Paper Group ANR 821
Lifelong Path Planning with Kinematic Constraints for Multi-Agent Pickup and Delivery. Distributionally Robust Semi-Supervised Learning for People-Centric Sensing. Sketching for Latent Dirichlet-Categorical Models. HANDS18: Methods, Techniques and Applications for Hand Observation. Human-Machine Interface for Remote Training of Robot Tasks. Debuggi …
Lifelong Path Planning with Kinematic Constraints for Multi-Agent Pickup and Delivery
Title | Lifelong Path Planning with Kinematic Constraints for Multi-Agent Pickup and Delivery |
Authors | Hang Ma, Wolfgang Hönig, T. K. Satish Kumar, Nora Ayanian, Sven Koenig |
Abstract | The Multi-Agent Pickup and Delivery (MAPD) problem models applications where a large number of agents attend to a stream of incoming pickup-and-delivery tasks. Token Passing (TP) is a recent MAPD algorithm that is efficient and effective. We make TP even more efficient and effective by using a novel combinatorial search algorithm, called Safe Interval Path Planning with Reservation Table (SIPPwRT), for single-agent path planning. SIPPwRT uses an advanced data structure that allows for fast updates and lookups of the current paths of all agents in an online setting. The resulting MAPD algorithm TP-SIPPwRT takes kinematic constraints of real robots into account directly during planning, computes continuous agent movements with given velocities that work on non-holonomic robots rather than discrete agent movements with uniform velocity, and is complete for well-formed MAPD instances. We demonstrate its benefits for automated warehouses using both an agent simulator and a standard robot simulator. For example, we demonstrate that it can compute paths for hundreds of agents and thousands of tasks in seconds and is more efficient and effective than existing MAPD algorithms that use a post-processing step to adapt their paths to continuous agent movements with given velocities. |
Tasks | |
Published | 2018-12-15 |
URL | http://arxiv.org/abs/1812.06355v1 |
http://arxiv.org/pdf/1812.06355v1.pdf | |
PWC | https://paperswithcode.com/paper/lifelong-path-planning-with-kinematic |
Repo | |
Framework | |
Distributionally Robust Semi-Supervised Learning for People-Centric Sensing
Title | Distributionally Robust Semi-Supervised Learning for People-Centric Sensing |
Authors | Kaixuan Chen, Lina Yao, Dalin Zhang, Xiaojun Chang, Guodong Long, Sen Wang |
Abstract | Semi-supervised learning is crucial for alleviating labelling burdens in people-centric sensing. However, human-generated data inherently suffer from distribution shift in semi-supervised learning due to the diverse biological conditions and behavior patterns of humans. To address this problem, we propose a generic distributionally robust model for semi-supervised learning on distributionally shifted data. Considering both the discrepancy and the consistency between the labeled data and the unlabeled data, we learn the latent features that reduce person-specific discrepancy and preserve task-specific consistency. We evaluate our model in a variety of people-centric recognition tasks on real-world datasets, including intention recognition, activity recognition, muscular movement recognition and gesture recognition. The experiment results demonstrate that the proposed model outperforms the state-of-the-art methods. |
Tasks | Activity Recognition, Gesture Recognition, Intent Detection, Muscular Movement Recognition |
Published | 2018-11-12 |
URL | http://arxiv.org/abs/1811.05299v1 |
http://arxiv.org/pdf/1811.05299v1.pdf | |
PWC | https://paperswithcode.com/paper/distributionally-robust-semi-supervised |
Repo | |
Framework | |
Sketching for Latent Dirichlet-Categorical Models
Title | Sketching for Latent Dirichlet-Categorical Models |
Authors | Joseph Tassarotti, Jean-Baptiste Tristan, Michael Wick |
Abstract | Recent work has explored transforming data sets into smaller, approximate summaries in order to scale Bayesian inference. We examine a related problem in which the parameters of a Bayesian model are very large and expensive to store in memory, and propose more compact representations of parameter values that can be used during inference. We focus on a class of graphical models that we refer to as latent Dirichlet-Categorical models, and show how a combination of two sketching algorithms known as count-min sketch and approximate counters provide an efficient representation for them. We show that this sketch combination – which, despite having been used before in NLP applications, has not been previously analyzed – enjoys desirable properties. We prove that for this class of models, when the sketches are used during Markov Chain Monte Carlo inference, the equilibrium of sketched MCMC converges to that of the exact chain as sketch parameters are tuned to reduce the error rate. |
Tasks | Bayesian Inference |
Published | 2018-10-02 |
URL | http://arxiv.org/abs/1810.01400v1 |
http://arxiv.org/pdf/1810.01400v1.pdf | |
PWC | https://paperswithcode.com/paper/sketching-for-latent-dirichlet-categorical |
Repo | |
Framework | |
HANDS18: Methods, Techniques and Applications for Hand Observation
Title | HANDS18: Methods, Techniques and Applications for Hand Observation |
Authors | Iason Oikonomidis, Guillermo Garcia-Hernando, Angela Yao, Antonis Argyros, Vincent Lepetit, Tae-Kyun Kim |
Abstract | This report outlines the proceedings of the Fourth International Workshop on Observing and Understanding Hands in Action (HANDS 2018). The fourth instantiation of this workshop attracted significant interest from both academia and the industry. The program of the workshop included regular papers that are published as the workshop’s proceedings, extended abstracts, invited posters, and invited talks. Topics of the submitted works and invited talks and posters included novel methods for hand pose estimation from RGB, depth, or skeletal data, datasets for special cases and real-world applications, and techniques for hand motion re-targeting and hand gesture recognition. The invited speakers are leaders in their respective areas of specialization, coming from both industry and academia. The main conclusions that can be drawn are the turn of the community towards RGB data and the maturation of some methods and techniques, which in turn has led to increasing interest for real-world applications. |
Tasks | Gesture Recognition, Hand Gesture Recognition, Hand-Gesture Recognition, Hand Pose Estimation, Pose Estimation |
Published | 2018-10-25 |
URL | http://arxiv.org/abs/1810.10818v1 |
http://arxiv.org/pdf/1810.10818v1.pdf | |
PWC | https://paperswithcode.com/paper/hands18-methods-techniques-and-applications |
Repo | |
Framework | |
Human-Machine Interface for Remote Training of Robot Tasks
Title | Human-Machine Interface for Remote Training of Robot Tasks |
Authors | Jordi Spranger, Roxana Buzatoiu, Athanasios Polydoros, Lazaros Nalpantidis, Evangelos Boukas |
Abstract | Regardless of their industrial or research application, the streamlining of robot operations is limited by the proximity of experienced users to the actual hardware. Be it massive open online robotics courses, crowd-sourcing of robot task training, or remote research on massive robot farms for machine learning, the need to create an apt remote Human-Machine Interface is quite prevalent. The paper at hand proposes a novel solution to the programming/training of remote robots employing an intuitive and accurate user-interface which offers all the benefits of working with real robots without imposing delays and inefficiency. The system includes: a vision-based 3D hand detection and gesture recognition subsystem, a simulated digital twin of a robot as visual feedback, and the “remote” robot learning/executing trajectories using dynamic motion primitives. Our results indicate that the system is a promising solution to the problem of remote training of robot tasks. |
Tasks | Gesture Recognition |
Published | 2018-09-25 |
URL | http://arxiv.org/abs/1809.09558v1 |
http://arxiv.org/pdf/1809.09558v1.pdf | |
PWC | https://paperswithcode.com/paper/human-machine-interface-for-remote-training |
Repo | |
Framework | |
Debugging Non-Ground ASP Programs: Technique and Graphical Tools
Title | Debugging Non-Ground ASP Programs: Technique and Graphical Tools |
Authors | Carmine Dodaro, Philip Gasteiger, Kristian Reale, Francesco Ricca, Konstantin Schekotihin |
Abstract | Answer Set Programming (ASP) is one of the major declarative programming paradigms in the area of logic programming and non-monotonic reasoning. Despite that ASP features a simple syntax and an intuitive semantics, errors are common during the development of ASP programs. In this paper we propose a novel debugging approach allowing for interactive localization of bugs in non-ground programs. The new approach points the user directly to a set of non-ground rules involved in the bug, which might be refined (up to the point in which the bug is easily identified) by asking the programmer a sequence of questions on an expected answer set. The approach has been implemented on top of the ASP solver WASP. The resulting debugger has been complemented by a user-friendly graphical interface, and integrated in ASPIDE, a rich IDE for answer set programs. In addition, an empirical analysis shows that the new debugger is not affected by the grounding blowup limiting the application of previous approaches based on meta-programming. Under consideration in Theory and Practice of Logic Programming (TPLP). |
Tasks | |
Published | 2018-08-01 |
URL | http://arxiv.org/abs/1808.00417v1 |
http://arxiv.org/pdf/1808.00417v1.pdf | |
PWC | https://paperswithcode.com/paper/debugging-non-ground-asp-programs-technique |
Repo | |
Framework | |
Multi-Agent Path Finding with Deadlines: Preliminary Results
Title | Multi-Agent Path Finding with Deadlines: Preliminary Results |
Authors | Hang Ma, Glenn Wagner, Ariel Felner, Jiaoyang Li, T. K. Satish Kumar, Sven Koenig |
Abstract | We formalize the problem of multi-agent path finding with deadlines (MAPF-DL). The objective is to maximize the number of agents that can reach their given goal vertices from their given start vertices within a given deadline, without colliding with each other. We first show that the MAPF-DL problem is NP-hard to solve optimally. We then present an optimal MAPF-DL algorithm based on a reduction of the MAPF-DL problem to a flow problem and a subsequent compact integer linear programming formulation of the resulting reduced abstracted multi-commodity flow network. |
Tasks | Multi-Agent Path Finding |
Published | 2018-05-13 |
URL | http://arxiv.org/abs/1805.04961v1 |
http://arxiv.org/pdf/1805.04961v1.pdf | |
PWC | https://paperswithcode.com/paper/multi-agent-path-finding-with-deadlines-1 |
Repo | |
Framework | |
Featureless: Bypassing feature extraction in action categorization
Title | Featureless: Bypassing feature extraction in action categorization |
Authors | Silvia L. Pintea, Pascal S. Mettes, Jan C. van Gemert, Arnold W. M. Smeulders |
Abstract | This method introduces an efficient manner of learning action categories without the need of feature estimation. The approach starts from low-level values, in a similar style to the successful CNN methods. However, rather than extracting general image features, we learn to predict specific video representations from raw video data. The benefit of such an approach is that at the same computational expense it can predict 2 D video representations as well as 3 D ones, based on motion. The proposed model relies on discriminative Waldboost, which we enhance to a multiclass formulation for the purpose of learning video representations. The suitability of the proposed approach as well as its time efficiency are tested on the UCF11 action recognition dataset. |
Tasks | Temporal Action Localization |
Published | 2018-03-19 |
URL | http://arxiv.org/abs/1803.06962v1 |
http://arxiv.org/pdf/1803.06962v1.pdf | |
PWC | https://paperswithcode.com/paper/featureless-bypassing-feature-extraction-in |
Repo | |
Framework | |
A Generic Multi-modal Dynamic Gesture Recognition System using Machine Learning
Title | A Generic Multi-modal Dynamic Gesture Recognition System using Machine Learning |
Authors | Gautham Krishna G, Karthik Subramanian Nathan, Yogesh Kumar B, Ankith A Prabhu, Ajay Kannan, Vineeth Vijayaraghavan |
Abstract | Human computer interaction facilitates intelligent communication between humans and computers, in which gesture recognition plays a prominent role. This paper proposes a machine learning system to identify dynamic gestures using tri-axial acceleration data acquired from two public datasets. These datasets, uWave and Sony, were acquired using accelerometers embedded in Wii remotes and smartwatches, respectively. A dynamic gesture signed by the user is characterized by a generic set of features extracted across time and frequency domains. The system was analyzed from an end-user perspective and was modelled to operate in three modes. The modes of operation determine the subsets of data to be used for training and testing the system. From an initial set of seven classifiers, three were chosen to evaluate each dataset across all modes rendering the system towards mode-neutrality and dataset-independence. The proposed system is able to classify gestures performed at varying speeds with minimum preprocessing, making it computationally efficient. Moreover, this system was found to run on a low-cost embedded platform - Raspberry Pi Zero (USD 5), making it economically viable. |
Tasks | Gesture Recognition |
Published | 2018-09-16 |
URL | http://arxiv.org/abs/1809.05839v1 |
http://arxiv.org/pdf/1809.05839v1.pdf | |
PWC | https://paperswithcode.com/paper/a-generic-multi-modal-dynamic-gesture |
Repo | |
Framework | |
Phaseless Subspace Tracking
Title | Phaseless Subspace Tracking |
Authors | Seyedehsara Nayer, Namrata Vaswani |
Abstract | This work takes the first steps towards solving the “phaseless subspace tracking” (PST) problem. PST involves recovering a time sequence of signals (or images) from phaseless linear projections of each signal under the following structural assumption: the signal sequence is generated from a much lower dimensional subspace (than the signal dimension) and this subspace can change over time, albeit gradually. It can be simply understood as a dynamic (time-varying subspace) extension of the low-rank phase retrieval problem studied in recent work. |
Tasks | |
Published | 2018-09-11 |
URL | http://arxiv.org/abs/1809.04176v1 |
http://arxiv.org/pdf/1809.04176v1.pdf | |
PWC | https://paperswithcode.com/paper/phaseless-subspace-tracking |
Repo | |
Framework | |
Egocentric Gesture Recognition for Head-Mounted AR devices
Title | Egocentric Gesture Recognition for Head-Mounted AR devices |
Authors | Tejo Chalasani, Jan Ondrej, Aljosa Smolic |
Abstract | Natural interaction with virtual objects in AR/VR environments makes for a smooth user experience. Gestures are a natural extension from real world to augmented space to achieve these interactions. Finding discriminating spatio-temporal features relevant to gestures and hands in ego-view is the primary challenge for recognising egocentric gestures. In this work we propose a data driven end-to-end deep learning approach to address the problem of egocentric gesture recognition, which combines an ego-hand encoder network to find ego-hand features, and a recurrent neural network to discern temporally discriminating features. Since deep learning networks are data intensive, we propose a novel data augmentation technique using green screen capture to alleviate the problem of ground truth annotation. In addition we publish a dataset of 10 gestures performed in a natural fashion in front of a green screen for training and the same 10 gestures performed in different natural scenes without green screen for validation. We also present the results of our network’s performance in comparison to the state-of-the-art using the AirGest dataset |
Tasks | Data Augmentation, Gesture Recognition |
Published | 2018-08-16 |
URL | http://arxiv.org/abs/1808.05380v1 |
http://arxiv.org/pdf/1808.05380v1.pdf | |
PWC | https://paperswithcode.com/paper/egocentric-gesture-recognition-for-head |
Repo | |
Framework | |
Clustered Monotone Transforms for Rating Factorization
Title | Clustered Monotone Transforms for Rating Factorization |
Authors | Gaurush Hiranandani, Raghav Somani, Oluwasanmi Koyejo, Sreangsu Acharyya |
Abstract | Exploiting low-rank structure of the user-item rating matrix has been the crux of many recommendation engines. However, existing recommendation engines force raters with heterogeneous behavior profiles to map their intrinsic rating scales to a common rating scale (e.g. 1-5). This non-linear transformation of the rating scale shatters the low-rank structure of the rating matrix, therefore resulting in a poor fit and consequentially, poor recommendations. In this paper, we propose Clustered Monotone Transforms for Rating Factorization (CMTRF), a novel approach to perform regression up to unknown monotonic transforms over unknown population segments. Essentially, for recommendation systems, the technique searches for monotonic transformations of the rating scales resulting in a better fit. This is combined with an underlying matrix factorization regression model that couples the user-wise ratings to exploit shared low dimensional structure. The rating scale transformations can be generated for each user, for a cluster of users, or for all the users at once, forming the basis of three simple and efficient algorithms proposed in this paper, all of which alternate between transformation of the rating scales and matrix factorization regression. Despite the non-convexity, CMTRF is theoretically shown to recover a unique solution under mild conditions. Experimental results on two synthetic and seven real-world datasets show that CMTRF outperforms other state-of-the-art baselines. |
Tasks | Recommendation Systems |
Published | 2018-10-31 |
URL | http://arxiv.org/abs/1811.00159v1 |
http://arxiv.org/pdf/1811.00159v1.pdf | |
PWC | https://paperswithcode.com/paper/clustered-monotone-transforms-for-rating |
Repo | |
Framework | |
Organization and Independence or Interdependence? Study of the Neurophysiological Dynamics of Syntactic and Semantic Processing
Title | Organization and Independence or Interdependence? Study of the Neurophysiological Dynamics of Syntactic and Semantic Processing |
Authors | Sabine Ploux, Viviane Déprez |
Abstract | In this article we present a multivariate model for determining the different syntactic, semantic, and form (surface-structure) processes underlying the comprehension of simple phrases. This model is applied to EEG signals recorded during a reading task. The results show a hierarchical precedence of the neurolinguistic processes : form, then syntactic and lastly semantic processes. We also found (a) that verbs are at the heart of phrase syntax processing, (b) an interaction between syntactic movement within the phrase, and semantic processes derived from a person-centered reference frame. Eigenvectors of the multivariate model provide electrode-times profiles that separate the distinctive linguistic processes and/or highlight their interaction. The accordance of these findings with different linguistic theories are discussed. |
Tasks | EEG |
Published | 2018-04-16 |
URL | http://arxiv.org/abs/1804.05686v1 |
http://arxiv.org/pdf/1804.05686v1.pdf | |
PWC | https://paperswithcode.com/paper/organization-and-independence-or |
Repo | |
Framework | |
Deep Learning of Geometric Constellation Shaping including Fiber Nonlinearities
Title | Deep Learning of Geometric Constellation Shaping including Fiber Nonlinearities |
Authors | Rasmus T. Jones, Tobias A. Eriksson, Metodi P. Yankov, Darko Zibar |
Abstract | A new geometric shaping method is proposed, leveraging unsupervised machine learning to optimize the constellation design. The learned constellation mitigates nonlinear effects with gains up to 0.13 bit/4D when trained with a simplified fiber channel model. |
Tasks | |
Published | 2018-05-10 |
URL | http://arxiv.org/abs/1805.03785v1 |
http://arxiv.org/pdf/1805.03785v1.pdf | |
PWC | https://paperswithcode.com/paper/deep-learning-of-geometric-constellation |
Repo | |
Framework | |
SeVeN: Augmenting Word Embeddings with Unsupervised Relation Vectors
Title | SeVeN: Augmenting Word Embeddings with Unsupervised Relation Vectors |
Authors | Luis Espinosa-Anke, Steven Schockaert |
Abstract | We present SeVeN (Semantic Vector Networks), a hybrid resource that encodes relationships between words in the form of a graph. Different from traditional semantic networks, these relations are represented as vectors in a continuous vector space. We propose a simple pipeline for learning such relation vectors, which is based on word vector averaging in combination with an ad hoc autoencoder. We show that by explicitly encoding relational information in a dedicated vector space we can capture aspects of word meaning that are complementary to what is captured by word embeddings. For example, by examining clusters of relation vectors, we observe that relational similarities can be identified at a more abstract level than with traditional word vector differences. Finally, we test the effectiveness of semantic vector networks in two tasks: measuring word similarity and neural text categorization. SeVeN is available at bitbucket.org/luisespinosa/seven. |
Tasks | Text Categorization, Word Embeddings |
Published | 2018-08-18 |
URL | http://arxiv.org/abs/1808.06068v1 |
http://arxiv.org/pdf/1808.06068v1.pdf | |
PWC | https://paperswithcode.com/paper/seven-augmenting-word-embeddings-with |
Repo | |
Framework | |