Paper Group ANR 76
Visual Tracking via Shallow and Deep Collaborative Model. Exercise Motion Classification from Large-Scale Wearable Sensor Data Using Convolutional Neural Networks. Probabilistic Neural Programs. Petrarch 2 : Petrarcher. Human Computer Interaction Using Marker Based Hand Gesture Recognition. GAdaBoost: Accelerating Adaboost Feature Selection with Ge …
Visual Tracking via Shallow and Deep Collaborative Model
| Title | Visual Tracking via Shallow and Deep Collaborative Model |
| Authors | Bohan Zhuang, Lijun Wang, Huchuan Lu |
| Abstract | In this paper, we propose a robust tracking method based on the collaboration of a generative model and a discriminative classifier, where features are learned by shallow and deep architectures, respectively. For the generative model, we introduce a block-based incremental learning scheme, in which a local binary mask is constructed to deal with occlusion. The similarity degrees between the local patches and their corresponding subspace are integrated to formulate a more accurate global appearance model. In the discriminative model, we exploit the advances of deep learning architectures to learn generic features which are robust to both background clutters and foreground appearance variations. To this end, we first construct a discriminative training set from auxiliary video sequences. A deep classification neural network is then trained offline on this training set. Through online fine-tuning, both the hierarchical feature extractor and the classifier can be adapted to the appearance change of the target for effective online tracking. The collaboration of these two models achieves a good balance in handling occlusion and target appearance change, which are two contradictory challenging factors in visual tracking. Both quantitative and qualitative evaluations against several state-of-the-art algorithms on challenging image sequences demonstrate the accuracy and the robustness of the proposed tracker. |
| Tasks | Visual Tracking |
| Published | 2016-07-27 |
| URL | http://arxiv.org/abs/1607.08040v1 |
| http://arxiv.org/pdf/1607.08040v1.pdf | |
| PWC | https://paperswithcode.com/paper/visual-tracking-via-shallow-and-deep |
| Repo | |
| Framework | |
Exercise Motion Classification from Large-Scale Wearable Sensor Data Using Convolutional Neural Networks
| Title | Exercise Motion Classification from Large-Scale Wearable Sensor Data Using Convolutional Neural Networks |
| Authors | Terry Taewoong Um, Vahid Babakeshizadeh, Dana Kulić |
| Abstract | The ability to accurately identify human activities is essential for developing automatic rehabilitation and sports training systems. In this paper, large-scale exercise motion data obtained from a forearm-worn wearable sensor are classified with a convolutional neural network (CNN). Time-series data consisting of accelerometer and orientation measurements are formatted as images, allowing the CNN to automatically extract discriminative features. A comparative study on the effects of image formatting and different CNN architectures is also presented. The best performing configuration classifies 50 gym exercises with 92.1% accuracy. |
| Tasks | Time Series |
| Published | 2016-10-22 |
| URL | http://arxiv.org/abs/1610.07031v3 |
| http://arxiv.org/pdf/1610.07031v3.pdf | |
| PWC | https://paperswithcode.com/paper/exercise-motion-classification-from-large |
| Repo | |
| Framework | |
Probabilistic Neural Programs
| Title | Probabilistic Neural Programs |
| Authors | Kenton W. Murray, Jayant Krishnamurthy |
| Abstract | We present probabilistic neural programs, a framework for program induction that permits flexible specification of both a computational model and inference algorithm while simultaneously enabling the use of deep neural networks. Probabilistic neural programs combine a computation graph for specifying a neural network with an operator for weighted nondeterministic choice. Thus, a program describes both a collection of decisions as well as the neural network architecture used to make each one. We evaluate our approach on a challenging diagram question answering task where probabilistic neural programs correctly execute nearly twice as many programs as a baseline model. |
| Tasks | Question Answering |
| Published | 2016-12-02 |
| URL | http://arxiv.org/abs/1612.00712v1 |
| http://arxiv.org/pdf/1612.00712v1.pdf | |
| PWC | https://paperswithcode.com/paper/probabilistic-neural-programs |
| Repo | |
| Framework | |
Petrarch 2 : Petrarcher
| Title | Petrarch 2 : Petrarcher |
| Authors | Clayton Norris |
| Abstract | PETRARCH 2 is the fourth generation of a series of Event-Data coders stemming from research by Phillip Schrodt. Each iteration has brought new functionality and usability, and this is no exception.Petrarch 2 takes much of the power of the original Petrarch’s dictionaries and redirects it into a faster and smarter core logic. Earlier iterations handled sentences largely as a list of words, incorporating some syntactic information here and there. Petrarch 2 now views the sentence entirely on the syntactic level. It receives the syntactic parse of a sentence from the Stanford CoreNLP software, and stores this data as a tree structure of linked nodes, where each node is a Phrase object. Prepositional, noun, and verb phrases each have their own version of this Phrase class, which deals with the logic particular to those kinds of phrases. Since this is an event coder, the core of the logic focuses around the verbs: who is acting, who is being acted on, and what is happening. The theory behind this new structure and its logic is founded in Generative Grammar, Information Theory, and Lambda-Calculus Semantics. |
| Tasks | |
| Published | 2016-02-23 |
| URL | http://arxiv.org/abs/1602.07236v1 |
| http://arxiv.org/pdf/1602.07236v1.pdf | |
| PWC | https://paperswithcode.com/paper/petrarch-2-petrarcher |
| Repo | |
| Framework | |
Human Computer Interaction Using Marker Based Hand Gesture Recognition
| Title | Human Computer Interaction Using Marker Based Hand Gesture Recognition |
| Authors | Sayem Mohammad Siam, Jahidul Adnan Sakel, Md. Hasanul Kabir |
| Abstract | Human Computer Interaction (HCI) has been redefined in this era. People want to interact with their devices in such a way that has physical significance in the real world, in other words, they want ergonomic input devices. In this paper, we propose a new method of interaction with computing devices having a consumer grade camera, that uses two colored markers (red and green) worn on tips of the fingers to generate desired hand gestures, and for marker detection and tracking we used template matching with kalman filter. We have implemented all the usual system commands, i.e., cursor movement, right click, left click, double click, going forward and backward, zoom in and out through different hand gestures. Our system can easily recognize these gestures and give corresponding system commands. Our system is suitable for both desktop devices and devices where touch screen is not feasible like large screens or projected screens. |
| Tasks | Gesture Recognition, Hand Gesture Recognition, Hand-Gesture Recognition |
| Published | 2016-06-23 |
| URL | http://arxiv.org/abs/1606.07247v1 |
| http://arxiv.org/pdf/1606.07247v1.pdf | |
| PWC | https://paperswithcode.com/paper/human-computer-interaction-using-marker-based |
| Repo | |
| Framework | |
GAdaBoost: Accelerating Adaboost Feature Selection with Genetic Algorithms
| Title | GAdaBoost: Accelerating Adaboost Feature Selection with Genetic Algorithms |
| Authors | Mai Tolba, Mohamed Moustafa |
| Abstract | Boosted cascade of simple features, by Viola and Jones, is one of the most famous object detection frameworks. However, it suffers from a lengthy training process. This is due to the vast features space and the exhaustive search nature of Adaboost. In this paper we propose GAdaboost: a Genetic Algorithm to accelerate the training procedure through natural feature selection. Specifically, we propose to limit Adaboost search within a subset of the huge feature space, while evolving this subset following a Genetic Algorithm. Experiments demonstrate that our proposed GAdaboost is up to 3.7 times faster than Adaboost. We also demonstrate that the price of this speedup is a mere decrease (3%, 4%) in detection accuracy when tested on FDDB benchmark face detection set, and Caltech Web Faces respectively. |
| Tasks | Face Detection, Feature Selection, Object Detection |
| Published | 2016-09-20 |
| URL | http://arxiv.org/abs/1609.06260v1 |
| http://arxiv.org/pdf/1609.06260v1.pdf | |
| PWC | https://paperswithcode.com/paper/gadaboost-accelerating-adaboost-feature |
| Repo | |
| Framework | |
Contextual LSTM (CLSTM) models for Large scale NLP tasks
| Title | Contextual LSTM (CLSTM) models for Large scale NLP tasks |
| Authors | Shalini Ghosh, Oriol Vinyals, Brian Strope, Scott Roy, Tom Dean, Larry Heck |
| Abstract | Documents exhibit sequential structure at multiple levels of abstraction (e.g., sentences, paragraphs, sections). These abstractions constitute a natural hierarchy for representing the context in which to infer the meaning of words and larger fragments of text. In this paper, we present CLSTM (Contextual LSTM), an extension of the recurrent neural network LSTM (Long-Short Term Memory) model, where we incorporate contextual features (e.g., topics) into the model. We evaluate CLSTM on three specific NLP tasks: word prediction, next sentence selection, and sentence topic prediction. Results from experiments run on two corpora, English documents in Wikipedia and a subset of articles from a recent snapshot of English Google News, indicate that using both words and topics as features improves performance of the CLSTM models over baseline LSTM models for these tasks. For example on the next sentence selection task, we get relative accuracy improvements of 21% for the Wikipedia dataset and 18% for the Google News dataset. This clearly demonstrates the significant benefit of using context appropriately in natural language (NL) tasks. This has implications for a wide variety of NL applications like question answering, sentence completion, paraphrase generation, and next utterance prediction in dialog systems. |
| Tasks | Paraphrase Generation, Question Answering |
| Published | 2016-02-19 |
| URL | http://arxiv.org/abs/1602.06291v2 |
| http://arxiv.org/pdf/1602.06291v2.pdf | |
| PWC | https://paperswithcode.com/paper/contextual-lstm-clstm-models-for-large-scale |
| Repo | |
| Framework | |
Fuzzy-based Propagation of Prior Knowledge to Improve Large-Scale Image Analysis Pipelines
| Title | Fuzzy-based Propagation of Prior Knowledge to Improve Large-Scale Image Analysis Pipelines |
| Authors | Johannes Stegmaier, Ralf Mikut |
| Abstract | Many automatically analyzable scientific questions are well-posed and offer a variety of information about the expected outcome a priori. Although often being neglected, this prior knowledge can be systematically exploited to make automated analysis operations sensitive to a desired phenomenon or to evaluate extracted content with respect to this prior knowledge. For instance, the performance of processing operators can be greatly enhanced by a more focused detection strategy and the direct information about the ambiguity inherent in the extracted data. We present a new concept for the estimation and propagation of uncertainty involved in image analysis operators. This allows using simple processing operators that are suitable for analyzing large-scale 3D+t microscopy images without compromising the result quality. On the foundation of fuzzy set theory, we transform available prior knowledge into a mathematical representation and extensively use it enhance the result quality of various processing operators. All presented concepts are illustrated on a typical bioimage analysis pipeline comprised of seed point detection, segmentation, multiview fusion and tracking. Furthermore, the functionality of the proposed approach is validated on a comprehensive simulated 3D+t benchmark data set that mimics embryonic development and on large-scale light-sheet microscopy data of a zebrafish embryo. The general concept introduced in this contribution represents a new approach to efficiently exploit prior knowledge to improve the result quality of image analysis pipelines. Especially, the automated analysis of terabyte-scale microscopy data will benefit from sophisticated and efficient algorithms that enable a quantitative and fast readout. The generality of the concept, however, makes it also applicable to practically any other field with processing strategies that are arranged as linear pipelines. |
| Tasks | |
| Published | 2016-08-03 |
| URL | http://arxiv.org/abs/1608.01276v1 |
| http://arxiv.org/pdf/1608.01276v1.pdf | |
| PWC | https://paperswithcode.com/paper/fuzzy-based-propagation-of-prior-knowledge-to |
| Repo | |
| Framework | |
Incorporating Language Level Information into Acoustic Models
| Title | Incorporating Language Level Information into Acoustic Models |
| Authors | Peidong Wang, Deliang Wang |
| Abstract | This paper proposed a class of novel Deep Recurrent Neural Networks which can incorporate language-level information into acoustic models. For simplicity, we named these networks Recurrent Deep Language Networks (RDLNs). Multiple variants of RDLNs were considered, including two kinds of context information, two methods to process the context, and two methods to incorporate the language-level information. RDLNs provided possible methods to fine-tune the whole Automatic Speech Recognition (ASR) system in the acoustic modeling process. |
| Tasks | Speech Recognition |
| Published | 2016-12-14 |
| URL | http://arxiv.org/abs/1612.04744v1 |
| http://arxiv.org/pdf/1612.04744v1.pdf | |
| PWC | https://paperswithcode.com/paper/incorporating-language-level-information-into |
| Repo | |
| Framework | |
Towards Lifelong Self-Supervision: A Deep Learning Direction for Robotics
| Title | Towards Lifelong Self-Supervision: A Deep Learning Direction for Robotics |
| Authors | Jay M. Wong |
| Abstract | Despite outstanding success in vision amongst other domains, many of the recent deep learning approaches have evident drawbacks for robots. This manuscript surveys recent work in the literature that pertain to applying deep learning systems to the robotics domain, either as means of estimation or as a tool to resolve motor commands directly from raw percepts. These recent advances are only a piece to the puzzle. We suggest that deep learning as a tool alone is insufficient in building a unified framework to acquire general intelligence. For this reason, we complement our survey with insights from cognitive development and refer to ideas from classical control theory, producing an integrated direction for a lifelong learning architecture. |
| Tasks | |
| Published | 2016-11-01 |
| URL | http://arxiv.org/abs/1611.00201v1 |
| http://arxiv.org/pdf/1611.00201v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-lifelong-self-supervision-a-deep |
| Repo | |
| Framework | |
Improving Quality of Hierarchical Clustering for Large Data Series
| Title | Improving Quality of Hierarchical Clustering for Large Data Series |
| Authors | Manuel R. Ciosici |
| Abstract | Brown clustering is a hard, hierarchical, bottom-up clustering of words in a vocabulary. Words are assigned to clusters based on their usage pattern in a given corpus. The resulting clusters and hierarchical structure can be used in constructing class-based language models and for generating features to be used in NLP tasks. Because of its high computational cost, the most-used version of Brown clustering is a greedy algorithm that uses a window to restrict its search space. Like other clustering algorithms, Brown clustering finds a sub-optimal, but nonetheless effective, mapping of words to clusters. Because of its ability to produce high-quality, human-understandable cluster, Brown clustering has seen high uptake the NLP research community where it is used in the preprocessing and feature generation steps. Little research has been done towards improving the quality of Brown clusters, despite the greedy and heuristic nature of the algorithm. The approaches tried so far have focused on: studying the effect of the initialisation in a similar algorithm; tuning the parameters used to define the desired number of clusters and the behaviour of the algorithm; and including a separate parameter to differentiate the window from the desired number of clusters. However, some of these approaches have not yielded significant improvements in cluster quality. In this thesis, a close analysis of the Brown algorithm is provided, revealing important under-specifications and weaknesses in the original algorithm. These have serious effects on cluster quality and reproducibility of research using Brown clustering. In the second part of the thesis, two modifications are proposed. Finally, a thorough evaluation is performed, considering both the optimization criterion of Brown clustering and the performance of the resulting class-based language models. |
| Tasks | |
| Published | 2016-08-03 |
| URL | http://arxiv.org/abs/1608.01238v1 |
| http://arxiv.org/pdf/1608.01238v1.pdf | |
| PWC | https://paperswithcode.com/paper/improving-quality-of-hierarchical-clustering |
| Repo | |
| Framework | |
Embedded all relevant feature selection with Random Ferns
| Title | Embedded all relevant feature selection with Random Ferns |
| Authors | Miron Bartosz Kursa |
| Abstract | Many machine learning methods can produce variable importance scores expressing the usability of each feature in context of the produced model; those scores on their own are yet not sufficient to generate feature selection, especially when an all relevant selection is required. Although there are wrapper methods aiming to solve this problem, they introduce a substantial increase in the required computational effort. In this paper I investigate an idea of incorporating all relevant selection within the training process by producing importance for implicitly generated shadows, attributes irrelevant by design. I propose and evaluate such a method in context of random ferns classifier. Experiment results confirm the effectiveness of such approach, although show that fully stochastic nature of random ferns limits its applicability either to small dimensions or as a part of a broader feature selection procedure. |
| Tasks | Feature Selection |
| Published | 2016-04-20 |
| URL | http://arxiv.org/abs/1604.06133v1 |
| http://arxiv.org/pdf/1604.06133v1.pdf | |
| PWC | https://paperswithcode.com/paper/embedded-all-relevant-feature-selection-with |
| Repo | |
| Framework | |
Dynamic Metric Learning from Pairwise Comparisons
| Title | Dynamic Metric Learning from Pairwise Comparisons |
| Authors | Kristjan Greenewald, Stephen Kelley, Alfred Hero III |
| Abstract | Recent work in distance metric learning has focused on learning transformations of data that best align with specified pairwise similarity and dissimilarity constraints, often supplied by a human observer. The learned transformations lead to improved retrieval, classification, and clustering algorithms due to the better adapted distance or similarity measures. Here, we address the problem of learning these transformations when the underlying constraint generation process is nonstationary. This nonstationarity can be due to changes in either the ground-truth clustering used to generate constraints or changes in the feature subspaces in which the class structure is apparent. We propose Online Convex Ensemble StrongLy Adaptive Dynamic Learning (OCELAD), a general adaptive, online approach for learning and tracking optimal metrics as they change over time that is highly robust to a variety of nonstationary behaviors in the changing metric. We apply the OCELAD framework to an ensemble of online learners. Specifically, we create a retro-initialized composite objective mirror descent (COMID) ensemble (RICE) consisting of a set of parallel COMID learners with different learning rates, demonstrate RICE-OCELAD on both real and synthetic data sets and show significant performance improvements relative to previously proposed batch and online distance metric learning algorithms. |
| Tasks | Metric Learning |
| Published | 2016-10-10 |
| URL | http://arxiv.org/abs/1610.03090v1 |
| http://arxiv.org/pdf/1610.03090v1.pdf | |
| PWC | https://paperswithcode.com/paper/dynamic-metric-learning-from-pairwise |
| Repo | |
| Framework | |
A Study of Lagrangean Decompositions and Dual Ascent Solvers for Graph Matching
| Title | A Study of Lagrangean Decompositions and Dual Ascent Solvers for Graph Matching |
| Authors | Paul Swoboda, Carsten Rother, Hassan Abu Alhaija, Dagmar Kainmueller, Bogdan Savchynskyy |
| Abstract | We study the quadratic assignment problem, in computer vision also known as graph matching. Two leading solvers for this problem optimize the Lagrange decomposition duals with sub-gradient and dual ascent (also known as message passing) updates. We explore s direction further and propose several additional Lagrangean relaxations of the graph matching problem along with corresponding algorithms, which are all based on a common dual ascent framework. Our extensive empirical evaluation gives several theoretical insights and suggests a new state-of-the-art any-time solver for the considered problem. Our improvement over state-of-the-art is particularly visible on a new dataset with large-scale sparse problem instances containing more than 500 graph nodes each. |
| Tasks | Graph Matching |
| Published | 2016-12-16 |
| URL | http://arxiv.org/abs/1612.05476v2 |
| http://arxiv.org/pdf/1612.05476v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-study-of-lagrangean-decompositions-and-dual |
| Repo | |
| Framework | |
Image Retrieval with Fisher Vectors of Binary Features
| Title | Image Retrieval with Fisher Vectors of Binary Features |
| Authors | Yusuke Uchida, Shigeyuki Sakazawa, Shin’ichi Satoh |
| Abstract | Recently, the Fisher vector representation of local features has attracted much attention because of its effectiveness in both image classification and image retrieval. Another trend in the area of image retrieval is the use of binary features such as ORB, FREAK, and BRISK. Considering the significant performance improvement for accuracy in both image classification and retrieval by the Fisher vector of continuous feature descriptors, if the Fisher vector were also to be applied to binary features, we would receive similar benefits in binary feature based image retrieval and classification. In this paper, we derive the closed-form approximation of the Fisher vector of binary features modeled by the Bernoulli mixture model. We also propose accelerating the Fisher vector by using the approximate value of posterior probability. Experiments show that the Fisher vector representation significantly improves the accuracy of image retrieval compared with a bag of binary words approach. |
| Tasks | Image Classification, Image Retrieval |
| Published | 2016-09-27 |
| URL | http://arxiv.org/abs/1609.08291v1 |
| http://arxiv.org/pdf/1609.08291v1.pdf | |
| PWC | https://paperswithcode.com/paper/image-retrieval-with-fisher-vectors-of-binary |
| Repo | |
| Framework | |
