Paper Group ANR 776
Bilingual Dictionary Induction for Bantu Languages. Domain Transfer for 3D Pose Estimation from Color Images without Manual Annotations. Exploiting feature representations through similarity learning, post-ranking and ranking aggregation for person re-identification. A Scalable Machine Learning System for Pre-Season Agriculture Yield Forecast. MemG …
Bilingual Dictionary Induction for Bantu Languages
| Title | Bilingual Dictionary Induction for Bantu Languages |
| Authors | Ndapa Nakashole |
| Abstract | We present a method for learning bilingual translation dictionaries between English and Bantu languages. We show that exploiting the grammatical structure common to Bantu languages enables bilingual dictionary induction for languages where training data is unavailable. |
| Tasks | |
| Published | 2018-11-17 |
| URL | https://arxiv.org/abs/1811.07080v2 |
| https://arxiv.org/pdf/1811.07080v2.pdf | |
| PWC | https://paperswithcode.com/paper/bilingual-dictionary-induction-for-bantu |
| Repo | |
| Framework | |
Domain Transfer for 3D Pose Estimation from Color Images without Manual Annotations
| Title | Domain Transfer for 3D Pose Estimation from Color Images without Manual Annotations |
| Authors | Mahdi Rad, Markus Oberweger, Vincent Lepetit |
| Abstract | We introduce a novel learning method for 3D pose estimation from color images. While acquiring annotations for color images is a difficult task, our approach circumvents this problem by learning a mapping from paired color and depth images captured with an RGB-D camera. We jointly learn the pose from synthetic depth images that are easy to generate, and learn to align these synthetic depth images with the real depth images. We show our approach for the task of 3D hand pose estimation and 3D object pose estimation, both from color images only. Our method achieves performances comparable to state-of-the-art methods on popular benchmark datasets, without requiring any annotations for the color images. |
| Tasks | 3D Pose Estimation, Hand Pose Estimation, Pose Estimation |
| Published | 2018-10-08 |
| URL | http://arxiv.org/abs/1810.03707v2 |
| http://arxiv.org/pdf/1810.03707v2.pdf | |
| PWC | https://paperswithcode.com/paper/domain-transfer-for-3d-pose-estimation-from |
| Repo | |
| Framework | |
Exploiting feature representations through similarity learning, post-ranking and ranking aggregation for person re-identification
| Title | Exploiting feature representations through similarity learning, post-ranking and ranking aggregation for person re-identification |
| Authors | Julio C. S. Jacques Junior, Xavier Baró, Sergio Escalera |
| Abstract | Person re-identification has received special attention by the human analysis community in the last few years. To address the challenges in this field, many researchers have proposed different strategies, which basically exploit either cross-view invariant features or cross-view robust metrics. In this work, we propose to exploit a post-ranking approach and combine different feature representations through ranking aggregation. Spatial information, which potentially benefits the person matching, is represented using a 2D body model, from which color and texture information are extracted and combined. We also consider background/foreground information, automatically extracted via Deep Decompositional Network, and the usage of Convolutional Neural Network (CNN) features. To describe the matching between images we use the polynomial feature map, also taking into account local and global information. The Discriminant Context Information Analysis based post-ranking approach is used to improve initial ranking lists. Finally, the Stuart ranking aggregation method is employed to combine complementary ranking lists obtained from different feature representations. Experimental results demonstrated that we improve the state-of-the-art on VIPeR and PRID450s datasets, achieving 67.21% and 75.64% on top-1 rank recognition rate, respectively, as well as obtaining competitive results on CUHK01 dataset. |
| Tasks | Person Re-Identification |
| Published | 2018-04-12 |
| URL | http://arxiv.org/abs/1804.04419v1 |
| http://arxiv.org/pdf/1804.04419v1.pdf | |
| PWC | https://paperswithcode.com/paper/exploiting-feature-representations-through |
| Repo | |
| Framework | |
A Scalable Machine Learning System for Pre-Season Agriculture Yield Forecast
| Title | A Scalable Machine Learning System for Pre-Season Agriculture Yield Forecast |
| Authors | Igor Oliveira, Renato L. F. Cunha, Bruno Silva, Marco A. S. Netto |
| Abstract | Yield forecast is essential to agriculture stakeholders and can be obtained with the use of machine learning models and data coming from multiple sources. Most solutions for yield forecast rely on NDVI (Normalized Difference Vegetation Index) data, which is time-consuming to be acquired and processed. To bring scalability for yield forecast, in the present paper we describe a system that incorporates satellite-derived precipitation and soil properties datasets, seasonal climate forecasting data from physical models and other sources to produce a pre-season prediction of soybean/maize yield—with no need of NDVI data. This system provides significantly useful results by the exempting the need for high-resolution remote-sensing data and allowing farmers to prepare for adverse climate influence on the crop cycle. In our studies, we forecast the soybean and maize yields for Brazil and USA, which corresponded to 44% of the world’s grain production in 2016. Results show the error metrics for soybean and maize yield forecasts are comparable to similar systems that only provide yield forecast information in the first weeks to months of the crop cycle. |
| Tasks | |
| Published | 2018-06-25 |
| URL | http://arxiv.org/abs/1806.09244v2 |
| http://arxiv.org/pdf/1806.09244v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-scalable-machine-learning-system-for-pre |
| Repo | |
| Framework | |
MemGEN: Memory is All You Need
| Title | MemGEN: Memory is All You Need |
| Authors | Sylvain Gelly, Karol Kurach, Marcin Michalski, Xiaohua Zhai |
| Abstract | We propose a new learning paradigm called Deep Memory. It has the potential to completely revolutionize the Machine Learning field. Surprisingly, this paradigm has not been reinvented yet, unlike Deep Learning. At the core of this approach is the \textit{Learning By Heart} principle, well studied in primary schools all over the world. Inspired by poem recitation, or by $\pi$ decimal memorization, we propose a concrete algorithm that mimics human behavior. We implement this paradigm on the task of generative modeling, and apply to images, natural language and even the $\pi$ decimals as long as one can print them as text. The proposed algorithm even generated this paper, in a one-shot learning setting. In carefully designed experiments, we show that the generated samples are indistinguishable from the training examples, as measured by any statistical tests or metrics. |
| Tasks | One-Shot Learning |
| Published | 2018-03-29 |
| URL | http://arxiv.org/abs/1803.11203v1 |
| http://arxiv.org/pdf/1803.11203v1.pdf | |
| PWC | https://paperswithcode.com/paper/memgen-memory-is-all-you-need |
| Repo | |
| Framework | |
Revisiting the poverty of the stimulus: hierarchical generalization without a hierarchical bias in recurrent neural networks
| Title | Revisiting the poverty of the stimulus: hierarchical generalization without a hierarchical bias in recurrent neural networks |
| Authors | R. Thomas McCoy, Robert Frank, Tal Linzen |
| Abstract | Syntactic rules in natural language typically need to make reference to hierarchical sentence structure. However, the simple examples that language learners receive are often equally compatible with linear rules. Children consistently ignore these linear explanations and settle instead on the correct hierarchical one. This fact has motivated the proposal that the learner’s hypothesis space is constrained to include only hierarchical rules. We examine this proposal using recurrent neural networks (RNNs), which are not constrained in such a way. We simulate the acquisition of question formation, a hierarchical transformation, in a fragment of English. We find that some RNN architectures tend to learn the hierarchical rule, suggesting that hierarchical cues within the language, combined with the implicit architectural biases inherent in certain RNNs, may be sufficient to induce hierarchical generalizations. The likelihood of acquiring the hierarchical generalization increased when the language included an additional cue to hierarchy in the form of subject-verb agreement, underscoring the role of cues to hierarchy in the learner’s input. |
| Tasks | |
| Published | 2018-02-25 |
| URL | http://arxiv.org/abs/1802.09091v3 |
| http://arxiv.org/pdf/1802.09091v3.pdf | |
| PWC | https://paperswithcode.com/paper/revisiting-the-poverty-of-the-stimulus |
| Repo | |
| Framework | |
One-Shot Imitation from Observing Humans via Domain-Adaptive Meta-Learning
| Title | One-Shot Imitation from Observing Humans via Domain-Adaptive Meta-Learning |
| Authors | Tianhe Yu, Chelsea Finn, Annie Xie, Sudeep Dasari, Tianhao Zhang, Pieter Abbeel, Sergey Levine |
| Abstract | Humans and animals are capable of learning a new behavior by observing others perform the skill just once. We consider the problem of allowing a robot to do the same – learning from a raw video pixels of a human, even when there is substantial domain shift in the perspective, environment, and embodiment between the robot and the observed human. Prior approaches to this problem have hand-specified how human and robot actions correspond and often relied on explicit human pose detection systems. In this work, we present an approach for one-shot learning from a video of a human by using human and robot demonstration data from a variety of previous tasks to build up prior knowledge through meta-learning. Then, combining this prior knowledge and only a single video demonstration from a human, the robot can perform the task that the human demonstrated. We show experiments on both a PR2 arm and a Sawyer arm, demonstrating that after meta-learning, the robot can learn to place, push, and pick-and-place new objects using just one video of a human performing the manipulation. |
| Tasks | Meta-Learning, One-Shot Learning |
| Published | 2018-02-05 |
| URL | http://arxiv.org/abs/1802.01557v1 |
| http://arxiv.org/pdf/1802.01557v1.pdf | |
| PWC | https://paperswithcode.com/paper/one-shot-imitation-from-observing-humans-via |
| Repo | |
| Framework | |
Structural Recurrent Neural Network (SRNN) for Group Activity Analysis
| Title | Structural Recurrent Neural Network (SRNN) for Group Activity Analysis |
| Authors | Sovan Biswas, Juergen Gall |
| Abstract | A group of persons can be analyzed at various semantic levels such as individual actions, their interactions, and the activity of the entire group. In this paper, we propose a structural recurrent neural network (SRNN) that uses a series of interconnected RNNs to jointly capture the actions of individuals, their interactions, as well as the group activity. While previous structural recurrent neural networks assumed that the number of nodes and edges is constant, we use a grid pooling layer to address the fact that the number of individuals in a group can vary. We evaluate two variants of the structural recurrent neural network on the Volleyball Dataset. |
| Tasks | |
| Published | 2018-02-06 |
| URL | http://arxiv.org/abs/1802.02091v1 |
| http://arxiv.org/pdf/1802.02091v1.pdf | |
| PWC | https://paperswithcode.com/paper/structural-recurrent-neural-network-srnn-for |
| Repo | |
| Framework | |
Fusion Network for Face-based Age Estimation
| Title | Fusion Network for Face-based Age Estimation |
| Authors | Haoyi Wang, Xingjie Wei, Victor Sanchez, Chang-Tsun Li |
| Abstract | Convolutional Neural Networks (CNN) have been applied to age-related research as the core framework. Although faces are composed of numerous facial attributes, most works with CNNs still consider a face as a typical object and do not pay enough attention to facial regions that carry age-specific feature for this particular task. In this paper, we propose a novel CNN architecture called Fusion Network (FusionNet) to tackle the age estimation problem. Apart from the whole face image, the FusionNet successively takes several age-specific facial patches as part of the input to emphasize the age-specific features. Through experiments, we show that the FusionNet significantly outperforms other state-of-the-art models on the MORPH II benchmark. |
| Tasks | Age Estimation |
| Published | 2018-07-27 |
| URL | http://arxiv.org/abs/1807.10421v1 |
| http://arxiv.org/pdf/1807.10421v1.pdf | |
| PWC | https://paperswithcode.com/paper/fusion-network-for-face-based-age-estimation |
| Repo | |
| Framework | |
FinBrain: When Finance Meets AI 2.0
| Title | FinBrain: When Finance Meets AI 2.0 |
| Authors | Xiaolin Zheng, Mengying Zhu, Qibing Li, Chaochao Chen, Yanchao Tan |
| Abstract | Artificial intelligence (AI) is the core technology of technological revolution and industrial transformation. As one of the new intelligent needs in the AI 2.0 era, financial intelligence has elicited much attention from the academia and industry. In our current dynamic capital market, financial intelligence demonstrates a fast and accurate machine learning capability to handle complex data and has gradually acquired the potential to become a “financial brain”. In this work, we survey existing studies on financial intelligence. First, we describe the concept of financial intelligence and elaborate on its position in the financial technology field. Second, we introduce the development of financial intelligence and review state-of-the-art techniques in wealth management, risk management, financial security, financial consulting, and blockchain. Finally, we propose a research framework called FinBrain and summarize four open issues, namely, explainable financial agents and causality, perception and prediction under uncertainty, risk-sensitive and robust decision making, and multi-agent game and mechanism design. We believe that these research directions can lay the foundation for the development of AI 2.0 in the finance field. |
| Tasks | Decision Making |
| Published | 2018-08-26 |
| URL | http://arxiv.org/abs/1808.08497v1 |
| http://arxiv.org/pdf/1808.08497v1.pdf | |
| PWC | https://paperswithcode.com/paper/finbrain-when-finance-meets-ai-20 |
| Repo | |
| Framework | |
Deep Multiple Instance Learning for Airplane Detection in High Resolution Imagery
| Title | Deep Multiple Instance Learning for Airplane Detection in High Resolution Imagery |
| Authors | Mohammad Reza Mohammadi |
| Abstract | Automatic airplane detection in aerial imagery has a variety of applications. Two of the major challenges in this area are variations in scale and direction of the airplanes. In order to solve these challenges, we present a rotation-and-scale invariant airplane proposal generator. This proposal generator is developed based on the symmetric and regular boundaries of airplanes from the top view called symmetric line segments (SLS). Then, the generated proposals are used to train a deep convolutional neural network for removing non-airplane proposals. Since each airplane can have multiple SLS proposals, where some of them are not in the direction of the fuselage, we collect all proposals correspond to one ground truth as a positive bag and the others as the negative instances. To have multiple instance deep learning, we modify the training approach of the network to learn from each positive bag at least one instance as well as all negative instances. Finally, we employ non-maximum suppression to remove duplicate detections. Our experiments on NWPU VHR-10 dataset show that our method is a promising approach for automatic airplane detection in very high resolution images. Moreover, the proposed algorithm can estimate the direction of the airplanes using box-level annotations as an extra achievement. |
| Tasks | Multiple Instance Learning |
| Published | 2018-08-19 |
| URL | http://arxiv.org/abs/1808.06178v1 |
| http://arxiv.org/pdf/1808.06178v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-multiple-instance-learning-for-airplane |
| Repo | |
| Framework | |
Colwell’s Castle Defence: A Custom Game Using Dynamic Difficulty Adjustment to Increase Player Enjoyment
| Title | Colwell’s Castle Defence: A Custom Game Using Dynamic Difficulty Adjustment to Increase Player Enjoyment |
| Authors | Anthony M. Colwell, Frank G. Glavin |
| Abstract | Dynamic Difficulty Adjustment (DDA) is a mechanism used in video games that automatically tailors the individual gaming experience to match an appropriate difficulty setting. This is generally achieved by removing pre-defined difficulty tiers such as Easy, Medium and Hard; and instead concentrates on balancing the gameplay to match the challenge to the individual’s abilities. The work presented in this paper examines the implementation of DDA in a custom survival game developed by the author, namely Colwell’s Castle Defence. The premise of this arcade-style game is to defend a castle from hordes of oncoming enemies. The AI system that we developed adjusts the enemy spawn rate based on the current performance of the player. Specifically, we read the Player Health and Gate Health at the end of each level and then assign the player with an appropriate difficulty tier for the proceeding level. We tested the impact of our technique on thirty human players and concluded, based on questionnaire feedback, that enabling the technique led to more enjoyable gameplay. |
| Tasks | |
| Published | 2018-06-12 |
| URL | http://arxiv.org/abs/1806.04471v1 |
| http://arxiv.org/pdf/1806.04471v1.pdf | |
| PWC | https://paperswithcode.com/paper/colwells-castle-defence-a-custom-game-using |
| Repo | |
| Framework | |
On-field player workload exposure and knee injury risk monitoring via deep learning
| Title | On-field player workload exposure and knee injury risk monitoring via deep learning |
| Authors | William R. Johnson, Ajmal Mian, David G. Lloyd, Jacqueline A. Alderson |
| Abstract | In sports analytics, an understanding of accurate on-field 3D knee joint moments (KJM) could provide an early warning system for athlete workload exposure and knee injury risk. Traditionally, this analysis has relied on captive laboratory force plates and associated downstream biomechanical modeling, and many researchers have approached the problem of portability by extrapolating models built on linear statistics. An alternative approach would be to capitalize on recent advances in deep learning. In this study, using the pre-trained CaffeNet convolutional neural network (CNN) model, multivariate regression of marker-based motion capture to 3D KJM for three sports-related movement types were compared. The strongest overall mean correlation to source modeling of 0.8895 was achieved over the initial 33 % of stance phase for sidestepping. The accuracy of these mean predictions of the three critical KJM associated with anterior cruciate ligament (ACL) injury demonstrate the feasibility of on-field knee injury assessment using deep learning in lieu of laboratory embedded force plates. This multidisciplinary research approach significantly advances machine representation of real-world physical models with practical application for both community and professional level athletes. |
| Tasks | Motion Capture |
| Published | 2018-09-21 |
| URL | https://arxiv.org/abs/1809.08016v3 |
| https://arxiv.org/pdf/1809.08016v3.pdf | |
| PWC | https://paperswithcode.com/paper/on-field-player-workload-exposure-and-knee |
| Repo | |
| Framework | |
Hierarchically Structured Reinforcement Learning for Topically Coherent Visual Story Generation
| Title | Hierarchically Structured Reinforcement Learning for Topically Coherent Visual Story Generation |
| Authors | Qiuyuan Huang, Zhe Gan, Asli Celikyilmaz, Dapeng Wu, Jianfeng Wang, Xiaodong He |
| Abstract | We propose a hierarchically structured reinforcement learning approach to address the challenges of planning for generating coherent multi-sentence stories for the visual storytelling task. Within our framework, the task of generating a story given a sequence of images is divided across a two-level hierarchical decoder. The high-level decoder constructs a plan by generating a semantic concept (i.e., topic) for each image in sequence. The low-level decoder generates a sentence for each image using a semantic compositional network, which effectively grounds the sentence generation conditioned on the topic. The two decoders are jointly trained end-to-end using reinforcement learning. We evaluate our model on the visual storytelling (VIST) dataset. Empirical results from both automatic and human evaluations demonstrate that the proposed hierarchically structured reinforced training achieves significantly better performance compared to a strong flat deep reinforcement learning baseline. |
| Tasks | Visual Storytelling |
| Published | 2018-05-21 |
| URL | http://arxiv.org/abs/1805.08191v3 |
| http://arxiv.org/pdf/1805.08191v3.pdf | |
| PWC | https://paperswithcode.com/paper/hierarchically-structured-reinforcement |
| Repo | |
| Framework | |
Hierarchical Behavioral Repertoires with Unsupervised Descriptors
| Title | Hierarchical Behavioral Repertoires with Unsupervised Descriptors |
| Authors | Antoine Cully, Yiannis Demiris |
| Abstract | Enabling artificial agents to automatically learn complex, versatile and high-performing behaviors is a long-lasting challenge. This paper presents a step in this direction with hierarchical behavioral repertoires that stack several behavioral repertoires to generate sophisticated behaviors. Each repertoire of this architecture uses the lower repertoires to create complex behaviors as sequences of simpler ones, while only the lowest repertoire directly controls the agent’s movements. This paper also introduces a novel approach to automatically define behavioral descriptors thanks to an unsupervised neural network that organizes the produced high-level behaviors. The experiments show that the proposed architecture enables a robot to learn how to draw digits in an unsupervised manner after having learned to draw lines and arcs. Compared to traditional behavioral repertoires, the proposed architecture reduces the dimensionality of the optimization problems by orders of magnitude and provides behaviors with a twice better fitness. More importantly, it enables the transfer of knowledge between robots: a hierarchical repertoire evolved for a robotic arm to draw digits can be transferred to a humanoid robot by simply changing the lowest layer of the hierarchy. This enables the humanoid to draw digits although it has never been trained for this task. |
| Tasks | |
| Published | 2018-04-19 |
| URL | http://arxiv.org/abs/1804.07127v1 |
| http://arxiv.org/pdf/1804.07127v1.pdf | |
| PWC | https://paperswithcode.com/paper/hierarchical-behavioral-repertoires-with |
| Repo | |
| Framework | |
