PyTorchKR Papers

최신 논문

총 3,383편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1806.09776

Cross-position Activity Recognition with Stratified Transfer Learning

Human activity recognition aims to recognize the activities of daily living by utilizing the sensors on different body parts. However, when the labeled data from a certain body position (i.e. target domain) is missing, how to leverage the data from other positions (i.e. source domain) to help learn the activity labels of this position? When there are several source domains available, it is often difficult to select the most similar source domain to the target domain. With the selected source domain, we need to perform accurate knowledge transfer between domains. Existing methods only learn the global distance between domains while ignoring the local property. In this paper, we propose a \textit{Stratified Transfer Learning} (STL) framework to perform both source domain selection and knowledge transfer. STL is based on our proposed \textit{Stratified} distance to capture the local property of domains. STL consists of two components: Stratified Domain Selection (STL-SDS) can select the most similar source domain to the target domain; Stratified Activity Transfer (STL-SAT) is able to perform accurate knowledge transfer. Extensive experiments on three public activity recognition datasets demonstrate the superiority of STL. Furthermore, we extensively investigate the performance of transfer learning across different degrees of similarities and activity levels between domains. We also discuss the potential applications of STL in other fields of pervasive computing for future research.

arXiv:1806.07844

Hide and Seek tracker: Real-time recovery from target loss

In this paper, we examine the real-time recovery of a video tracker from a target loss, using information that is already available from the original tracker and without a significant computational overhead. More specifically, before using the tracker output to update the target position we estimate the detection confidence. In the case of a low confidence, the position update is rejected and the tracker passes to a single-frame failure mode, during which the patch low-level visual content is used to swiftly update the object position, before recovering from the target loss in the next frame. Orthogonally to this improvement, we further enhance the running average method used for creating the query model in tracking-through-similarity. The experimental evidence provided by evaluation on standard tracking datasets (OTB-50, OTB-100 and OTB-2013) validate that target recovery can be successfully achieved without compromising the real-time update of the target position.

arXiv:1304.1098

Occupancy Grids: A Stochastic Spatial Representation for Active Robot Perception

In this paper we provide an overview of a new framework for robot perception, real-world modelling, and navigation that uses a stochastic tesselated representation of spatial information called the Occupancy Grid. The Occupancy Grid is a multi-dimensional random field model that maintains probabilistic estimates of the occupancy state of each cell in a spatial lattice. Bayesian estimation mechanisms employing stochastic sensor models allow incremental updating of the Occupancy Grid using multi-view, multi-sensor data, composition of multiple maps, decision-making, and incorporation of robot and sensor position uncertainty. We present the underlying stochastic formulation of the Occupancy Grid framework, and discuss its application to a variety of robotic tusks. These include range-based mapping, multi-sensor integration, path-planning and obstacle avoidance, handling of robot position uncertainty, incorporation of pre-compiled maps, recovery of geometric representations, and other related problems. The experimental results show that the Occupancy Grid approach generates dense world models, is robust under sensor uncertainty and errors, and allows explicit handling of uncertainty. It supports the development of robust and agile sensor interpretation methods, incremental discovery procedures, and composition of information from multiple sources. Furthermore, the results illustrate that robotic tasks can be addressed through operations performed di- rectly on the Occupancy Grid, and that these operations have strong parallels to operations performed in the image processing domain.

arXiv:1205.5920

On latent position inference from doubly stochastic messaging activities

We model messaging activities as a hierarchical doubly stochastic point process with three main levels, and develop an iterative algorithm for inferring actors' relative latent positions from a stream of messaging activity data. Each of the message-exchanging actors is modeled as a process in a latent space. The actors' latent positions are assumed to be influenced by the distribution of a much larger population over the latent space. Each actor's movement in the latent space is modeled as being governed by two parameters that we call confidence and visibility, in addition to dependence on the population distribution. The messaging frequency between a pair of actors is assumed to be inversely proportional to the distance between their latent positions. Our inference algorithm is based on a projection approach to an online filtering problem. The algorithm associates each actor with a probability density-valued process, and each probability density is assumed to be a mixture of basis functions. For efficient numerical experiments, we further develop our algorithm for the case where the basis functions are obtained by translating and scaling a standard Gaussian density.

arXiv:1304.7399

Bingham Procrustean Alignment for Object Detection in Clutter

A new system for object detection in cluttered RGB-D images is presented. Our main contribution is a new method called Bingham Procrustean Alignment (BPA) to align models with the scene. BPA uses point correspondences between oriented features to derive a probability distribution over possible model poses. The orientation component of this distribution, conditioned on the position, is shown to be a Bingham distribution. This result also applies to the classic problem of least-squares alignment of point sets, when point features are orientation-less, and gives a principled, probabilistic way to measure pose uncertainty in the rigid alignment problem. Our detection system leverages BPA to achieve more reliable object detections in clutter.

arXiv:1305.2830

Performance Enhancement of Distributed Quasi Steady-State Genetic Algorithm

This paper proposes a new scheme for performance enhancement of distributed genetic algorithm (DGA). Initial population is divided in two classes i.e. female and male. Simple distance based clustering is used for cluster formation around females. For reclustering self-adaptive K-means is used, which produces well distributed and well separated clusters. The self-adaptive K-means used for reclustering automatically locates initial position of centroids and number of clusters. Four plans of co-evolution are applied on these clusters independently. Clusters evolve separately. Merging of clusters takes place depending on their performance. For experimentation unimodal and multimodal test functions have been used. Test result show that the new scheme of distribution of population has given better performance.

arXiv:1305.4893

Out-of-sample Extension for Latent Position Graphs

We consider the problem of vertex classification for graphs constructed from the latent position model. It was shown previously that the approach of embedding the graphs into some Euclidean space followed by classification in that space can yields a universally consistent vertex classifier. However, a major technical difficulty of the approach arises when classifying unlabeled out-of-sample vertices without including them in the embedding stage. In this paper, we studied the out-of-sample extension for the graph embedding step and its impact on the subsequent inference tasks. We show that, under the latent position graph model and for sufficiently large $n$, the mapping of the out-of-sample vertices is close to its true latent position. We then demonstrate that successful inference for the out-of-sample vertices is possible.

arXiv:1306.3058

Physeter catodon localization by sparse coding

This paper presents a spermwhale' localization architecture using jointly a bag-of-features (BoF) approach and machine learning framework. BoF methods are known, especially in computer vision, to produce from a collection of local features a global representation invariant to principal signal transformations. Our idea is to regress supervisely from these local features two rough estimates of the distance and azimuth thanks to some datasets where both acoustic events and ground-truth position are now available. Furthermore, these estimates can feed a particle filter system in order to obtain a precise spermwhale' position even in mono-hydrophone configuration. Anti-collision system and whale watching are considered applications of this work.

arXiv:1306.5308

Cognitive Interpretation of Everyday Activities: Toward Perceptual Narrative Based Visuo-Spatial Scene Interpretation

We position a narrative-centred computational model for high-level knowledge representation and reasoning in the context of a range of assistive technologies concerned with "visuo-spatial perception and cognition" tasks. Our proposed narrative model encompasses aspects such as \emph{space, events, actions, change, and interaction} from the viewpoint of commonsense reasoning and learning in large-scale cognitive systems. The broad focus of this paper is on the domain of "human-activity interpretation" in smart environments, ambient intelligence etc. In the backdrop of a "smart meeting cinematography" domain, we position the proposed narrative model, preliminary work on perceptual narrativisation, and the immediate outlook on constructing general-purpose open-source tools for perceptual narrativisation. ACM Classification: I.2 Artificial Intelligence: I.2.0 General -- Cognitive Simulation, I.2.4 Knowledge Representation Formalisms and Methods, I.2.10 Vision and Scene Understanding: Architecture and control structures, Motion, Perceptual reasoning, Shape, Video analysis General keywords: cognitive systems; human-computer interaction; spatial cognition and computation; commonsense reasoning; spatial and temporal reasoning; assistive technologies

arXiv:1301.3611

Jitter-Adaptive Dictionary Learning - Application to Multi-Trial Neuroelectric Signals

Dictionary Learning has proven to be a powerful tool for many image processing tasks, where atoms are typically defined on small image patches. As a drawback, the dictionary only encodes basic structures. In addition, this approach treats patches of different locations in one single set, which means a loss of information when features are well-aligned across signals. This is the case, for instance, in multi-trial magneto- or electroencephalography (M/EEG). Learning the dictionary on the entire signals could make use of the alignement and reveal higher-level features. In this case, however, small missalignements or phase variations of features would not be compensated for. In this paper, we propose an extension to the common dictionary learning framework to overcome these limitations by allowing atoms to adapt their position across signals. The method is validated on simulated and real neuroelectric data.

arXiv:1307.1388

Introducing Memory and Association Mechanism into a Biologically Inspired Visual Model

A famous biologically inspired hierarchical model firstly proposed by Riesenhuber and Poggio has been successfully applied to multiple visual recognition tasks. The model is able to achieve a set of position- and scale-tolerant recognition, which is a central problem in pattern recognition. In this paper, based on some other biological experimental results, we introduce the Memory and Association Mechanisms into the above biologically inspired model. The main motivations of the work are (a) to mimic the active memory and association mechanism and add the 'top down' adjustment to the above biologically inspired hierarchical model and (b) to build up an algorithm which can save the space and keep a good recognition performance. The new model is also applied to object recognition processes. The primary experimental results show that our method is efficient with much less memory requirement.

arXiv:1308.0701

Ontology Enrichment by Extracting Hidden Assertional Knowledge from Text

In this position paper we present a new approach for discovering some special classes of assertional knowledge in the text by using large RDF repositories, resulting in the extraction of new non-taxonomic ontological relations. Also we use inductive reasoning beside our approach to make it outperform. Then, we prepare a case study by applying our approach on sample data and illustrate the soundness of our proposed approach. Moreover in our point of view current LOD cloud is not a suitable base for our proposal in all informational domains. Therefore we figure out some directions based on prior works to enrich datasets of Linked Data by using web mining. The result of such enrichment can be reused for further relation extraction and ontology enrichment from unstructured free text documents.

arXiv:1212.1182

Universally consistent vertex classification for latent positions graphs

In this work we show that, using the eigen-decomposition of the adjacency matrix, we can consistently estimate feature maps for latent position graphs with positive definite link function $\kappa$, provided that the latent positions are i.i.d. from some distribution F. We then consider the exploitation task of vertex classification where the link function $\kappa$ belongs to the class of universal kernels and class labels are observed for a number of vertices tending to infinity and that the remaining vertices are to be classified. We show that minimization of the empirical $\varphi$-risk for some convex surrogate $\varphi$ of 0-1 loss over a class of linear classifiers with increasing complexities yields a universally consistent classifier, that is, a classification rule with error converging to Bayes optimal for any distribution F.

arXiv:1311.1939

Fast Tracking via Spatio-Temporal Context Learning

In this paper, we present a simple yet fast and robust algorithm which exploits the spatio-temporal context for visual tracking. Our approach formulates the spatio-temporal relationships between the object of interest and its local context based on a Bayesian framework, which models the statistical correlation between the low-level features (i.e., image intensity and position) from the target and its surrounding regions. The tracking problem is posed by computing a confidence map, and obtaining the best target location by maximizing an object location likelihood function. The Fast Fourier Transform is adopted for fast learning and detection in this work. Implemented in MATLAB without code optimization, the proposed tracker runs at 350 frames per second on an i7 machine. Extensive experimental results show that the proposed algorithm performs favorably against state-of-the-art methods in terms of efficiency, accuracy and robustness.

arXiv:1311.7656

Statistical estimation for optimization problems on graphs

Large graphs abound in machine learning, data mining, and several related areas. A useful step towards analyzing such graphs is that of obtaining certain summary statistics - e.g., or the expected length of a shortest path between two nodes, or the expected weight of a minimum spanning tree of the graph, etc. These statistics provide insight into the structure of a graph, and they can help predict global properties of a graph. Motivated thus, we propose to study statistical properties of structured subgraphs (of a given graph), in particular, to estimate the expected objective function value of a combinatorial optimization problem over these subgraphs. The general task is very difficult, if not unsolvable; so for concreteness we describe a more specific statistical estimation problem based on spanning trees. We hope that our position paper encourages others to also study other types of graphical structures for which one can prove nontrivial statistical estimates.

arXiv:1107.0845

Automatic Road Lighting System (ARLS) Model Based on Image Processing of Moving Object

Using a vehicle toy (in next future called vehicle) as a moving object an automatic road lighting system (ARLS) model is constructed. A digital video camera with 25 fps is used to capture the vehicle motion as it moves in the test segment of the road. Captured images are then processed to calculate vehicle speed. This information of the speed together with position of vehicle is then used to control the lighting system along the path that passes by the vehicle. Length of the road test segment is 1 m, the video camera is positioned about 1.1 m above the test segment, and the vehicle toy dimension is 13 cm \times 9.3 cm. In this model, the maximum speed that ARLS can handle is about 1.32 m/s, and the highest performance is obtained about 91% at speed 0.93 m/s.

arXiv:1312.6834

Face Detection from still and Video Images using Unsupervised Cellular Automata with K means clustering algorithm

Pattern recognition problem rely upon the features inherent in the pattern of images. Face detection and recognition is one of the challenging research areas in the field of computer vision. In this paper, we present a method to identify skin pixels from still and video images using skin color. Face regions are identified from this skin pixel region. Facial features such as eyes, nose and mouth are then located. Faces are recognized from color images using an RBF based neural network. Unsupervised Cellular Automata with K means clustering algorithm is used to locate different facial elements. Orientation is corrected by using eyes. Parameters like inter eye distance, nose length, mouth position, Discrete Cosine Transform (DCT) coefficients etc. are computed and used for a Radial Basis Function (RBF) based neural network. This approach reliably works for face sequence with orientation in head, expressions etc.

arXiv:1312.4346

Teleoperation System Using Past Image Records Considering Narrow Communication Band

Teleoperation is necessary when the robot is applied to real missions, for example surveillance, search and rescue. We proposed teleoperation system using past image records (SPIR). SPIR virtually generates the bird's-eye view image by overlaying the CG model of the robot at the corresponding current position on the background image which is captured from the camera mounted on the robot at a past time. The problem for SPIR is that the communication bandwidth is often narrow in some teleoperation tasks. In this case, the candidates of background image of SPIR are few and the position of the robot is often delayed. In this study, we propose zoom function for insufficiency of candidates of the background image and additional interpolation lines for the delay of the position data of the robot. To evaluate proposed system, an outdoor experiments are carried out. The outdoor experiment is conducted on a training course of a driving school.

arXiv:1312.1752

Particle Swarm Optimization of Information-Content Weighting of Symbolic Aggregate Approximation

Bio-inspired optimization algorithms have been gaining more popularity recently. One of the most important of these algorithms is particle swarm optimization (PSO). PSO is based on the collective intelligence of a swam of particles. Each particle explores a part of the search space looking for the optimal position and adjusts its position according to two factors; the first is its own experience and the second is the collective experience of the whole swarm. PSO has been successfully used to solve many optimization problems. In this work we use PSO to improve the performance of a well-known representation method of time series data which is the symbolic aggregate approximation (SAX). As with other time series representation methods, SAX results in loss of information when applied to represent time series. In this paper we use PSO to propose a new minimum distance WMD for SAX to remedy this problem. Unlike the original minimum distance, the new distance sets different weights to different segments of the time series according to their information content. This weighted minimum distance enhances the performance of SAX as we show through experiments using different time series datasets.

arXiv:1401.4599

Learning and Reasoning with Action-Related Places for Robust Mobile Manipulation

We propose the concept of Action-Related Place (ARPlace) as a powerful and flexible representation of task-related place in the context of mobile manipulation. ARPlace represents robot base locations not as a single position, but rather as a collection of positions, each with an associated probability that the manipulation action will succeed when located there. ARPlaces are generated using a predictive model that is acquired through experience-based learning, and take into account the uncertainty the robot has about its own location and the location of the object to be manipulated. When executing the task, rather than choosing one specific goal position based only on the initial knowledge about the task context, the robot instantiates an ARPlace, and bases its decisions on this ARPlace, which is updated as new information about the task becomes available. To show the advantages of this least-commitment approach, we present a transformational planner that reasons about ARPlaces in order to optimize symbolic plans. Our empirical evaluation demonstrates that using ARPlaces leads to more robust and efficient mobile manipulation in the face of state estimation uncertainty on our simulated robot.