Paper Group ANR 375
Probabilistic Inference of Twitter Users’ Age based on What They Follow. Visual Question Answering: Datasets, Algorithms, and Future Challenges. DNA-inspired online behavioral modeling and its application to spambot detection. Generic Instance Search and Re-identification from One Example via Attributes and Categories. Dynamic Attention-controlled …
Probabilistic Inference of Twitter Users’ Age based on What They Follow
| Title | Probabilistic Inference of Twitter Users’ Age based on What They Follow |
| Authors | Benjamin Paul Chamberlain, Clive Humby, Marc Peter Deisenroth |
| Abstract | Twitter provides an open and rich source of data for studying human behaviour at scale and is widely used in social and network sciences. However, a major criticism of Twitter data is that demographic information is largely absent. Enhancing Twitter data with user ages would advance our ability to study social network structures, information flows and the spread of contagions. Approaches toward age detection of Twitter users typically focus on specific properties of tweets, e.g., linguistic features, which are language dependent. In this paper, we devise a language-independent methodology for determining the age of Twitter users from data that is native to the Twitter ecosystem. The key idea is to use a Bayesian framework to generalise ground-truth age information from a few Twitter users to the entire network based on what/whom they follow. Our approach scales to inferring the age of 700 million Twitter accounts with high accuracy. |
| Tasks | |
| Published | 2016-01-18 |
| URL | http://arxiv.org/abs/1601.04621v2 |
| http://arxiv.org/pdf/1601.04621v2.pdf | |
| PWC | https://paperswithcode.com/paper/probabilistic-inference-of-twitter-users-age |
| Repo | |
| Framework | |
Visual Question Answering: Datasets, Algorithms, and Future Challenges
| Title | Visual Question Answering: Datasets, Algorithms, and Future Challenges |
| Authors | Kushal Kafle, Christopher Kanan |
| Abstract | Visual Question Answering (VQA) is a recent problem in computer vision and natural language processing that has garnered a large amount of interest from the deep learning, computer vision, and natural language processing communities. In VQA, an algorithm needs to answer text-based questions about images. Since the release of the first VQA dataset in 2014, additional datasets have been released and many algorithms have been proposed. In this review, we critically examine the current state of VQA in terms of problem formulation, existing datasets, evaluation metrics, and algorithms. In particular, we discuss the limitations of current datasets with regard to their ability to properly train and assess VQA algorithms. We then exhaustively review existing algorithms for VQA. Finally, we discuss possible future directions for VQA and image understanding research. |
| Tasks | Question Answering, Visual Question Answering |
| Published | 2016-10-05 |
| URL | http://arxiv.org/abs/1610.01465v4 |
| http://arxiv.org/pdf/1610.01465v4.pdf | |
| PWC | https://paperswithcode.com/paper/visual-question-answering-datasets-algorithms |
| Repo | |
| Framework | |
DNA-inspired online behavioral modeling and its application to spambot detection
| Title | DNA-inspired online behavioral modeling and its application to spambot detection |
| Authors | Stefano Cresci, Roberto Di Pietro, Marinella Petrocchi, Angelo Spognardi, Maurizio Tesconi |
| Abstract | We propose a strikingly novel, simple, and effective approach to model online user behavior: we extract and analyze digital DNA sequences from user online actions and we use Twitter as a benchmark to test our proposal. We obtain an incisive and compact DNA-inspired characterization of user actions. Then, we apply standard DNA analysis techniques to discriminate between genuine and spambot accounts on Twitter. An experimental campaign supports our proposal, showing its effectiveness and viability. To the best of our knowledge, we are the first ones to identify and adapt DNA-inspired techniques to online user behavioral modeling. While Twitter spambot detection is a specific use case on a specific social media, our proposed methodology is platform and technology agnostic, hence paving the way for diverse behavioral characterization tasks. |
| Tasks | |
| Published | 2016-01-30 |
| URL | http://arxiv.org/abs/1602.00110v1 |
| http://arxiv.org/pdf/1602.00110v1.pdf | |
| PWC | https://paperswithcode.com/paper/dna-inspired-online-behavioral-modeling-and |
| Repo | |
| Framework | |
Generic Instance Search and Re-identification from One Example via Attributes and Categories
| Title | Generic Instance Search and Re-identification from One Example via Attributes and Categories |
| Authors | Ran Tao, Arnold W. M. Smeulders, Shih-Fu Chang |
| Abstract | This paper aims for generic instance search from one example where the instance can be an arbitrary object like shoes, not just near-planar and one-sided instances like buildings and logos. First, we evaluate state-of-the-art instance search methods on this problem. We observe that what works for buildings loses its generality on shoes. Second, we propose to use automatically learned category-specific attributes to address the large appearance variations present in generic instance search. Searching among instances from the same category as the query, the category-specific attributes outperform existing approaches by a large margin on shoes and cars and perform on par with the state-of-the-art on buildings. Third, we treat person re-identification as a special case of generic instance search. On the popular VIPeR dataset, we reach state-of-the-art performance with the same method. Fourth, we extend our method to search objects without restriction to the specifically known category. We show that the combination of category-level information and the category-specific attributes is superior to the alternative method combining category-level information with low-level features such as Fisher vector. |
| Tasks | Instance Search, Person Re-Identification |
| Published | 2016-05-23 |
| URL | http://arxiv.org/abs/1605.07104v1 |
| http://arxiv.org/pdf/1605.07104v1.pdf | |
| PWC | https://paperswithcode.com/paper/generic-instance-search-and-re-identification |
| Repo | |
| Framework | |
Dynamic Attention-controlled Cascaded Shape Regression Exploiting Training Data Augmentation and Fuzzy-set Sample Weighting
| Title | Dynamic Attention-controlled Cascaded Shape Regression Exploiting Training Data Augmentation and Fuzzy-set Sample Weighting |
| Authors | Zhen-Hua Feng, Josef Kittler, William Christmas, Patrik Huber, Xiao-Jun Wu |
| Abstract | We present a new Cascaded Shape Regression (CSR) architecture, namely Dynamic Attention-Controlled CSR (DAC-CSR), for robust facial landmark detection on unconstrained faces. Our DAC-CSR divides facial landmark detection into three cascaded sub-tasks: face bounding box refinement, general CSR and attention-controlled CSR. The first two stages refine initial face bounding boxes and output intermediate facial landmarks. Then, an online dynamic model selection method is used to choose appropriate domain-specific CSRs for further landmark refinement. The key innovation of our DAC-CSR is the fault-tolerant mechanism, using fuzzy set sample weighting for attention-controlled domain-specific model training. Moreover, we advocate data augmentation with a simple but effective 2D profile face generator, and context-aware feature extraction for better facial feature representation. Experimental results obtained on challenging datasets demonstrate the merits of our DAC-CSR over the state-of-the-art. |
| Tasks | Data Augmentation, Facial Landmark Detection, Model Selection |
| Published | 2016-11-16 |
| URL | http://arxiv.org/abs/1611.05396v2 |
| http://arxiv.org/pdf/1611.05396v2.pdf | |
| PWC | https://paperswithcode.com/paper/dynamic-attention-controlled-cascaded-shape |
| Repo | |
| Framework | |
Predictive Entropy Search for Multi-objective Bayesian Optimization with Constraints
| Title | Predictive Entropy Search for Multi-objective Bayesian Optimization with Constraints |
| Authors | Eduardo C. Garrido-Merchán, Daniel Hernández-Lobato |
| Abstract | This work presents PESMOC, Predictive Entropy Search for Multi-objective Bayesian Optimization with Constraints, an information-based strategy for the simultaneous optimization of multiple expensive-to-evaluate black-box functions under the presence of several constraints. PESMOC can hence be used to solve a wide range of optimization problems. Iteratively, PESMOC chooses an input location on which to evaluate the objective functions and the constraints so as to maximally reduce the entropy of the Pareto set of the corresponding optimization problem. The constraints considered in PESMOC are assumed to have similar properties to those of the objective functions in typical Bayesian optimization problems. That is, they do not have a known expression (which prevents gradient computation), their evaluation is considered to be very expensive, and the resulting observations may be corrupted by noise. These constraints arise in a plethora of expensive black-box optimization problems. We carry out synthetic experiments to illustrate the effectiveness of PESMOC, where we sample both the objectives and the constraints from a Gaussian process prior. The results obtained show that PESMOC is able to provide better recommendations with a smaller number of evaluations than a strategy based on random search. |
| Tasks | |
| Published | 2016-09-05 |
| URL | http://arxiv.org/abs/1609.01051v2 |
| http://arxiv.org/pdf/1609.01051v2.pdf | |
| PWC | https://paperswithcode.com/paper/predictive-entropy-search-for-multi-objective |
| Repo | |
| Framework | |
MGNC-CNN: A Simple Approach to Exploiting Multiple Word Embeddings for Sentence Classification
| Title | MGNC-CNN: A Simple Approach to Exploiting Multiple Word Embeddings for Sentence Classification |
| Authors | Ye Zhang, Stephen Roller, Byron Wallace |
| Abstract | We introduce a novel, simple convolution neural network (CNN) architecture - multi-group norm constraint CNN (MGNC-CNN) that capitalizes on multiple sets of word embeddings for sentence classification. MGNC-CNN extracts features from input embedding sets independently and then joins these at the penultimate layer in the network to form a final feature vector. We then adopt a group regularization strategy that differentially penalizes weights associated with the subcomponents generated from the respective embedding sets. This model is much simpler than comparable alternative architectures and requires substantially less training time. Furthermore, it is flexible in that it does not require input word embeddings to be of the same dimensionality. We show that MGNC-CNN consistently outperforms baseline models. |
| Tasks | Sentence Classification, Word Embeddings |
| Published | 2016-03-03 |
| URL | http://arxiv.org/abs/1603.00968v2 |
| http://arxiv.org/pdf/1603.00968v2.pdf | |
| PWC | https://paperswithcode.com/paper/mgnc-cnn-a-simple-approach-to-exploiting |
| Repo | |
| Framework | |
Uniform Hypergraph Partitioning: Provable Tensor Methods and Sampling Techniques
| Title | Uniform Hypergraph Partitioning: Provable Tensor Methods and Sampling Techniques |
| Authors | Debarghya Ghoshdastidar, Ambedkar Dukkipati |
| Abstract | In a series of recent works, we have generalised the consistency results in the stochastic block model literature to the case of uniform and non-uniform hypergraphs. The present paper continues the same line of study, where we focus on partitioning weighted uniform hypergraphs—a problem often encountered in computer vision. This work is motivated by two issues that arise when a hypergraph partitioning approach is used to tackle computer vision problems: (i) The uniform hypergraphs constructed for higher-order learning contain all edges, but most have negligible weights. Thus, the adjacency tensor is nearly sparse, and yet, not binary. (ii) A more serious concern is that standard partitioning algorithms need to compute all edge weights, which is computationally expensive for hypergraphs. This is usually resolved in practice by merging the clustering algorithm with a tensor sampling strategy—an approach that is yet to be analysed rigorously. We build on our earlier work on partitioning dense unweighted uniform hypergraphs (Ghoshdastidar and Dukkipati, ICML, 2015), and address the aforementioned issues by proposing provable and efficient partitioning algorithms. Our analysis justifies the empirical success of practical sampling techniques. We also complement our theoretical findings by elaborate empirical comparison of various hypergraph partitioning schemes. |
| Tasks | hypergraph partitioning |
| Published | 2016-02-21 |
| URL | http://arxiv.org/abs/1602.06516v4 |
| http://arxiv.org/pdf/1602.06516v4.pdf | |
| PWC | https://paperswithcode.com/paper/uniform-hypergraph-partitioning-provable |
| Repo | |
| Framework | |
Chinese Event Extraction Using DeepNeural Network with Word Embedding
| Title | Chinese Event Extraction Using DeepNeural Network with Word Embedding |
| Authors | Yandi Xia, Yang Liu |
| Abstract | A lot of prior work on event extraction has exploited a variety of features to represent events. Such methods have several drawbacks: 1) the features are often specific for a particular domain and do not generalize well; 2) the features are derived from various linguistic analyses and are error-prone; and 3) some features may be expensive and require domain expert. In this paper, we develop a Chinese event extraction system that uses word embedding vectors to represent language, and deep neural networks to learn the abstract feature representation in order to greatly reduce the effort of feature engineering. In addition, in this framework, we leverage large amount of unlabeled data, which can address the problem of limited labeled corpus for this task. Our experiments show that our proposed method performs better compared to the system using rich language features, and using unlabeled data benefits the word embeddings. This study suggests the potential of DNN and word embedding for the event extraction task. |
| Tasks | Feature Engineering, Word Embeddings |
| Published | 2016-10-04 |
| URL | http://arxiv.org/abs/1610.00842v1 |
| http://arxiv.org/pdf/1610.00842v1.pdf | |
| PWC | https://paperswithcode.com/paper/chinese-event-extraction-using-deepneural |
| Repo | |
| Framework | |
Longitudinal Face Modeling via Temporal Deep Restricted Boltzmann Machines
| Title | Longitudinal Face Modeling via Temporal Deep Restricted Boltzmann Machines |
| Authors | Chi Nhan Duong, Khoa Luu, Kha Gia Quach, Tien D. Bui |
| Abstract | Modeling the face aging process is a challenging task due to large and non-linear variations present in different stages of face development. This paper presents a deep model approach for face age progression that can efficiently capture the non-linear aging process and automatically synthesize a series of age-progressed faces in various age ranges. In this approach, we first decompose the long-term age progress into a sequence of short-term changes and model it as a face sequence. The Temporal Deep Restricted Boltzmann Machines based age progression model together with the prototype faces are then constructed to learn the aging transformation between faces in the sequence. In addition, to enhance the wrinkles of faces in the later age ranges, the wrinkle models are further constructed using Restricted Boltzmann Machines to capture their variations in different facial regions. The geometry constraints are also taken into account in the last step for more consistent age-progressed results. The proposed approach is evaluated using various face aging databases, i.e. FG-NET, Cross-Age Celebrity Dataset (CACD) and MORPH, and our collected large-scale aging database named AginG Faces in the Wild (AGFW). In addition, when ground-truth age is not available for input image, our proposed system is able to automatically estimate the age of the input face before aging process is employed. |
| Tasks | |
| Published | 2016-06-07 |
| URL | http://arxiv.org/abs/1606.02254v1 |
| http://arxiv.org/pdf/1606.02254v1.pdf | |
| PWC | https://paperswithcode.com/paper/longitudinal-face-modeling-via-temporal-deep |
| Repo | |
| Framework | |
Lock-Free Optimization for Non-Convex Problems
| Title | Lock-Free Optimization for Non-Convex Problems |
| Authors | Shen-Yi Zhao, Gong-Duo Zhang, Wu-Jun Li |
| Abstract | Stochastic gradient descent~(SGD) and its variants have attracted much attention in machine learning due to their efficiency and effectiveness for optimization. To handle large-scale problems, researchers have recently proposed several lock-free strategy based parallel SGD~(LF-PSGD) methods for multi-core systems. However, existing works have only proved the convergence of these LF-PSGD methods for convex problems. To the best of our knowledge, no work has proved the convergence of the LF-PSGD methods for non-convex problems. In this paper, we provide the theoretical proof about the convergence of two representative LF-PSGD methods, Hogwild! and AsySVRG, for non-convex problems. Empirical results also show that both Hogwild! and AsySVRG are convergent on non-convex problems, which successfully verifies our theoretical results. |
| Tasks | |
| Published | 2016-12-11 |
| URL | http://arxiv.org/abs/1612.03441v1 |
| http://arxiv.org/pdf/1612.03441v1.pdf | |
| PWC | https://paperswithcode.com/paper/lock-free-optimization-for-non-convex |
| Repo | |
| Framework | |
Authoring image decompositions with generative models
| Title | Authoring image decompositions with generative models |
| Authors | Jason Rock, Theerasit Issaranon, Aditya Deshpande, David Forsyth |
| Abstract | We show how to extend traditional intrinsic image decompositions to incorporate further layers above albedo and shading. It is hard to obtain data to learn a multi-layer decomposition. Instead, we can learn to decompose an image into layers that are “like this” by authoring generative models for each layer using proxy examples that capture the Platonic ideal (Mondrian images for albedo; rendered 3D primitives for shading; material swatches for shading detail). Our method then generates image layers, one from each model, that explain the image. Our approach rests on innovation in generative models for images. We introduce a Convolutional Variational Auto Encoder (conv-VAE), a novel VAE architecture that can reconstruct high fidelity images. The approach is general, and does not require that layers admit a physical interpretation. |
| Tasks | |
| Published | 2016-12-05 |
| URL | http://arxiv.org/abs/1612.01479v1 |
| http://arxiv.org/pdf/1612.01479v1.pdf | |
| PWC | https://paperswithcode.com/paper/authoring-image-decompositions-with |
| Repo | |
| Framework | |
Unsupervised Place Discovery for Visual Place Classification
| Title | Unsupervised Place Discovery for Visual Place Classification |
| Authors | Fei Xiaoxiao, Tanaka Kanji, Inamoto Kouya |
| Abstract | In this study, we explore the use of deep convolutional neural networks (DCNNs) in visual place classification for robotic mapping and localization. An open question is how to partition the robot’s workspace into places to maximize the performance (e.g., accuracy, precision, recall) of potential DCNN classifiers. This is a chicken and egg problem: If we had a well-trained DCNN classifier, it is rather easy to partition the robot’s workspace into places, but the training of a DCNN classifier requires a set of pre-defined place classes. In this study, we address this problem and present several strategies for unsupervised discovery of place classes (“time cue,” “location cue,” “time-appearance cue,” and “location-appearance cue”). We also evaluate the efficacy of the proposed methods using the publicly available University of Michigan North Campus Long-Term (NCLT) Dataset. |
| Tasks | |
| Published | 2016-12-21 |
| URL | http://arxiv.org/abs/1612.06933v1 |
| http://arxiv.org/pdf/1612.06933v1.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-place-discovery-for-visual-place |
| Repo | |
| Framework | |
An Approach for Noise Removal on Depth Images
| Title | An Approach for Noise Removal on Depth Images |
| Authors | Rashi Chaudhary, Himanshu Dasgupta |
| Abstract | Image based rendering is a fundamental problem in computer vision and graphics. Modern techniques often rely on depth image for the 3D construction. However for most of the existing depth cameras, the large and unpredictable noises can be problematic, which can cause noticeable artifacts in the rendered results. In this paper, we proposed an efficacious method for depth image noise removal that can be applied for most RGBD systems. The proposed solution will benefit many subsequent vision problems such as 3D reconstruction, novel view rendering, object recognition. Our experimental results demonstrate the efficacy and accuracy. |
| Tasks | 3D Reconstruction, Object Recognition |
| Published | 2016-02-16 |
| URL | http://arxiv.org/abs/1602.05168v1 |
| http://arxiv.org/pdf/1602.05168v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-approach-for-noise-removal-on-depth-images |
| Repo | |
| Framework | |
A Constant-Factor Bi-Criteria Approximation Guarantee for $k$-means++
| Title | A Constant-Factor Bi-Criteria Approximation Guarantee for $k$-means++ |
| Authors | Dennis Wei |
| Abstract | This paper studies the $k$-means++ algorithm for clustering as well as the class of $D^\ell$ sampling algorithms to which $k$-means++ belongs. It is shown that for any constant factor $\beta > 1$, selecting $\beta k$ cluster centers by $D^\ell$ sampling yields a constant-factor approximation to the optimal clustering with $k$ centers, in expectation and without conditions on the dataset. This result extends the previously known $O(\log k)$ guarantee for the case $\beta = 1$ to the constant-factor bi-criteria regime. It also improves upon an existing constant-factor bi-criteria result that holds only with constant probability. |
| Tasks | |
| Published | 2016-05-16 |
| URL | http://arxiv.org/abs/1605.04986v1 |
| http://arxiv.org/pdf/1605.04986v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-constant-factor-bi-criteria-approximation |
| Repo | |
| Framework | |
