Paper Group ANR 727
Multimodal Interaction-aware Motion Prediction for Autonomous Street Crossing. Predicting Movie Genres Based on Plot Summaries. Yes, IoU loss is submodular - as a function of the mispredictions. Prediction of Atomization Energy Using Graph Kernel and Active Learning. Skin Lesion Segmentation and Classification for ISIC 2018 Using Traditional Classi …
Multimodal Interaction-aware Motion Prediction for Autonomous Street Crossing
| Title | Multimodal Interaction-aware Motion Prediction for Autonomous Street Crossing |
| Authors | Noha Radwan, Abhinav Valada, Wolfram Burgard |
| Abstract | For mobile robots navigating on sidewalks, it is essential to be able to safely cross street intersections. Most existing approaches rely on the recognition of the traffic light signal to make an informed crossing decision. Although these approaches have been crucial enablers for urban navigation, the capabilities of robots employing such approaches are still limited to navigating only on streets containing signalized intersections. In this paper, we address this challenge and propose a multimodal convolutional neural network framework to predict the safety of a street intersection for crossing. Our architecture consists of two subnetworks; an interaction-aware trajectory estimation stream IA-TCNN, that predicts the future states of all observed traffic participants in the scene, and a traffic light recognition stream AtteNet. Our IA-TCNN utilizes dilated causal convolutions to model the behavior of the observable dynamic agents in the scene without explicitly assigning priorities to the interactions among them. While AtteNet utilizes Squeeze-Excitation blocks to learn a content-aware mechanism for selecting the relevant features from the data, thereby improving the noise robustness. Learned representations from the traffic light recognition stream are fused with the estimated trajectories from the motion prediction stream to learn the crossing decision. Furthermore, we extend our previously introduced Freiburg Street Crossing dataset with sequences captured at different types of intersections, demonstrating complex interactions among the traffic participants. Extensive experimental evaluations on public benchmark datasets and our proposed dataset demonstrate that our network achieves state-of-the-art performance for each of the subtasks, as well as for the crossing safety prediction. |
| Tasks | motion prediction |
| Published | 2018-08-21 |
| URL | https://arxiv.org/abs/1808.06887v3 |
| https://arxiv.org/pdf/1808.06887v3.pdf | |
| PWC | https://paperswithcode.com/paper/multimodal-interaction-aware-motion |
| Repo | |
| Framework | |
Predicting Movie Genres Based on Plot Summaries
| Title | Predicting Movie Genres Based on Plot Summaries |
| Authors | Quan Hoang |
| Abstract | This project explores several Machine Learning methods to predict movie genres based on plot summaries. Naive Bayes, Word2Vec+XGBoost and Recurrent Neural Networks are used for text classification, while K-binary transformation, rank method and probabilistic classification with learned probability threshold are employed for the multi-label problem involved in the genre tagging task.Experiments with more than 250,000 movies show that employing the Gated Recurrent Units (GRU) neural networks for the probabilistic classification with learned probability threshold approach achieves the best result on the test set. The model attains a Jaccard Index of 50.0%, a F-score of 0.56, and a hit rate of 80.5%. |
| Tasks | Text Classification |
| Published | 2018-01-15 |
| URL | http://arxiv.org/abs/1801.04813v1 |
| http://arxiv.org/pdf/1801.04813v1.pdf | |
| PWC | https://paperswithcode.com/paper/predicting-movie-genres-based-on-plot |
| Repo | |
| Framework | |
Yes, IoU loss is submodular - as a function of the mispredictions
| Title | Yes, IoU loss is submodular - as a function of the mispredictions |
| Authors | Maxim Berman, Matthew B. Blaschko, Amal Rannen Triki, Jiaqian Yu |
| Abstract | This note is a response to [7] in which it is claimed that [13, Proposition 11] is false. We demonstrate here that this assertion in [7] is false, and is based on a misreading of the notion of set membership in [13, Proposition 11]. We maintain that [13, Proposition 11] is true. ([7] = arXiv:1809.00593, [13] = arXiv:1512.07797) |
| Tasks | |
| Published | 2018-09-06 |
| URL | http://arxiv.org/abs/1809.01845v1 |
| http://arxiv.org/pdf/1809.01845v1.pdf | |
| PWC | https://paperswithcode.com/paper/yes-iou-loss-is-submodular-as-a-function-of |
| Repo | |
| Framework | |
Prediction of Atomization Energy Using Graph Kernel and Active Learning
| Title | Prediction of Atomization Energy Using Graph Kernel and Active Learning |
| Authors | Yu-Hang Tang, Wibe A. de Jong |
| Abstract | Data-driven prediction of molecular properties presents unique challenges to the design of machine learning methods concerning data structure/dimensionality, symmetry adaption, and confidence management. In this paper, we present a kernel-based pipeline that can learn and predict the atomization energy of molecules with high accuracy. The framework employs Gaussian process regression to perform predictions based on the similarity between molecules, which is computed using the marginalized graph kernel. To apply the marginalized graph kernel, a spatial adjacency rule is first employed to convert molecules into graphs whose vertices and edges are labeled by elements and interatomic distances, respectively. We then derive formulas for the efficient evaluation of the kernel. Specific functional components for the marginalized graph kernel are proposed, while the effect of the associated hyperparameters on accuracy and predictive confidence are examined. We show that the graph kernel is particularly suitable for predicting extensive properties because its convolutional structure coincides with that of the covariance formula between sums of random variables. Using an active learning procedure, we demonstrate that the proposed method can achieve a mean absolute error of 0.62 +- 0.01 kcal/mol using as few as 2000 training samples on the QM7 data set. |
| Tasks | Active Learning |
| Published | 2018-10-16 |
| URL | http://arxiv.org/abs/1810.07310v3 |
| http://arxiv.org/pdf/1810.07310v3.pdf | |
| PWC | https://paperswithcode.com/paper/prediction-of-atomization-energy-using-graph |
| Repo | |
| Framework | |
Skin Lesion Segmentation and Classification for ISIC 2018 Using Traditional Classifiers with Hand-Crafted Features
| Title | Skin Lesion Segmentation and Classification for ISIC 2018 Using Traditional Classifiers with Hand-Crafted Features |
| Authors | Russell C. Hardie, Redha Ali, Manawaduge Supun De Silva, Temesguen Messay Kebede |
| Abstract | This paper provides the required description of the methods used to obtain submitted results for Task1 and Task 3 of ISIC 2018: Skin Lesion Analysis Towards Melanoma Detection. The results have been created by a team of researchers at the University of Dayton Signal and Image Processing Lab. In this submission, traditional classifiers with hand-crafted features are utilized for Task 1 and Task 3. Our team is providing additional separate submissions using deep learning methods for comparison. |
| Tasks | Lesion Segmentation |
| Published | 2018-07-18 |
| URL | http://arxiv.org/abs/1807.07001v1 |
| http://arxiv.org/pdf/1807.07001v1.pdf | |
| PWC | https://paperswithcode.com/paper/skin-lesion-segmentation-and-classification-1 |
| Repo | |
| Framework | |
Deterministic Pod Repositioning Problem in Robotic Mobile Fulfillment Systems
| Title | Deterministic Pod Repositioning Problem in Robotic Mobile Fulfillment Systems |
| Authors | Ruslan Krenzler, Lin Xie, Hanyi Li |
| Abstract | In a robotic mobile fulfillment system, robots bring shelves, called pods, with storage items from the storage area to pick stations. At every pick station there is a person – the picker – who takes parts from the pod and packs them into boxes according to orders. Usually there are multiple shelves at the pick station. In this case, they build a queue with the picker at its head. When the picker does not need the pod any more, a robot transports the pod back to the storage area. At that time, we need to answer a question: “Where is the optimal place in the inventory to put this pod back?". It is a tough question, because there are many uncertainties to consider before answering it. Moreover, each decision made to answer the question influences the subsequent ones. The goal of this paper is to answer the question properly. We call this problem the Pod Repositioning Problem and formulate a deterministic model. This model is tested with different algorithms, including binary integer programming, cheapest place, fixed place, random place, genetic algorithms, and a novel algorithm called tetris. |
| Tasks | |
| Published | 2018-10-09 |
| URL | http://arxiv.org/abs/1810.05514v1 |
| http://arxiv.org/pdf/1810.05514v1.pdf | |
| PWC | https://paperswithcode.com/paper/deterministic-pod-repositioning-problem-in |
| Repo | |
| Framework | |
Multi-Task Learning for Email Search Ranking with Auxiliary Query Clustering
| Title | Multi-Task Learning for Email Search Ranking with Auxiliary Query Clustering |
| Authors | Jiaming Shen, Maryam Karimzadehgan, Michael Bendersky, Zhen Qin, Donald Metzler |
| Abstract | User information needs vary significantly across different tasks, and therefore their queries will also differ considerably in their expressiveness and semantics. Many studies have been proposed to model such query diversity by obtaining query types and building query-dependent ranking models. These studies typically require either a labeled query dataset or clicks from multiple users aggregated over the same document. These techniques, however, are not applicable when manual query labeling is not viable, and aggregated clicks are unavailable due to the private nature of the document collection, e.g., in email search scenarios. In this paper, we study how to obtain query type in an unsupervised fashion and how to incorporate this information into query-dependent ranking models. We first develop a hierarchical clustering algorithm based on truncated SVD and varimax rotation to obtain coarse-to-fine query types. Then, we study three query-dependent ranking models, including two neural models that leverage query type information as additional features, and one novel multi-task neural model that views query type as the label for the auxiliary query cluster prediction task. This multi-task model is trained to simultaneously rank documents and predict query types. Our experiments on tens of millions of real-world email search queries demonstrate that the proposed multi-task model can significantly outperform the baseline neural ranking models, which either do not incorporate query type information or just simply feed query type as an additional feature. |
| Tasks | Multi-Task Learning |
| Published | 2018-09-15 |
| URL | https://arxiv.org/abs/1809.05618v1 |
| https://arxiv.org/pdf/1809.05618v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-task-learning-for-email-search-ranking |
| Repo | |
| Framework | |
Recognizing Disguised Faces in the Wild
| Title | Recognizing Disguised Faces in the Wild |
| Authors | Maneet Singh, Richa Singh, Mayank Vatsa, Nalini Ratha, Rama Chellappa |
| Abstract | Research in face recognition has seen tremendous growth over the past couple of decades. Beginning from algorithms capable of performing recognition in constrained environments, the current face recognition systems achieve very high accuracies on large-scale unconstrained face datasets. While upcoming algorithms continue to achieve improved performance, a majority of the face recognition systems are susceptible to failure under disguise variations, one of the most challenging covariate of face recognition. Most of the existing disguise datasets contain images with limited variations, often captured in controlled settings. This does not simulate a real world scenario, where both intentional and unintentional unconstrained disguises are encountered by a face recognition system. In this paper, a novel Disguised Faces in the Wild (DFW) dataset is proposed which contains over 11000 images of 1000 identities with different types of disguise accessories. The dataset is collected from the Internet, resulting in unconstrained face images similar to real world settings. This is the first-of-a-kind dataset with the availability of impersonator and genuine obfuscated face images for each subject. The proposed dataset has been analyzed in terms of three levels of difficulty: (i) easy, (ii) medium, and (iii) hard in order to showcase the challenging nature of the problem. It is our view that the research community can greatly benefit from the DFW dataset in terms of developing algorithms robust to such adversaries. The proposed dataset was released as part of the First International Workshop and Competition on Disguised Faces in the Wild at CVPR, 2018. This paper presents the DFW dataset in detail, including the evaluation protocols, baseline results, performance analysis of the submissions received as part of the competition, and three levels of difficulties of the DFW challenge dataset. |
| Tasks | Disguised Face Verification, Face Recognition |
| Published | 2018-11-21 |
| URL | http://arxiv.org/abs/1811.08837v1 |
| http://arxiv.org/pdf/1811.08837v1.pdf | |
| PWC | https://paperswithcode.com/paper/recognizing-disguised-faces-in-the-wild |
| Repo | |
| Framework | |
Towards Emotion Recognition: A Persistent Entropy Application
| Title | Towards Emotion Recognition: A Persistent Entropy Application |
| Authors | R. Gonzalez-Diaz, E. Paluzo-Hidalgo, J. F. Quesada |
| Abstract | Emotion recognition and classification is a very active area of research. In this paper, we present a first approach to emotion classification using persistent entropy and support vector machines. A topology-based model is applied to obtain a single real number from each raw signal. These data are used as input of a support vector machine to classify signals into 8 different emotions (calm, happy, sad, angry, fearful, disgust and surprised). |
| Tasks | Emotion Classification, Emotion Recognition |
| Published | 2018-11-21 |
| URL | http://arxiv.org/abs/1811.09607v1 |
| http://arxiv.org/pdf/1811.09607v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-emotion-recognition-a-persistent |
| Repo | |
| Framework | |
Disjoint Label Space Transfer Learning with Common Factorised Space
| Title | Disjoint Label Space Transfer Learning with Common Factorised Space |
| Authors | Xiaobin Chang, Yongxin Yang, Tao Xiang, Timothy M. Hospedales |
| Abstract | In this paper, a unified approach is presented to transfer learning that addresses several source and target domain label-space and annotation assumptions with a single model. It is particularly effective in handling a challenging case, where source and target label-spaces are disjoint, and outperforms alternatives in both unsupervised and semi-supervised settings. The key ingredient is a common representation termed Common Factorised Space. It is shared between source and target domains, and trained with an unsupervised factorisation loss and a graph-based loss. With a wide range of experiments, we demonstrate the flexibility, relevance and efficacy of our method, both in the challenging cases with disjoint label spaces, and in the more conventional cases such as unsupervised domain adaptation, where the source and target domains share the same label-sets. |
| Tasks | Domain Adaptation, Transfer Learning, Unsupervised Domain Adaptation |
| Published | 2018-12-06 |
| URL | http://arxiv.org/abs/1812.02605v1 |
| http://arxiv.org/pdf/1812.02605v1.pdf | |
| PWC | https://paperswithcode.com/paper/disjoint-label-space-transfer-learning-with |
| Repo | |
| Framework | |
Syntactic Dependency Representations in Neural Relation Classification
| Title | Syntactic Dependency Representations in Neural Relation Classification |
| Authors | Farhad Nooralahzadeh, Lilja Øvrelid |
| Abstract | We investigate the use of different syntactic dependency representations in a neural relation classification task and compare the CoNLL, Stanford Basic and Universal Dependencies schemes. We further compare with a syntax-agnostic approach and perform an error analysis in order to gain a better understanding of the results. |
| Tasks | Relation Classification |
| Published | 2018-05-28 |
| URL | http://arxiv.org/abs/1805.11461v1 |
| http://arxiv.org/pdf/1805.11461v1.pdf | |
| PWC | https://paperswithcode.com/paper/syntactic-dependency-representations-in |
| Repo | |
| Framework | |
Model-based Pricing for Machine Learning in a Data Marketplace
| Title | Model-based Pricing for Machine Learning in a Data Marketplace |
| Authors | Lingjiao Chen, Paraschos Koutris, Arun Kumar |
| Abstract | Data analytics using machine learning (ML) has become ubiquitous in science, business intelligence, journalism and many other domains. While a lot of work focuses on reducing the training cost, inference runtime and storage cost of ML models, little work studies how to reduce the cost of data acquisition, which potentially leads to a loss of sellers’ revenue and buyers’ affordability and efficiency. In this paper, we propose a model-based pricing (MBP) framework, which instead of pricing the data, directly prices ML model instances. We first formally describe the desired properties of the MBP framework, with a focus on avoiding arbitrage. Next, we show a concrete realization of the MBP framework via a noise injection approach, which provably satisfies the desired formal properties. Based on the proposed framework, we then provide algorithmic solutions on how the seller can assign prices to models under different market scenarios (such as to maximize revenue). Finally, we conduct extensive experiments, which validate that the MBP framework can provide high revenue to the seller, high affordability to the buyer, and also operate on low runtime cost. |
| Tasks | |
| Published | 2018-05-26 |
| URL | http://arxiv.org/abs/1805.11450v1 |
| http://arxiv.org/pdf/1805.11450v1.pdf | |
| PWC | https://paperswithcode.com/paper/model-based-pricing-for-machine-learning-in-a |
| Repo | |
| Framework | |
Learning Shared Dynamics with Meta-World Models
| Title | Learning Shared Dynamics with Meta-World Models |
| Authors | Lisheng Wu, Minne Li, Jun Wang |
| Abstract | Humans have consciousness as the ability to perceive events and objects: a mental model of the world developed from the most impoverished of visual stimuli, enabling humans to make rapid decisions and take actions. Although spatial and temporal aspects of different scenes are generally diverse, the underlying physics among environments still work the same way, thus learning an abstract description of shared physical dynamics helps human to understand the world. In this paper, we explore building this mental world with neural network models through multi-task learning, namely the meta-world model. We show through extensive experiments that our proposed meta-world models successfully capture the common dynamics over the compact representations of visually different environments from Atari Games. We also demonstrate that agents equipped with our meta-world model possess the ability of visual self-recognition, i.e., recognize themselves from the reflected mirrored environment derived from the classic mirror self-recognition test (MSR). |
| Tasks | Atari Games, Multi-Task Learning |
| Published | 2018-11-05 |
| URL | http://arxiv.org/abs/1811.01741v1 |
| http://arxiv.org/pdf/1811.01741v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-shared-dynamics-with-meta-world |
| Repo | |
| Framework | |
Contextual Memory Trees
| Title | Contextual Memory Trees |
| Authors | Wen Sun, Alina Beygelzimer, Hal Daumé III, John Langford, Paul Mineiro |
| Abstract | We design and study a Contextual Memory Tree (CMT), a learning memory controller that inserts new memories into an experience store of unbounded size. It is designed to efficiently query for memories from that store, supporting logarithmic time insertion and retrieval operations. Hence CMT can be integrated into existing statistical learning algorithms as an augmented memory unit without substantially increasing training and inference computation. Furthermore CMT operates as a reduction to classification, allowing it to benefit from advances in representation or architecture. We demonstrate the efficacy of CMT by augmenting existing multi-class and multi-label classification algorithms with CMT and observe statistical improvement. We also test CMT learning on several image-captioning tasks to demonstrate that it performs computationally better than a simple nearest neighbors memory system while benefitting from reward learning. |
| Tasks | Image Captioning, Multi-Label Classification |
| Published | 2018-07-17 |
| URL | https://arxiv.org/abs/1807.06473v3 |
| https://arxiv.org/pdf/1807.06473v3.pdf | |
| PWC | https://paperswithcode.com/paper/contextual-memory-trees |
| Repo | |
| Framework | |
Novel Feature-Based Clustering of Micro-Panel Data (CluMP)
| Title | Novel Feature-Based Clustering of Micro-Panel Data (CluMP) |
| Authors | Lukas Sobisek, Maria Stachova, Jan Fojtik |
| Abstract | Micro-panel data are collected and analysed in many research and industry areas. Cluster analysis of micro-panel data is an unsupervised learning exploratory method identifying subgroup clusters in a data set which include homogeneous objects in terms of the development dynamics of monitored variables. The supply of clustering methods tailored to micro-panel data is limited. The present paper focuses on a feature-based clustering method, introducing a novel two-step characteristic-based approach designed for this type of data. The proposed CluMP method aims to identify clusters that are at least as internally homogeneous and externally heterogeneous as those obtained by alternative methods already implemented in the statistical system R. We compare the clustering performance of the devised algorithm with two extant methods using simulated micro-panel data sets. Our approach has yielded similar or better outcomes than the other methods, the advantage of the proposed algorithm being time efficiency which makes it applicable for large data sets. |
| Tasks | |
| Published | 2018-07-16 |
| URL | http://arxiv.org/abs/1807.05926v1 |
| http://arxiv.org/pdf/1807.05926v1.pdf | |
| PWC | https://paperswithcode.com/paper/novel-feature-based-clustering-of-micro-panel |
| Repo | |
| Framework | |
