Paper Group ANR 491
Real-Time Adaptive Image Compression. Social Learning and Diffusion of Pervasive Goods: An Empirical Study of an African App Store. Efficient Version-Space Reduction for Visual Tracking. Learning to Represent Haptic Feedback for Partially-Observable Tasks. On Early-stage Debunking Rumors on Twitter: Leveraging the Wisdom of Weak Learners. Person Re …
Real-Time Adaptive Image Compression
| Title | Real-Time Adaptive Image Compression |
| Authors | Oren Rippel, Lubomir Bourdev |
| Abstract | We present a machine learning-based approach to lossy image compression which outperforms all existing codecs, while running in real-time. Our algorithm typically produces files 2.5 times smaller than JPEG and JPEG 2000, 2 times smaller than WebP, and 1.7 times smaller than BPG on datasets of generic images across all quality levels. At the same time, our codec is designed to be lightweight and deployable: for example, it can encode or decode the Kodak dataset in around 10ms per image on GPU. Our architecture is an autoencoder featuring pyramidal analysis, an adaptive coding module, and regularization of the expected codelength. We also supplement our approach with adversarial training specialized towards use in a compression setting: this enables us to produce visually pleasing reconstructions for very low bitrates. |
| Tasks | Image Compression |
| Published | 2017-05-16 |
| URL | http://arxiv.org/abs/1705.05823v1 |
| http://arxiv.org/pdf/1705.05823v1.pdf | |
| PWC | https://paperswithcode.com/paper/real-time-adaptive-image-compression |
| Repo | |
| Framework | |
Social Learning and Diffusion of Pervasive Goods: An Empirical Study of an African App Store
| Title | Social Learning and Diffusion of Pervasive Goods: An Empirical Study of an African App Store |
| Authors | Meisam Hejazi Nia, Brian T. Ratchford, Norris Bruce |
| Abstract | In this study, the authors develop a structural model that combines a macro diffusion model with a micro choice model to control for the effect of social influence on the mobile app choices of customers over app stores. Social influence refers to the density of adopters within the proximity of other customers. Using a large data set from an African app store and Bayesian estimation methods, the authors quantify the effect of social influence and investigate the impact of ignoring this process in estimating customer choices. The findings show that customer choices in the app store are explained better by offline than online density of adopters and that ignoring social influence in estimations results in biased estimates. Furthermore, the findings show that the mobile app adoption process is similar to adoption of music CDs, among all other classic economy goods. A counterfactual analysis shows that the app store can increase its revenue by 13.6% through a viral marketing policy (e.g., a sharing with friends and family button). |
| Tasks | |
| Published | 2017-02-22 |
| URL | http://arxiv.org/abs/1702.06661v1 |
| http://arxiv.org/pdf/1702.06661v1.pdf | |
| PWC | https://paperswithcode.com/paper/social-learning-and-diffusion-of-pervasive |
| Repo | |
| Framework | |
Efficient Version-Space Reduction for Visual Tracking
| Title | Efficient Version-Space Reduction for Visual Tracking |
| Authors | Kourosh Meshgi, Shigeyuki Oba, Shin Ishii |
| Abstract | Discrminative trackers, employ a classification approach to separate the target from its background. To cope with variations of the target shape and appearance, the classifier is updated online with different samples of the target and the background. Sample selection, labeling and updating the classifier is prone to various sources of errors that drift the tracker. We introduce the use of an efficient version space shrinking strategy to reduce the labeling errors and enhance its sampling strategy by measuring the uncertainty of the tracker about the samples. The proposed tracker, utilize an ensemble of classifiers that represents different hypotheses about the target, diversify them using boosting to provide a larger and more consistent coverage of the version-space and tune the classifiers’ weights in voting. The proposed system adjusts the model update rate by promoting the co-training of the short-memory ensemble with a long-memory oracle. The proposed tracker outperformed state-of-the-art trackers on different sequences bearing various tracking challenges. |
| Tasks | Visual Tracking |
| Published | 2017-04-02 |
| URL | http://arxiv.org/abs/1704.00299v1 |
| http://arxiv.org/pdf/1704.00299v1.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-version-space-reduction-for-visual |
| Repo | |
| Framework | |
Learning to Represent Haptic Feedback for Partially-Observable Tasks
| Title | Learning to Represent Haptic Feedback for Partially-Observable Tasks |
| Authors | Jaeyong Sung, J. Kenneth Salisbury, Ashutosh Saxena |
| Abstract | The sense of touch, being the earliest sensory system to develop in a human body [1], plays a critical part of our daily interaction with the environment. In order to successfully complete a task, many manipulation interactions require incorporating haptic feedback. However, manually designing a feedback mechanism can be extremely challenging. In this work, we consider manipulation tasks that need to incorporate tactile sensor feedback in order to modify a provided nominal plan. To incorporate partial observation, we present a new framework that models the task as a partially observable Markov decision process (POMDP) and learns an appropriate representation of haptic feedback which can serve as the state for a POMDP model. The model, that is parametrized by deep recurrent neural networks, utilizes variational Bayes methods to optimize the approximate posterior. Finally, we build on deep Q-learning to be able to select the optimal action in each state without access to a simulator. We test our model on a PR2 robot for multiple tasks of turning a knob until it clicks. |
| Tasks | Q-Learning |
| Published | 2017-05-17 |
| URL | http://arxiv.org/abs/1705.06243v1 |
| http://arxiv.org/pdf/1705.06243v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-to-represent-haptic-feedback-for |
| Repo | |
| Framework | |
On Early-stage Debunking Rumors on Twitter: Leveraging the Wisdom of Weak Learners
| Title | On Early-stage Debunking Rumors on Twitter: Leveraging the Wisdom of Weak Learners |
| Authors | Tu Ngoc Nguyen, Cheng Li, Claudia Niederée |
| Abstract | Recently a lot of progress has been made in rumor modeling and rumor detection for micro-blogging streams. However, existing automated methods do not perform very well for early rumor detection, which is crucial in many settings, e.g., in crisis situations. One reason for this is that aggregated rumor features such as propagation features, which work well on the long run, are - due to their accumulating characteristic - not very helpful in the early phase of a rumor. In this work, we present an approach for early rumor detection, which leverages Convolutional Neural Networks for learning the hidden representations of individual rumor-related tweets to gain insights on the credibility of each tweets. We then aggregate the predictions from the very beginning of a rumor to obtain the overall event credits (so-called wisdom), and finally combine it with a time series based rumor classification model. Our extensive experiments show a clearly improved classification performance within the critical very first hours of a rumor. For a better understanding, we also conduct an extensive feature evaluation that emphasized on the early stage and shows that the low-level credibility has best predictability at all phases of the rumor lifetime. |
| Tasks | Time Series |
| Published | 2017-09-13 |
| URL | http://arxiv.org/abs/1709.04402v1 |
| http://arxiv.org/pdf/1709.04402v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-early-stage-debunking-rumors-on-twitter |
| Repo | |
| Framework | |
Person Re-Identification via Recurrent Feature Aggregation
| Title | Person Re-Identification via Recurrent Feature Aggregation |
| Authors | Yichao Yan, Bingbing Ni, Zhichao Song, Chao Ma, Yan Yan, Xiaokang Yang |
| Abstract | We address the person re-identification problem by effectively exploiting a globally discriminative feature representation from a sequence of tracked human regions/patches. This is in contrast to previous person re-id works, which rely on either single frame based person to person patch matching, or graph based sequence to sequence matching. We show that a progressive/sequential fusion framework based on long short term memory (LSTM) network aggregates the frame-wise human region representation at each time stamp and yields a sequence level human feature representation. Since LSTM nodes can remember and propagate previously accumulated good features and forget newly input inferior ones, even with simple hand-crafted features, the proposed recurrent feature aggregation network (RFA-Net) is effective in generating highly discriminative sequence level human representations. Extensive experimental results on two person re-identification benchmarks demonstrate that the proposed method performs favorably against state-of-the-art person re-identification methods. |
| Tasks | Person Re-Identification |
| Published | 2017-01-23 |
| URL | http://arxiv.org/abs/1701.06351v1 |
| http://arxiv.org/pdf/1701.06351v1.pdf | |
| PWC | https://paperswithcode.com/paper/person-re-identification-via-recurrent |
| Repo | |
| Framework | |
Distributed Representations of Signed Networks
| Title | Distributed Representations of Signed Networks |
| Authors | Mohammad Raihanul Islam, B. Aditya Prakash, Naren Ramakrishnan |
| Abstract | Recent successes in word embedding and document embedding have motivated researchers to explore similar representations for networks and to use such representations for tasks such as edge prediction, node label prediction, and community detection. Such network embedding methods are largely focused on finding distributed representations for unsigned networks and are unable to discover embeddings that respect polarities inherent in edges. We propose SIGNet, a fast scalable embedding method suitable for signed networks. Our proposed objective function aims to carefully model the social structure implicit in signed networks by reinforcing the principles of social balance theory. Our method builds upon the traditional word2vec family of embedding approaches and adds a new targeted node sampling strategy to maintain structural balance in higher-order neighborhoods. We demonstrate the superiority of SIGNet over state-of-the-art methods proposed for both signed and unsigned networks on several real world datasets from different domains. In particular, SIGNet offers an approach to generate a richer vocabulary of features of signed networks to support representation and reasoning. |
| Tasks | Community Detection, Document Embedding, Network Embedding |
| Published | 2017-02-22 |
| URL | http://arxiv.org/abs/1702.06819v5 |
| http://arxiv.org/pdf/1702.06819v5.pdf | |
| PWC | https://paperswithcode.com/paper/signet-scalable-embeddings-for-signed |
| Repo | |
| Framework | |
Dueling Bandits With Weak Regret
| Title | Dueling Bandits With Weak Regret |
| Authors | Bangrui Chen, Peter I. Frazier |
| Abstract | We consider online content recommendation with implicit feedback through pairwise comparisons, formalized as the so-called dueling bandit problem. We study the dueling bandit problem in the Condorcet winner setting, and consider two notions of regret: the more well-studied strong regret, which is 0 only when both arms pulled are the Condorcet winner; and the less well-studied weak regret, which is 0 if either arm pulled is the Condorcet winner. We propose a new algorithm for this problem, Winner Stays (WS), with variations for each kind of regret: WS for weak regret (WS-W) has expected cumulative weak regret that is $O(N^2)$, and $O(N\log(N))$ if arms have a total order; WS for strong regret (WS-S) has expected cumulative strong regret of $O(N^2 + N \log(T))$, and $O(N\log(N)+N\log(T))$ if arms have a total order. WS-W is the first dueling bandit algorithm with weak regret that is constant in time. WS is simple to compute, even for problems with many arms, and we demonstrate through numerical experiments on simulated and real data that WS has significantly smaller regret than existing algorithms in both the weak- and strong-regret settings. |
| Tasks | |
| Published | 2017-06-14 |
| URL | http://arxiv.org/abs/1706.04304v1 |
| http://arxiv.org/pdf/1706.04304v1.pdf | |
| PWC | https://paperswithcode.com/paper/dueling-bandits-with-weak-regret |
| Repo | |
| Framework | |
Deep multi-frame face super-resolution
| Title | Deep multi-frame face super-resolution |
| Authors | E. Ustinova, V. Lempitsky |
| Abstract | Face verification and recognition problems have seen rapid progress in recent years, however recognition from small size images remains a challenging task that is inherently intertwined with the task of face super-resolution. Tackling this problem using multiple frames is an attractive idea, yet requires solving the alignment problem that is also challenging for low-resolution faces. Here we present a holistic system for multi-frame recognition, alignment, and superresolution of faces. Our neural network architecture restores the central frame of each input sequence additionally taking into account a number of adjacent frames and making use of sub-pixel movements. We present our results using the popular dataset for video face recognition (YouTube Faces). We show a notable improvement of identification score compared to several baselines including the one based on single-image super-resolution. |
| Tasks | Face Recognition, Face Verification, Image Super-Resolution, Super-Resolution |
| Published | 2017-09-10 |
| URL | http://arxiv.org/abs/1709.03196v2 |
| http://arxiv.org/pdf/1709.03196v2.pdf | |
| PWC | https://paperswithcode.com/paper/deep-multi-frame-face-super-resolution |
| Repo | |
| Framework | |
Reinforcement Learning in a large scale photonic Recurrent Neural Network
| Title | Reinforcement Learning in a large scale photonic Recurrent Neural Network |
| Authors | Julian Bueno, Sheler Maktoobi, Luc Froehly, Ingo Fischer, Maxime Jacquot, Laurent Larger, Daniel Brunner |
| Abstract | Photonic Neural Network implementations have been gaining considerable attention as a potentially disruptive future technology. Demonstrating learning in large scale neural networks is essential to establish photonic machine learning substrates as viable information processing systems. Realizing photonic Neural Networks with numerous nonlinear nodes in a fully parallel and efficient learning hardware was lacking so far. We demonstrate a network of up to 2500 diffractively coupled photonic nodes, forming a large scale Recurrent Neural Network. Using a Digital Micro Mirror Device, we realize reinforcement learning. Our scheme is fully parallel, and the passive weights maximize energy efficiency and bandwidth. The computational output efficiently converges and we achieve very good performance. |
| Tasks | |
| Published | 2017-11-14 |
| URL | http://arxiv.org/abs/1711.05133v2 |
| http://arxiv.org/pdf/1711.05133v2.pdf | |
| PWC | https://paperswithcode.com/paper/reinforcement-learning-in-a-large-scale |
| Repo | |
| Framework | |
Learning Context-Sensitive Convolutional Filters for Text Processing
| Title | Learning Context-Sensitive Convolutional Filters for Text Processing |
| Authors | Dinghan Shen, Martin Renqiang Min, Yitong Li, Lawrence Carin |
| Abstract | Convolutional neural networks (CNNs) have recently emerged as a popular building block for natural language processing (NLP). Despite their success, most existing CNN models employed in NLP share the same learned (and static) set of filters for all input sentences. In this paper, we consider an approach of using a small meta network to learn context-sensitive convolutional filters for text processing. The role of meta network is to abstract the contextual information of a sentence or document into a set of input-aware filters. We further generalize this framework to model sentence pairs, where a bidirectional filter generation mechanism is introduced to encapsulate co-dependent sentence representations. In our benchmarks on four different tasks, including ontology classification, sentiment analysis, answer sentence selection, and paraphrase identification, our proposed model, a modified CNN with context-sensitive filters, consistently outperforms the standard CNN and attention-based CNN baselines. By visualizing the learned context-sensitive filters, we further validate and rationalize the effectiveness of proposed framework. |
| Tasks | Paraphrase Identification, Sentiment Analysis, Text Classification |
| Published | 2017-09-25 |
| URL | http://arxiv.org/abs/1709.08294v3 |
| http://arxiv.org/pdf/1709.08294v3.pdf | |
| PWC | https://paperswithcode.com/paper/learning-context-sensitive-convolutional |
| Repo | |
| Framework | |
Intent-Aware Contextual Recommendation System
| Title | Intent-Aware Contextual Recommendation System |
| Authors | Biswarup Bhattacharya, Iftikhar Burhanuddin, Abhilasha Sancheti, Kushal Satya |
| Abstract | Recommender systems take inputs from user history, use an internal ranking algorithm to generate results and possibly optimize this ranking based on feedback. However, often the recommender system is unaware of the actual intent of the user and simply provides recommendations dynamically without properly understanding the thought process of the user. An intelligent recommender system is not only useful for the user but also for businesses which want to learn the tendencies of their users. Finding out tendencies or intents of a user is a difficult problem to solve. Keeping this in mind, we sought out to create an intelligent system which will keep track of the user’s activity on a web-application as well as determine the intent of the user in each session. We devised a way to encode the user’s activity through the sessions. Then, we have represented the information seen by the user in a high dimensional format which is reduced to lower dimensions using tensor factorization techniques. The aspect of intent awareness (or scoring) is dealt with at this stage. Finally, combining the user activity data with the contextual information gives the recommendation score. The final recommendations are then ranked using filtering and collaborative recommendation techniques to show the top-k recommendations to the user. A provision for feedback is also envisioned in the current system which informs the model to update the various weights in the recommender system. Our overall model aims to combine both frequency-based and context-based recommendation systems and quantify the intent of a user to provide better recommendations. We ran experiments on real-world timestamped user activity data, in the setting of recommending reports to the users of a business analytics tool and the results are better than the baselines. We also tuned certain aspects of our model to arrive at optimized results. |
| Tasks | Recommendation Systems |
| Published | 2017-11-28 |
| URL | http://arxiv.org/abs/1711.10558v1 |
| http://arxiv.org/pdf/1711.10558v1.pdf | |
| PWC | https://paperswithcode.com/paper/intent-aware-contextual-recommendation-system |
| Repo | |
| Framework | |
Secrets in Computing Optical Flow by Convolutional Networks
| Title | Secrets in Computing Optical Flow by Convolutional Networks |
| Authors | Junxuan Li |
| Abstract | Convolutional neural networks (CNNs) have been widely used over many areas in compute vision. Especially in classification. Recently, FlowNet and several works on opti- cal estimation using CNNs shows the potential ability of CNNs in doing per-pixel regression. We proposed several CNNs network architectures that can estimate optical flow, and fully unveiled the intrinsic different between these structures. |
| Tasks | Optical Flow Estimation |
| Published | 2017-10-04 |
| URL | http://arxiv.org/abs/1710.01462v1 |
| http://arxiv.org/pdf/1710.01462v1.pdf | |
| PWC | https://paperswithcode.com/paper/secrets-in-computing-optical-flow-by |
| Repo | |
| Framework | |
A concatenating framework of shortcut convolutional neural networks
| Title | A concatenating framework of shortcut convolutional neural networks |
| Authors | Yujian Li, Ting Zhang, Zhaoying Liu, Haihe Hu |
| Abstract | It is well accepted that convolutional neural networks play an important role in learning excellent features for image classification and recognition. However, in tradition they only allow adjacent layers connected, limiting integration of multi-scale information. To further improve their performance, we present a concatenating framework of shortcut convolutional neural networks. This framework can concatenate multi-scale features by shortcut connections to the fully-connected layer that is directly fed to the output layer. We do a large number of experiments to investigate performance of the shortcut convolutional neural networks on many benchmark visual datasets for different tasks. The datasets include AR, FERET, FaceScrub, CelebA for gender classification, CUReT for texture classification, MNIST for digit recognition, and CIFAR-10 for object recognition. Experimental results show that the shortcut convolutional neural networks can achieve better results than the traditional ones on these tasks, with more stability in different settings of pooling schemes, activation functions, optimizations, initializations, kernel numbers and kernel sizes. |
| Tasks | Image Classification, Object Recognition, Texture Classification |
| Published | 2017-10-03 |
| URL | http://arxiv.org/abs/1710.00974v1 |
| http://arxiv.org/pdf/1710.00974v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-concatenating-framework-of-shortcut |
| Repo | |
| Framework | |
Automatic Renal Segmentation in DCE-MRI using Convolutional Neural Networks
| Title | Automatic Renal Segmentation in DCE-MRI using Convolutional Neural Networks |
| Authors | Marzieh Haghighi, Simon K. Warfield, Sila Kurugol |
| Abstract | Kidney function evaluation using dynamic contrast-enhanced MRI (DCE-MRI) images could help in diagnosis and treatment of kidney diseases of children. Automatic segmentation of renal parenchyma is an important step in this process. In this paper, we propose a time and memory efficient fully automated segmentation method which achieves high segmentation accuracy with running time in the order of seconds in both normal kidneys and kidneys with hydronephrosis. The proposed method is based on a cascaded application of two 3D convolutional neural networks that employs spatial and temporal information at the same time in order to learn the tasks of localization and segmentation of kidneys, respectively. Segmentation performance is evaluated on both normal and abnormal kidneys with varying levels of hydronephrosis. We achieved a mean dice coefficient of 91.4 and 83.6 for normal and abnormal kidneys of pediatric patients, respectively. |
| Tasks | |
| Published | 2017-12-19 |
| URL | http://arxiv.org/abs/1712.07022v1 |
| http://arxiv.org/pdf/1712.07022v1.pdf | |
| PWC | https://paperswithcode.com/paper/automatic-renal-segmentation-in-dce-mri-using |
| Repo | |
| Framework | |
