $k$ goes to infinity can be made arbitrarily small by an appropriate choice of $n$. We also find a lower bound on the probability that $\hat X^n_k$ is far from $x^\star$ as $k\rightarrow \infty$. We apply the result to study probabilistic convergence of certain randomized value and Q-value iteration algorithms for discounted and average cost Markov decision processes. |
Tasks | |
Published | 2018-04-04 |
URL | http://arxiv.org/abs/1804.01195v4 |
http://arxiv.org/pdf/1804.01195v4.pdf | |
PWC | https://paperswithcode.com/paper/probabilistic-contraction-analysis-of |
Repo | |
Framework | |
The RBO Dataset of Articulated Objects and Interactions
Title | The RBO Dataset of Articulated Objects and Interactions |
Authors | Roberto Martín-Martín, Clemens Eppner, Oliver Brock |
Abstract | We present a dataset with models of 14 articulated objects commonly found in human environments and with RGB-D video sequences and wrenches recorded of human interactions with them. The 358 interaction sequences total 67 minutes of human manipulation under varying experimental conditions (type of interaction, lighting, perspective, and background). Each interaction with an object is annotated with the ground truth poses of its rigid parts and the kinematic state obtained by a motion capture system. For a subset of 78 sequences (25 minutes), we also measured the interaction wrenches. The object models contain textured three-dimensional triangle meshes of each link and their motion constraints. We provide Python scripts to download and visualize the data. The data is available at https://tu-rbo.github.io/articulated-objects/ and hosted at https://zenodo.org/record/1036660/. |
Tasks | Motion Capture |
Published | 2018-06-17 |
URL | http://arxiv.org/abs/1806.06465v1 |
http://arxiv.org/pdf/1806.06465v1.pdf | |
PWC | https://paperswithcode.com/paper/the-rbo-dataset-of-articulated-objects-and |
Repo | |
Framework | |
Combinatorial Testing for Deep Learning Systems
Title | Combinatorial Testing for Deep Learning Systems |
Authors | Lei Ma, Fuyuan Zhang, Minhui Xue, Bo Li, Yang Liu, Jianjun Zhao, Yadong Wang |
Abstract | Deep learning (DL) has achieved remarkable progress over the past decade and been widely applied to many safety-critical applications. However, the robustness of DL systems recently receives great concerns, such as adversarial examples against computer vision systems, which could potentially result in severe consequences. Adopting testing techniques could help to evaluate the robustness of a DL system and therefore detect vulnerabilities at an early stage. The main challenge of testing such systems is that its runtime state space is too large: if we view each neuron as a runtime state for DL, then a DL system often contains massive states, rendering testing each state almost impossible. For traditional software, combinatorial testing (CT) is an effective testing technique to reduce the testing space while obtaining relatively high defect detection abilities. In this paper, we perform an exploratory study of CT on DL systems. We adapt the concept in CT and propose a set of coverage criteria for DL systems, as well as a CT coverage guided test generation technique. Our evaluation demonstrates that CT provides a promising avenue for testing DL systems. We further pose several open questions and interesting directions for combinatorial testing of DL systems. |
Tasks | |
Published | 2018-06-20 |
URL | http://arxiv.org/abs/1806.07723v1 |
http://arxiv.org/pdf/1806.07723v1.pdf | |
PWC | https://paperswithcode.com/paper/combinatorial-testing-for-deep-learning |
Repo | |
Framework | |
An Ontology-Based Recommender System with an Application to the Star Trek Television Franchise
Title | An Ontology-Based Recommender System with an Application to the Star Trek Television Franchise |
Authors | Paul Sheridan, Mikael Onsjö, Claudia Becerra, Sergio Jimenez, George Dueñas |
Abstract | Collaborative filtering based recommender systems have proven to be extremely successful in settings where user preference data on items is abundant. However, collaborative filtering algorithms are hindered by their weakness against the item cold-start problem and general lack of interpretability. Ontology-based recommender systems exploit hierarchical organizations of users and items to enhance browsing, recommendation, and profile construction. While ontology-based approaches address the shortcomings of their collaborative filtering counterparts, ontological organizations of items can be difficult to obtain for items that mostly belong to the same category (e.g., television series episodes). In this paper, we present an ontology-based recommender system that integrates the knowledge represented in a large ontology of literary themes to produce fiction content recommendations. The main novelty of this work is an ontology-based method for computing similarities between items and its integration with the classical Item-KNN (K-nearest neighbors) algorithm. As a study case, we evaluated the proposed method against other approaches by performing the classical rating prediction task on a collection of Star Trek television series episodes in an item cold-start scenario. This transverse evaluation provides insights into the utility of different information resources and methods for the initial stages of recommender system development. We found our proposed method to be a convenient alternative to collaborative filtering approaches for collections of mostly similar items, particularly when other content-based approaches are not applicable or otherwise unavailable. Aside from the new methods, this paper contributes a testbed for future research and an online framework to collaboratively extend the ontology of literary themes to cover other narrative content. |
Tasks | Recommendation Systems, Topic Models |
Published | 2018-07-31 |
URL | https://arxiv.org/abs/1808.00103v3 |
https://arxiv.org/pdf/1808.00103v3.pdf | |
PWC | https://paperswithcode.com/paper/a-knowledge-based-filtering-story-recommender |
Repo | |
Framework | |
Evaluation of Complex-Valued Neural Networks on Real-Valued Classification Tasks
Title | Evaluation of Complex-Valued Neural Networks on Real-Valued Classification Tasks |
Authors | Nils Mönning, Suresh Manandhar |
Abstract | Complex-valued neural networks are not a new concept, however, the use of real-valued models has often been favoured over complex-valued models due to difficulties in training and performance. When comparing real-valued versus complex-valued neural networks, existing literature often ignores the number of parameters, resulting in comparisons of neural networks with vastly different sizes. We find that when real and complex neural networks of similar capacity are compared, complex models perform equal to or slightly worse than real-valued models for a range of real-valued classification tasks. The use of complex numbers allows neural networks to handle noise on the complex plane. When classifying real-valued data with a complex-valued neural network, the imaginary parts of the weights follow their real parts. This behaviour is indicative for a task that does not require a complex-valued model. We further investigated this in a synthetic classification task. We can transfer many activation functions from the real to the complex domain using different strategies. The weight initialisation of complex neural networks, however, remains a significant problem. |
Tasks | |
Published | 2018-11-29 |
URL | http://arxiv.org/abs/1811.12351v1 |
http://arxiv.org/pdf/1811.12351v1.pdf | |
PWC | https://paperswithcode.com/paper/evaluation-of-complex-valued-neural-networks |
Repo | |
Framework | |
End-to-end Image Captioning Exploits Multimodal Distributional Similarity
Title | End-to-end Image Captioning Exploits Multimodal Distributional Similarity |
Authors | Pranava Madhyastha, Josiah Wang, Lucia Specia |
Abstract | We hypothesize that end-to-end neural image captioning systems work seemingly well because they exploit and learn distributional similarity' in a multimodal feature space by mapping a test image to similar training images in this space and generating a caption from the same space. To validate our hypothesis, we focus on the image’ side of image captioning, and vary the input image representation but keep the RNN text generation component of a CNN-RNN model constant. Our analysis indicates that image captioning models (i) are capable of separating structure from noisy input representations; (ii) suffer virtually no significant performance loss when a high dimensional representation is compressed to a lower dimensional space; (iii) cluster images with similar visual and linguistic information together. Our findings indicate that our distributional similarity hypothesis holds. We conclude that regardless of the image representation used image captioning systems seem to match images and generate captions in a learned joint image-text semantic subspace. |
Tasks | Image Captioning, Text Generation |
Published | 2018-09-11 |
URL | http://arxiv.org/abs/1809.04144v1 |
http://arxiv.org/pdf/1809.04144v1.pdf | |
PWC | https://paperswithcode.com/paper/end-to-end-image-captioning-exploits-1 |
Repo | |
Framework | |
Multi-Reference Training with Pseudo-References for Neural Translation and Text Generation
Title | Multi-Reference Training with Pseudo-References for Neural Translation and Text Generation |
Authors | Renjie Zheng, Mingbo Ma, Liang Huang |
Abstract | Neural text generation, including neural machine translation, image captioning, and summarization, has been quite successful recently. However, during training time, typically only one reference is considered for each example, even though there are often multiple references available, e.g., 4 references in NIST MT evaluations, and 5 references in image captioning data. We first investigate several different ways of utilizing multiple human references during training. But more importantly, we then propose an algorithm to generate exponentially many pseudo-references by first compressing existing human references into lattices and then traversing them to generate new pseudo-references. These approaches lead to substantial improvements over strong baselines in both machine translation (+1.5 BLEU) and image captioning (+3.1 BLEU / +11.7 CIDEr). |
Tasks | Image Captioning, Machine Translation, Text Generation |
Published | 2018-08-28 |
URL | http://arxiv.org/abs/1808.09564v1 |
http://arxiv.org/pdf/1808.09564v1.pdf | |
PWC | https://paperswithcode.com/paper/multi-reference-training-with-pseudo |
Repo | |
Framework | |
Modelling the Influence of Cultural Information on Vision-Based Human Home Activity Recognition
Title | Modelling the Influence of Cultural Information on Vision-Based Human Home Activity Recognition |
Authors | Roberto Menicatti, Barbara Bruno, Antonio Sgorbissa |
Abstract | Daily life activities, such as eating and sleeping, are deeply influenced by a person’s culture, hence generating differences in the way a same activity is performed by individuals belonging to different cultures. We argue that taking cultural information into account can improve the performance of systems for the automated recognition of human activities. We propose four different solutions to the problem and present a system which uses a Naive Bayes model to associate cultural information with semantic information extracted from still images. Preliminary experiments with a dataset of images of individuals lying on the floor, sleeping on a futon and sleeping on a bed suggest that: i) solutions explicitly taking cultural information into account are more accurate than culture-unaware solutions; and ii) the proposed system is a promising starting point for the development of culture-aware Human Activity Recognition methods. |
Tasks | Activity Recognition, Human Activity Recognition |
Published | 2018-03-21 |
URL | http://arxiv.org/abs/1803.07915v1 |
http://arxiv.org/pdf/1803.07915v1.pdf | |
PWC | https://paperswithcode.com/paper/modelling-the-influence-of-cultural |
Repo | |
Framework | |