Paper Group ANR 309
Sparse vs. Non-sparse: Which One Is Better for Practical Visual Tracking?. Decoding visual stimuli in human brain by using Anatomical Pattern Analysis on fMRI images. A Noise-Filtering Approach for Cancer Drug Sensitivity Prediction. A Semi-supervised Framework for Image Captioning. Identifiability and Transportability in Dynamic Causal Networks. O …
Sparse vs. Non-sparse: Which One Is Better for Practical Visual Tracking?
| Title | Sparse vs. Non-sparse: Which One Is Better for Practical Visual Tracking? |
| Authors | Yashar Deldjoo, Shengping Zhang, Bahman Zanj, Paolo Cremonesi, Matteo Matteucci |
| Abstract | Recently, sparse representation based visual tracking methods have attracted increasing attention in the computer vision community. Although achieve superior performance to traditional tracking methods, however, a basic problem has not been answered yet — that whether the sparsity constrain is really needed for visual tracking? To answer this question, in this paper, we first propose a robust non-sparse representation based tracker and then conduct extensive experiments to compare it against several state-of-the-art sparse representation based trackers. Our experiment results and analysis indicate that the proposed non-sparse tracker achieved competitive tracking accuracy with sparse trackers while having faster running speed, which support our non-sparse tracker to be used in practical applications. |
| Tasks | Visual Tracking |
| Published | 2016-07-30 |
| URL | http://arxiv.org/abs/1608.00168v1 |
| http://arxiv.org/pdf/1608.00168v1.pdf | |
| PWC | https://paperswithcode.com/paper/sparse-vs-non-sparse-which-one-is-better-for |
| Repo | |
| Framework | |
Decoding visual stimuli in human brain by using Anatomical Pattern Analysis on fMRI images
| Title | Decoding visual stimuli in human brain by using Anatomical Pattern Analysis on fMRI images |
| Authors | Muhammad Yousefnezhad, Daoqiang Zhang |
| Abstract | A universal unanswered question in neuroscience and machine learning is whether computers can decode the patterns of the human brain. Multi-Voxels Pattern Analysis (MVPA) is a critical tool for addressing this question. However, there are two challenges in the previous MVPA methods, which include decreasing sparsity and noises in the extracted features and increasing the performance of prediction. In overcoming mentioned challenges, this paper proposes Anatomical Pattern Analysis (APA) for decoding visual stimuli in the human brain. This framework develops a novel anatomical feature extraction method and a new imbalance AdaBoost algorithm for binary classification. Further, it utilizes an Error-Correcting Output Codes (ECOC) method for multi-class prediction. APA can automatically detect active regions for each category of the visual stimuli. Moreover, it enables us to combine homogeneous datasets for applying advanced classification. Experimental studies on 4 visual categories (words, consonants, objects and scrambled photos) demonstrate that the proposed approach achieves superior performance to state-of-the-art methods. |
| Tasks | |
| Published | 2016-09-04 |
| URL | http://arxiv.org/abs/1609.00921v1 |
| http://arxiv.org/pdf/1609.00921v1.pdf | |
| PWC | https://paperswithcode.com/paper/decoding-visual-stimuli-in-human-brain-by |
| Repo | |
| Framework | |
A Noise-Filtering Approach for Cancer Drug Sensitivity Prediction
| Title | A Noise-Filtering Approach for Cancer Drug Sensitivity Prediction |
| Authors | Turki Turki, Zhi Wei |
| Abstract | Accurately predicting drug responses to cancer is an important problem hindering oncologists’ efforts to find the most effective drugs to treat cancer, which is a core goal in precision medicine. The scientific community has focused on improving this prediction based on genomic, epigenomic, and proteomic datasets measured in human cancer cell lines. Real-world cancer cell lines contain noise, which degrades the performance of machine learning algorithms. This problem is rarely addressed in the existing approaches. In this paper, we present a noise-filtering approach that integrates techniques from numerical linear algebra and information retrieval targeted at filtering out noisy cancer cell lines. By filtering out noisy cancer cell lines, we can train machine learning algorithms on better quality cancer cell lines. We evaluate the performance of our approach and compare it with an existing approach using the Area Under the ROC Curve (AUC) on clinical trial data. The experimental results show that our proposed approach is stable and also yields the highest AUC at a statistically significant level. |
| Tasks | Information Retrieval |
| Published | 2016-12-02 |
| URL | http://arxiv.org/abs/1612.00525v2 |
| http://arxiv.org/pdf/1612.00525v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-noise-filtering-approach-for-cancer-drug |
| Repo | |
| Framework | |
A Semi-supervised Framework for Image Captioning
| Title | A Semi-supervised Framework for Image Captioning |
| Authors | Wenhu Chen, Aurelien Lucchi, Thomas Hofmann |
| Abstract | State-of-the-art approaches for image captioning require supervised training data consisting of captions with paired image data. These methods are typically unable to use unsupervised data such as textual data with no corresponding images, which is a much more abundant commodity. We here propose a novel way of using such textual data by artificially generating missing visual information. We evaluate this learning approach on a newly designed model that detects visual concepts present in an image and feed them to a reviewer-decoder architecture with an attention mechanism. Unlike previous approaches that encode visual concepts using word embeddings, we instead suggest using regional image features which capture more intrinsic information. The main benefit of this architecture is that it synthesizes meaningful thought vectors that capture salient image properties and then applies a soft attentive decoder to decode the thought vectors and generate image captions. We evaluate our model on both Microsoft COCO and Flickr30K datasets and demonstrate that this model combined with our semi-supervised learning method can largely improve performance and help the model to generate more accurate and diverse captions. |
| Tasks | Image Captioning, Word Embeddings |
| Published | 2016-11-16 |
| URL | http://arxiv.org/abs/1611.05321v3 |
| http://arxiv.org/pdf/1611.05321v3.pdf | |
| PWC | https://paperswithcode.com/paper/a-semi-supervised-framework-for-image |
| Repo | |
| Framework | |
Identifiability and Transportability in Dynamic Causal Networks
| Title | Identifiability and Transportability in Dynamic Causal Networks |
| Authors | Gilles Blondel, Marta Arias, Ricard Gavaldà |
| Abstract | In this paper we propose a causal analog to the purely observational Dynamic Bayesian Networks, which we call Dynamic Causal Networks. We provide a sound and complete algorithm for identification of Dynamic Causal Net- works, namely, for computing the effect of an intervention or experiment, based on passive observations only, whenever possible. We note the existence of two types of confounder variables that affect in substantially different ways the iden- tification procedures, a distinction with no analog in either Dynamic Bayesian Networks or standard causal graphs. We further propose a procedure for the transportability of causal effects in Dynamic Causal Network settings, where the re- sult of causal experiments in a source domain may be used for the identification of causal effects in a target domain. |
| Tasks | |
| Published | 2016-10-18 |
| URL | http://arxiv.org/abs/1610.05556v1 |
| http://arxiv.org/pdf/1610.05556v1.pdf | |
| PWC | https://paperswithcode.com/paper/identifiability-and-transportability-in |
| Repo | |
| Framework | |
On Study of the Binarized Deep Neural Network for Image Classification
| Title | On Study of the Binarized Deep Neural Network for Image Classification |
| Authors | Song Wang, Dongchun Ren, Li Chen, Wei Fan, Jun Sun, Satoshi Naoi |
| Abstract | Recently, the deep neural network (derived from the artificial neural network) has attracted many researchers’ attention by its outstanding performance. However, since this network requires high-performance GPUs and large storage, it is very hard to use it on individual devices. In order to improve the deep neural network, many trials have been made by refining the network structure or training strategy. Unlike those trials, in this paper, we focused on the basic propagation function of the artificial neural network and proposed the binarized deep neural network. This network is a pure binary system, in which all the values and calculations are binarized. As a result, our network can save a lot of computational resource and storage. Therefore, it is possible to use it on various devices. Moreover, the experimental results proved the feasibility of the proposed network. |
| Tasks | Image Classification |
| Published | 2016-02-24 |
| URL | http://arxiv.org/abs/1602.07373v1 |
| http://arxiv.org/pdf/1602.07373v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-study-of-the-binarized-deep-neural-network |
| Repo | |
| Framework | |
Deploying learning materials to game content for serious education game development: A case study
| Title | Deploying learning materials to game content for serious education game development: A case study |
| Authors | Harits Ar Rosyid, Matt Palmerlee, Ke Chen |
| Abstract | The ultimate goals of serious education games (SEG) are to facilitate learning and maximizing enjoyment during playing SEGs. In SEG development, there are normally two spaces to be taken into account: knowledge space regarding learning materials and content space regarding games to be used to convey learning materials. How to deploy the learning materials seamlessly and effectively into game content becomes one of the most challenging problems in SEG development. Unlike previous work where experts in education have to be used heavily, we proposed a novel approach that works toward minimizing the efforts of education experts in mapping learning materials to content space. For a proof-of-concept, we apply the proposed approach in developing an SEG game, named \emph{Chem Dungeon}, as a case study in order to demonstrate the effectiveness of our proposed approach. This SEG game has been tested with a number of users, and the user survey suggests our method works reasonably well. |
| Tasks | |
| Published | 2016-08-04 |
| URL | http://arxiv.org/abs/1608.01611v1 |
| http://arxiv.org/pdf/1608.01611v1.pdf | |
| PWC | https://paperswithcode.com/paper/deploying-learning-materials-to-game-content |
| Repo | |
| Framework | |
SnapToGrid: From Statistical to Interpretable Models for Biomedical Information Extraction
| Title | SnapToGrid: From Statistical to Interpretable Models for Biomedical Information Extraction |
| Authors | Marco A. Valenzuela-Escarcega, Gus Hahn-Powell, Dane Bell, Mihai Surdeanu |
| Abstract | We propose an approach for biomedical information extraction that marries the advantages of machine learning models, e.g., learning directly from data, with the benefits of rule-based approaches, e.g., interpretability. Our approach starts by training a feature-based statistical model, then converts this model to a rule-based variant by converting its features to rules, and “snapping to grid” the feature weights to discrete votes. In doing so, our proposal takes advantage of the large body of work in machine learning, but it produces an interpretable model, which can be directly edited by experts. We evaluate our approach on the BioNLP 2009 event extraction task. Our results show that there is a small performance penalty when converting the statistical model to rules, but the gain in interpretability compensates for that: with minimal effort, human experts improve this model to have similar performance to the statistical model that served as starting point. |
| Tasks | |
| Published | 2016-06-30 |
| URL | http://arxiv.org/abs/1606.09604v1 |
| http://arxiv.org/pdf/1606.09604v1.pdf | |
| PWC | https://paperswithcode.com/paper/snaptogrid-from-statistical-to-interpretable |
| Repo | |
| Framework | |
Finding Approximate Local Minima Faster than Gradient Descent
| Title | Finding Approximate Local Minima Faster than Gradient Descent |
| Authors | Naman Agarwal, Zeyuan Allen-Zhu, Brian Bullins, Elad Hazan, Tengyu Ma |
| Abstract | We design a non-convex second-order optimization algorithm that is guaranteed to return an approximate local minimum in time which scales linearly in the underlying dimension and the number of training examples. The time complexity of our algorithm to find an approximate local minimum is even faster than that of gradient descent to find a critical point. Our algorithm applies to a general class of optimization problems including training a neural network and other non-convex objectives arising in machine learning. |
| Tasks | |
| Published | 2016-11-03 |
| URL | http://arxiv.org/abs/1611.01146v4 |
| http://arxiv.org/pdf/1611.01146v4.pdf | |
| PWC | https://paperswithcode.com/paper/finding-approximate-local-minima-faster-than |
| Repo | |
| Framework | |
Reliability of PET/CT shape and heterogeneity features in functional and morphological components of Non-Small Cell Lung Cancer tumors: a repeatability analysis in a prospective multi-center cohort
| Title | Reliability of PET/CT shape and heterogeneity features in functional and morphological components of Non-Small Cell Lung Cancer tumors: a repeatability analysis in a prospective multi-center cohort |
| Authors | Marie-Charlotte Desseroit, Florent Tixier, Wolfgang Weber, Barry A Siegel, Catherine Cheze Le Rest, Dimitris Visvikis, Mathieu Hatt |
| Abstract | Purpose: The main purpose of this study was to assess the reliability of shape and heterogeneity features in both Positron Emission Tomography (PET) and low-dose Computed Tomography (CT) components of PET/CT. A secondary objective was to investigate the impact of image quantization.Material and methods: A Health Insurance Portability and Accountability Act -compliant secondary analysis of deidentified prospectively acquired PET/CT test-retest datasets of 74 patients from multi-center Merck and ACRIN trials was performed. Metabolically active volumes were automatically delineated on PET with Fuzzy Locally Adaptive Bayesian algorithm. 3DSlicerTM was used to semi-automatically delineate the anatomical volumes on low-dose CT components. Two quantization methods were considered: a quantization into a set number of bins (quantizationB) and an alternative quantization with bins of fixed width (quantizationW). Four shape descriptors, ten first-order metrics and 26 textural features were computed. Bland-Altman analysis was used to quantify repeatability. Features were subsequently categorized as very reliable, reliable, moderately reliable and poorly reliable with respect to the corresponding volume variability. Results: Repeatability was highly variable amongst features. Numerous metrics were identified as poorly or moderately reliable. Others were (very) reliable in both modalities, and in all categories (shape, 1st-, 2nd- and 3rd-order metrics). Image quantization played a major role in the features repeatability. Features were more reliable in PET with quantizationB, whereas quantizationW showed better results in CT.Conclusion: The test-retest repeatability of shape and heterogeneity features in PET and low-dose CT varied greatly amongst metrics. The level of repeatability also depended strongly on the quantization step, with different optimal choices for each modality. The repeatability of PET and low-dose CT features should be carefully taken into account when selecting metrics to build multiparametric models. |
| Tasks | Computed Tomography (CT), Quantization |
| Published | 2016-10-05 |
| URL | http://arxiv.org/abs/1610.01390v1 |
| http://arxiv.org/pdf/1610.01390v1.pdf | |
| PWC | https://paperswithcode.com/paper/reliability-of-petct-shape-and-heterogeneity |
| Repo | |
| Framework | |
Binary Particle Swarm Optimization versus Hybrid Genetic Algorithm for Inferring Well Supported Phylogenetic Trees
| Title | Binary Particle Swarm Optimization versus Hybrid Genetic Algorithm for Inferring Well Supported Phylogenetic Trees |
| Authors | Bassam AlKindy, Bashar Al-Nuaimi, Christophe Guyeux, Jean-François Couchot, Michel Salomon, Reem Alsrraj, Laurent Philippe |
| Abstract | The amount of completely sequenced chloroplast genomes increases rapidly every day, leading to the possibility to build large-scale phylogenetic trees of plant species. Considering a subset of close plant species defined according to their chloroplasts, the phylogenetic tree that can be inferred by their core genes is not necessarily well supported, due to the possible occurrence of problematic genes (i.e., homoplasy, incomplete lineage sorting, horizontal gene transfers, etc.) which may blur the phylogenetic signal. However, a trustworthy phylogenetic tree can still be obtained provided such a number of blurring genes is reduced. The problem is thus to determine the largest subset of core genes that produces the best-supported tree. To discard problematic genes and due to the overwhelming number of possible combinations, this article focuses on how to extract the largest subset of sequences in order to obtain the most supported species tree. Due to computational complexity, a distributed Binary Particle Swarm Optimization (BPSO) is proposed in sequential and distributed fashions. Obtained results from both versions of the BPSO are compared with those computed using an hybrid approach embedding both genetic algorithms and statistical tests. The proposal has been applied to different cases of plant families, leading to encouraging results for these families. |
| Tasks | |
| Published | 2016-08-31 |
| URL | http://arxiv.org/abs/1608.08749v1 |
| http://arxiv.org/pdf/1608.08749v1.pdf | |
| PWC | https://paperswithcode.com/paper/binary-particle-swarm-optimization-versus |
| Repo | |
| Framework | |
Infinite Variational Autoencoder for Semi-Supervised Learning
| Title | Infinite Variational Autoencoder for Semi-Supervised Learning |
| Authors | Ehsan Abbasnejad, Anthony Dick, Anton van den Hengel |
| Abstract | This paper presents an infinite variational autoencoder (VAE) whose capacity adapts to suit the input data. This is achieved using a mixture model where the mixing coefficients are modeled by a Dirichlet process, allowing us to integrate over the coefficients when performing inference. Critically, this then allows us to automatically vary the number of autoencoders in the mixture based on the data. Experiments show the flexibility of our method, particularly for semi-supervised learning, where only a small number of training samples are available. |
| Tasks | |
| Published | 2016-11-23 |
| URL | http://arxiv.org/abs/1611.07800v2 |
| http://arxiv.org/pdf/1611.07800v2.pdf | |
| PWC | https://paperswithcode.com/paper/infinite-variational-autoencoder-for-semi |
| Repo | |
| Framework | |
The Intelligent Voice 2016 Speaker Recognition System
| Title | The Intelligent Voice 2016 Speaker Recognition System |
| Authors | Abbas Khosravani, Cornelius Glackin, Nazim Dugan, Gérard Chollet, Nigel Cannings |
| Abstract | This paper presents the Intelligent Voice (IV) system submitted to the NIST 2016 Speaker Recognition Evaluation (SRE). The primary emphasis of SRE this year was on developing speaker recognition technology which is robust for novel languages that are much more heterogeneous than those used in the current state-of-the-art, using significantly less training data, that does not contain meta-data from those languages. The system is based on the state-of-the-art i-vector/PLDA which is developed on the fixed training condition, and the results are reported on the protocol defined on the development set of the challenge. |
| Tasks | Speaker Recognition |
| Published | 2016-11-02 |
| URL | http://arxiv.org/abs/1611.00514v1 |
| http://arxiv.org/pdf/1611.00514v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-intelligent-voice-2016-speaker |
| Repo | |
| Framework | |
Dimensionality reduction based on Distance Preservation to Local Mean (DPLM) for SPD matrices and its application in BCI
| Title | Dimensionality reduction based on Distance Preservation to Local Mean (DPLM) for SPD matrices and its application in BCI |
| Authors | Alireza Davoudi, Saeed Shiry Ghidary, Khadijeh Sadatnejad |
| Abstract | In this paper, we propose a nonlinear dimensionality reduction algorithm for the manifold of Symmetric Positive Definite (SPD) matrices that considers the geometry of SPD matrices and provides a low dimensional representation of the manifold with high class discrimination. The proposed algorithm, tries to preserve the local structure of the data by preserving distance to local mean (DPLM) and also provides an implicit projection matrix. DPLM is linear in terms of the number of training samples and may use the label information when they are available in order to performance improvement in classification tasks. We performed several experiments on the multi-class dataset IIa from BCI competition IV. The results show that our approach as dimensionality reduction technique - leads to superior results in comparison with other competitor in the related literature because of its robustness against outliers. The experiments confirm that the combination of DPLM with FGMDM as the classifier leads to the state of the art performance on this dataset. |
| Tasks | Dimensionality Reduction |
| Published | 2016-07-29 |
| URL | http://arxiv.org/abs/1608.00514v1 |
| http://arxiv.org/pdf/1608.00514v1.pdf | |
| PWC | https://paperswithcode.com/paper/dimensionality-reduction-based-on-distance |
| Repo | |
| Framework | |
Deep fusion of visual signatures for client-server facial analysis
| Title | Deep fusion of visual signatures for client-server facial analysis |
| Authors | Binod Bhattarai, Gaurav Sharma, Frederic Jurie |
| Abstract | Facial analysis is a key technology for enabling human-machine interaction. In this context, we present a client-server framework, where a client transmits the signature of a face to be analyzed to the server, and, in return, the server sends back various information describing the face e.g. is the person male or female, is she/he bald, does he have a mustache, etc. We assume that a client can compute one (or a combination) of visual features; from very simple and efficient features, like Local Binary Patterns, to more complex and computationally heavy, like Fisher Vectors and CNN based, depending on the computing resources available. The challenge addressed in this paper is to design a common universal representation such that a single merged signature is transmitted to the server, whatever be the type and number of features computed by the client, ensuring nonetheless an optimal performance. Our solution is based on learning of a common optimal subspace for aligning the different face features and merging them into a universal signature. We have validated the proposed method on the challenging CelebA dataset, on which our method outperforms existing state-of-the-art methods when rich representation is available at test time, while giving competitive performance when only simple signatures (like LBP) are available at test time due to resource constraints on the client. |
| Tasks | |
| Published | 2016-11-01 |
| URL | http://arxiv.org/abs/1611.00142v2 |
| http://arxiv.org/pdf/1611.00142v2.pdf | |
| PWC | https://paperswithcode.com/paper/deep-fusion-of-visual-signatures-for-client |
| Repo | |
| Framework | |
