Paper Group ANR 324
FSL-BM: Fuzzy Supervised Learning with Binary Meta-Feature for Classification. Properties on n-dimensional convolution for image deconvolution. A Joint Identification Approach for Argumentative Writing Revisions. PatternNet: Visual Pattern Mining with Deep Neural Network. Computing Egomotion with Local Loop Closures for Egocentric Videos. WebVision …
FSL-BM: Fuzzy Supervised Learning with Binary Meta-Feature for Classification
| Title | FSL-BM: Fuzzy Supervised Learning with Binary Meta-Feature for Classification |
| Authors | Kamran Kowsari, Nima Bari, Roman Vichr, Farhad A. Goodarzi |
| Abstract | This paper introduces a novel real-time Fuzzy Supervised Learning with Binary Meta-Feature (FSL-BM) for big data classification task. The study of real-time algorithms addresses several major concerns, which are namely: accuracy, memory consumption, and ability to stretch assumptions and time complexity. Attaining a fast computational model providing fuzzy logic and supervised learning is one of the main challenges in the machine learning. In this research paper, we present FSL-BM algorithm as an efficient solution of supervised learning with fuzzy logic processing using binary meta-feature representation using Hamming Distance and Hash function to relax assumptions. While many studies focused on reducing time complexity and increasing accuracy during the last decade, the novel contribution of this proposed solution comes through integration of Hamming Distance, Hash function, binary meta-features, binary classification to provide real time supervised method. Hash Tables (HT) component gives a fast access to existing indices; and therefore, the generation of new indices in a constant time complexity, which supersedes existing fuzzy supervised algorithms with better or comparable results. To summarize, the main contribution of this technique for real-time Fuzzy Supervised Learning is to represent hypothesis through binary input as meta-feature space and creating the Fuzzy Supervised Hash table to train and validate model. |
| Tasks | |
| Published | 2017-09-26 |
| URL | http://arxiv.org/abs/1709.09268v2 |
| http://arxiv.org/pdf/1709.09268v2.pdf | |
| PWC | https://paperswithcode.com/paper/fsl-bm-fuzzy-supervised-learning-with-binary |
| Repo | |
| Framework | |
Properties on n-dimensional convolution for image deconvolution
| Title | Properties on n-dimensional convolution for image deconvolution |
| Authors | Song Yizhi, Xu Cheng, Ding Daoxin, Zhou Hang, Quan Tingwei, Li Shiwei |
| Abstract | Convolution system is linear and time invariant, and can describe the optical imaging process. Based on convolution system, many deconvolution techniques have been developed for optical image analysis, such as boosting the space resolution of optical images, image denoising, image enhancement and so on. Here, we gave properties on N-dimensional convolution. By using these properties, we proposed image deconvolution method. This method uses a series of convolution operations to deconvolute image. We demonstrated that the method has the similar deconvolution results to the state-of-art method. The core calculation of the proposed method is image convolution, and thus our method can easily be integrated into GPU mode for large-scale image deconvolution. |
| Tasks | Denoising, Image Deconvolution, Image Denoising, Image Enhancement |
| Published | 2017-11-30 |
| URL | http://arxiv.org/abs/1711.11224v1 |
| http://arxiv.org/pdf/1711.11224v1.pdf | |
| PWC | https://paperswithcode.com/paper/properties-on-n-dimensional-convolution-for |
| Repo | |
| Framework | |
A Joint Identification Approach for Argumentative Writing Revisions
| Title | A Joint Identification Approach for Argumentative Writing Revisions |
| Authors | Fan Zhang, Diane Litman |
| Abstract | Prior work on revision identification typically uses a pipeline method: revision extraction is first conducted to identify the locations of revisions and revision classification is then conducted on the identified revisions. Such a setting propagates the errors of the revision extraction step to the revision classification step. This paper proposes an approach that identifies the revision location and the revision type jointly to solve the issue of error propagation. It utilizes a sequence representation of revisions and conducts sequence labeling for revision identification. A mutation-based approach is utilized to update identification sequences. Results demonstrate that our proposed approach yields better performance on both revision location extraction and revision type classification compared to a pipeline baseline. |
| Tasks | |
| Published | 2017-02-28 |
| URL | http://arxiv.org/abs/1703.00089v1 |
| http://arxiv.org/pdf/1703.00089v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-joint-identification-approach-for |
| Repo | |
| Framework | |
PatternNet: Visual Pattern Mining with Deep Neural Network
| Title | PatternNet: Visual Pattern Mining with Deep Neural Network |
| Authors | Hongzhi Li, Joseph G. Ellis, Lei Zhang, Shih-Fu Chang |
| Abstract | Visual patterns represent the discernible regularity in the visual world. They capture the essential nature of visual objects or scenes. Understanding and modeling visual patterns is a fundamental problem in visual recognition that has wide ranging applications. In this paper, we study the problem of visual pattern mining and propose a novel deep neural network architecture called PatternNet for discovering these patterns that are both discriminative and representative. The proposed PatternNet leverages the filters in the last convolution layer of a convolutional neural network to find locally consistent visual patches, and by combining these filters we can effectively discover unique visual patterns. In addition, PatternNet can discover visual patterns efficiently without performing expensive image patch sampling, and this advantage provides an order of magnitude speedup compared to most other approaches. We evaluate the proposed PatternNet subjectively by showing randomly selected visual patterns which are discovered by our method and quantitatively by performing image classification with the identified visual patterns and comparing our performance with the current state-of-the-art. We also directly evaluate the quality of the discovered visual patterns by leveraging the identified patterns as proposed objects in an image and compare with other relevant methods. Our proposed network and procedure, PatterNet, is able to outperform competing methods for the tasks described. |
| Tasks | Image Classification |
| Published | 2017-03-18 |
| URL | http://arxiv.org/abs/1703.06339v2 |
| http://arxiv.org/pdf/1703.06339v2.pdf | |
| PWC | https://paperswithcode.com/paper/patternnet-visual-pattern-mining-with-deep |
| Repo | |
| Framework | |
Computing Egomotion with Local Loop Closures for Egocentric Videos
| Title | Computing Egomotion with Local Loop Closures for Egocentric Videos |
| Authors | Suvam Patra, Himanshu Aggarwal, Himani Arora, Chetan Arora, Subhashis Banerjee |
| Abstract | Finding the camera pose is an important step in many egocentric video applications. It has been widely reported that, state of the art SLAM algorithms fail on egocentric videos. In this paper, we propose a robust method for camera pose estimation, designed specifically for egocentric videos. In an egocentric video, the camera views the same scene point multiple times as the wearer’s head sweeps back and forth. We use this specific motion profile to perform short loop closures aligned with wearer’s footsteps. For egocentric videos, depth estimation is usually noisy. In an important departure, we use 2D computations for rotation averaging which do not rely upon depth estimates. The two modification results in much more stable algorithm as is evident from our experiments on various egocentric video datasets for different egocentric applications. The proposed algorithm resolves a long standing problem in egocentric vision and unlocks new usage scenarios for future applications. |
| Tasks | Depth Estimation, Pose Estimation |
| Published | 2017-01-17 |
| URL | http://arxiv.org/abs/1701.04743v1 |
| http://arxiv.org/pdf/1701.04743v1.pdf | |
| PWC | https://paperswithcode.com/paper/computing-egomotion-with-local-loop-closures |
| Repo | |
| Framework | |
WebVision Challenge: Visual Learning and Understanding With Web Data
| Title | WebVision Challenge: Visual Learning and Understanding With Web Data |
| Authors | Wen Li, Limin Wang, Wei Li, Eirikur Agustsson, Jesse Berent, Abhinav Gupta, Rahul Sukthankar, Luc Van Gool |
| Abstract | We present the 2017 WebVision Challenge, a public image recognition challenge designed for deep learning based on web images without instance-level human annotation. Following the spirit of previous vision challenges, such as ILSVRC, Places2 and PASCAL VOC, which have played critical roles in the development of computer vision by contributing to the community with large scale annotated data for model designing and standardized benchmarking, we contribute with this challenge a large scale web images dataset, and a public competition with a workshop co-located with CVPR 2017. The WebVision dataset contains more than $2.4$ million web images crawled from the Internet by using queries generated from the $1,000$ semantic concepts of the benchmark ILSVRC 2012 dataset. Meta information is also included. A validation set and test set containing human annotated images are also provided to facilitate algorithmic development. The 2017 WebVision challenge consists of two tracks, the image classification task on WebVision test set, and the transfer learning task on PASCAL VOC 2012 dataset. In this paper, we describe the details of data collection and annotation, highlight the characteristics of the dataset, and introduce the evaluation metrics. |
| Tasks | Image Classification, Transfer Learning |
| Published | 2017-05-16 |
| URL | http://arxiv.org/abs/1705.05640v1 |
| http://arxiv.org/pdf/1705.05640v1.pdf | |
| PWC | https://paperswithcode.com/paper/webvision-challenge-visual-learning-and |
| Repo | |
| Framework | |
Syntax-Directed Attention for Neural Machine Translation
| Title | Syntax-Directed Attention for Neural Machine Translation |
| Authors | Kehai Chen, Rui Wang, Masao Utiyama, Eiichiro Sumita, Tiejun Zhao |
| Abstract | Attention mechanism, including global attention and local attention, plays a key role in neural machine translation (NMT). Global attention attends to all source words for word prediction. In comparison, local attention selectively looks at fixed-window source words. However, alignment weights for the current target word often decrease to the left and right by linear distance centering on the aligned source position and neglect syntax-directed distance constraints. In this paper, we extend local attention with syntax-distance constraint, to focus on syntactically related source words with the predicted target word, thus learning a more effective context vector for word prediction. Moreover, we further propose a double context NMT architecture, which consists of a global context vector and a syntax-directed context vector over the global attention, to provide more translation performance for NMT from source representation. The experiments on the large-scale Chinese-to-English and English-to-Germen translation tasks show that the proposed approach achieves a substantial and significant improvement over the baseline system. |
| Tasks | Machine Translation |
| Published | 2017-11-12 |
| URL | https://arxiv.org/abs/1711.04231v3 |
| https://arxiv.org/pdf/1711.04231v3.pdf | |
| PWC | https://paperswithcode.com/paper/syntax-directed-attention-for-neural-machine |
| Repo | |
| Framework | |
Combining Deep Universal Features, Semantic Attributes, and Hierarchical Classification for Zero-Shot Learning
| Title | Combining Deep Universal Features, Semantic Attributes, and Hierarchical Classification for Zero-Shot Learning |
| Authors | Jared Markowitz, Aurora C. Schmidt, Philippe M. Burlina, I-Jeng Wang |
| Abstract | We address zero-shot (ZS) learning, building upon prior work in hierarchical classification by combining it with approaches based on semantic attribute estimation. For both non-novel and novel image classes we compare multiple formulations of the problem, starting with deep universal features in each case. We investigate the effect of using different posterior probabilities as inputs to the hierarchical classifier, comparing the performances of posteriors derived from distances to SVM classifier boundaries with those of posteriors based on semantic attribute estimation. Using a dataset consisting of 150 object classes from the ImageNet ILSVRC2012 data set, we find that the hierarchical classification method that maximizes expected reward for non-novel classes differs from the method that maximizes expected reward for novel classes. We also show that using input posteriors based on semantic attributes improves the expected reward for novel classes. |
| Tasks | Zero-Shot Learning |
| Published | 2017-12-08 |
| URL | http://arxiv.org/abs/1712.03151v1 |
| http://arxiv.org/pdf/1712.03151v1.pdf | |
| PWC | https://paperswithcode.com/paper/combining-deep-universal-features-semantic |
| Repo | |
| Framework | |
Discovering Discrete Latent Topics with Neural Variational Inference
| Title | Discovering Discrete Latent Topics with Neural Variational Inference |
| Authors | Yishu Miao, Edward Grefenstette, Phil Blunsom |
| Abstract | Topic models have been widely explored as probabilistic generative models of documents. Traditional inference methods have sought closed-form derivations for updating the models, however as the expressiveness of these models grows, so does the difficulty of performing fast and accurate inference over their parameters. This paper presents alternative neural approaches to topic modelling by providing parameterisable distributions over topics which permit training by backpropagation in the framework of neural variational inference. In addition, with the help of a stick-breaking construction, we propose a recurrent network that is able to discover a notionally unbounded number of topics, analogous to Bayesian non-parametric topic models. Experimental results on the MXM Song Lyrics, 20NewsGroups and Reuters News datasets demonstrate the effectiveness and efficiency of these neural topic models. |
| Tasks | Topic Models |
| Published | 2017-06-01 |
| URL | http://arxiv.org/abs/1706.00359v2 |
| http://arxiv.org/pdf/1706.00359v2.pdf | |
| PWC | https://paperswithcode.com/paper/discovering-discrete-latent-topics-with |
| Repo | |
| Framework | |
Contrast and visual saliency similarity-induced index for assessing image quality
| Title | Contrast and visual saliency similarity-induced index for assessing image quality |
| Authors | Huizhen Jia, Lu Zhang, Tonghan Wang |
| Abstract | Image quality that is consistent with human opinion is assessed by a perceptual image quality assessment (IQA) that defines/utilizes a computational model. A good model should take effectiveness and efficiency into consideration, but most of the previously proposed IQA models do not simultaneously consider these factors. Therefore, this study attempts to develop an effective and efficient IQA metric. Contrast is an inherent visual attribute that indicates image quality, and visual saliency (VS) is a quality that attracts the attention of human beings. The proposed model utilized these two features to characterize the image local quality. After obtaining the local contrast quality map and the global VS quality map, we added the weighted standard deviation of the previous two quality maps together to yield the final quality score. The experimental results for three benchmark databases (LIVE, TID2008, and CSIQ) demonstrated that our model performs the best in terms of a correlation with the human judgment of visual quality. Furthermore, compared with competing IQA models, this proposed model is more efficient. |
| Tasks | Image Quality Assessment |
| Published | 2017-08-22 |
| URL | http://arxiv.org/abs/1708.06616v3 |
| http://arxiv.org/pdf/1708.06616v3.pdf | |
| PWC | https://paperswithcode.com/paper/contrast-and-visual-saliency-similarity |
| Repo | |
| Framework | |
Learning the distribution with largest mean: two bandit frameworks
| Title | Learning the distribution with largest mean: two bandit frameworks |
| Authors | Emilie Kaufmann, Aurélien Garivier |
| Abstract | Over the past few years, the multi-armed bandit model has become increasingly popular in the machine learning community, partly because of applications including online content optimization. This paper reviews two different sequential learning tasks that have been considered in the bandit literature ; they can be formulated as (sequentially) learning which distribution has the highest mean among a set of distributions, with some constraints on the learning process. For both of them (regret minimization and best arm identification) we present recent, asymptotically optimal algorithms. We compare the behaviors of the sampling rule of each algorithm as well as the complexity terms associated to each problem. |
| Tasks | |
| Published | 2017-01-31 |
| URL | http://arxiv.org/abs/1702.00001v3 |
| http://arxiv.org/pdf/1702.00001v3.pdf | |
| PWC | https://paperswithcode.com/paper/learning-the-distribution-with-largest-mean |
| Repo | |
| Framework | |
Towards a Dedicated Computer Vision Tool set for Crowd Simulation Models
| Title | Towards a Dedicated Computer Vision Tool set for Crowd Simulation Models |
| Authors | Sultan Daud Khan, Muhammad Saqib, Michael Blumenstein |
| Abstract | As the population of world is increasing, and even more concentrated in urban areas, ensuring public safety is becoming a taunting job for security personnel and crowd managers. Mass events like sports, festivals, concerts, political gatherings attract thousand of people in a constraint environment,therefore adequate safety measures should be adopted. Despite safety measures, crowd disasters still occur frequently. Understanding underlying dynamics and behavior of crowd is becoming areas of interest for most of computer scientists. In recent years, researchers developed several models for understanding crowd dynamics. These models should be properly calibrated and validated by means of data acquired in the field. In this paper, we developed a computer vision tool set that can be helpful not only in initializing the crowd simulation models but can also validate the simulation results. The main features of proposed tool set are: (1) Crowd flow segmentation and crowd counting, (2) Identifying source/sink location for understanding crowd behavior, (3) Group detection and tracking in crowds. |
| Tasks | Crowd Counting |
| Published | 2017-09-01 |
| URL | http://arxiv.org/abs/1709.02243v1 |
| http://arxiv.org/pdf/1709.02243v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-a-dedicated-computer-vision-tool-set |
| Repo | |
| Framework | |
Revisiting the Centroid-based Method: A Strong Baseline for Multi-Document Summarization
| Title | Revisiting the Centroid-based Method: A Strong Baseline for Multi-Document Summarization |
| Authors | Demian Gholipour Ghalandari |
| Abstract | The centroid-based model for extractive document summarization is a simple and fast baseline that ranks sentences based on their similarity to a centroid vector. In this paper, we apply this ranking to possible summaries instead of sentences and use a simple greedy algorithm to find the best summary. Furthermore, we show possi- bilities to scale up to larger input docu- ment collections by selecting a small num- ber of sentences from each document prior to constructing the summary. Experiments were done on the DUC2004 dataset for multi-document summarization. We ob- serve a higher performance over the orig- inal model, on par with more complex state-of-the-art methods. |
| Tasks | Document Summarization, Extractive Document Summarization, Multi-Document Summarization |
| Published | 2017-08-25 |
| URL | http://arxiv.org/abs/1708.07690v1 |
| http://arxiv.org/pdf/1708.07690v1.pdf | |
| PWC | https://paperswithcode.com/paper/revisiting-the-centroid-based-method-a-strong |
| Repo | |
| Framework | |
Reader-Aware Multi-Document Summarization: An Enhanced Model and The First Dataset
| Title | Reader-Aware Multi-Document Summarization: An Enhanced Model and The First Dataset |
| Authors | Piji Li, Lidong Bing, Wai Lam |
| Abstract | We investigate the problem of reader-aware multi-document summarization (RA-MDS) and introduce a new dataset for this problem. To tackle RA-MDS, we extend a variational auto-encodes (VAEs) based MDS framework by jointly considering news documents and reader comments. To conduct evaluation for summarization performance, we prepare a new dataset. We describe the methods for data collection, aspect annotation, and summary writing as well as scrutinizing by experts. Experimental results show that reader comments can improve the summarization performance, which also demonstrates the usefulness of the proposed dataset. The annotated dataset for RA-MDS is available online. |
| Tasks | Document Summarization, Multi-Document Summarization |
| Published | 2017-08-03 |
| URL | http://arxiv.org/abs/1708.01065v1 |
| http://arxiv.org/pdf/1708.01065v1.pdf | |
| PWC | https://paperswithcode.com/paper/reader-aware-multi-document-summarization-an |
| Repo | |
| Framework | |
D-PCN: Parallel Convolutional Networks for Image Recognition via a Discriminator
| Title | D-PCN: Parallel Convolutional Networks for Image Recognition via a Discriminator |
| Authors | Shiqi Yang, Gang Peng |
| Abstract | In this paper, we introduce a simple but quite effective recognition framework dubbed D-PCN, aiming at enhancing feature extracting ability of CNN. The framework consists of two parallel CNNs, a discriminator and an extra classifier which takes integrated features from parallel networks and gives final prediction. The discriminator is core which drives parallel networks to focus on different regions and learn complementary representations. The corresponding joint training strategy is introduced which ensures the utilization of discriminator. We validate D-PCN with several CNN models on two benchmark datasets: CIFAR-100 and ImageNet32x32, D-PCN enhances all models. In particular it yields state of the art performance on CIFAR-100 compared with related works. We also conduct visualization experiment on fine-grained Stanford Dogs dataset and verify our motivation. Additionally, we apply D-PCN for segmentation on PASCAL VOC 2012 and also find promotion. |
| Tasks | |
| Published | 2017-11-12 |
| URL | http://arxiv.org/abs/1711.04237v3 |
| http://arxiv.org/pdf/1711.04237v3.pdf | |
| PWC | https://paperswithcode.com/paper/d-pcn-parallel-convolutional-networks-for |
| Repo | |
| Framework | |
