Paper Group ANR 635
SocialML: machine learning for social media video creators. Rotational 3D Texture Classification Using Group Equivariant CNNs. An Efficient Data Retrieval Parallel Reeb Graph Algorithm. Tight Bayesian Ambiguity Sets for Robust MDPs. ABC Samplers. Active Learning for Deep Object Detection. Semantic bottleneck for computer vision tasks. Multi-layer R …
SocialML: machine learning for social media video creators
| Title | SocialML: machine learning for social media video creators |
| Authors | Tomasz Trzcinski, Adam Bielski, Paweł Cyrta, Matthew Zak |
| Abstract | In the recent years, social media have become one of the main places where creative content is being published and consumed by billions of users. Contrary to traditional media, social media allow the publishers to receive almost instantaneous feedback regarding their creative work at an unprecedented scale. This is a perfect use case for machine learning methods that can use these massive amounts of data to provide content creators with inspirational ideas and constructive criticism of their work. In this work, we present a comprehensive overview of machine learning-empowered tools we developed for video creators at Group Nine Media - one of the major social media companies that creates short-form videos with over three billion views per month. Our main contribution is a set of tools that allow the creators to leverage massive amounts of data to improve their creation process, evaluate their videos before the publication and improve content quality. These applications include an interactive conversational bot that allows access to material archives, a Web-based application for automatic selection of optimal video thumbnail, as well as deep learning methods for optimizing headline and predicting video popularity. Our A/B tests show that deployment of our tools leads to significant increase of average video view count by 12.9%. Our additional contribution is a set of considerations collected during the deployment of those tools that can hel |
| Tasks | |
| Published | 2018-01-25 |
| URL | http://arxiv.org/abs/1802.02204v1 |
| http://arxiv.org/pdf/1802.02204v1.pdf | |
| PWC | https://paperswithcode.com/paper/socialml-machine-learning-for-social-media |
| Repo | |
| Framework | |
Rotational 3D Texture Classification Using Group Equivariant CNNs
| Title | Rotational 3D Texture Classification Using Group Equivariant CNNs |
| Authors | Vincent Andrearczyk, Adrien Depeursinge |
| Abstract | Convolutional Neural Networks (CNNs) traditionally encode translation equivariance via the convolution operation. Generalization to other transformations has recently received attraction to encode the knowledge of the data geometry in group convolution operations. Equivariance to rotation is particularly important for 3D image analysis due to the large diversity of possible pattern orientations. 3D texture is a particularly important cue for the analysis of medical images such as CT and MRI scans as it describes different types of tissues and lesions. In this paper, we evaluate the use of 3D group equivariant CNNs accounting for the simplified group of right-angle rotations to classify 3D synthetic textures from a publicly available dataset. The results validate the importance of rotation equivariance in a controlled setup and yet motivate the use of a finer coverage of orientations in order to obtain equivariance to realistic rotations present in 3D textures. |
| Tasks | Texture Classification |
| Published | 2018-10-16 |
| URL | http://arxiv.org/abs/1810.06889v1 |
| http://arxiv.org/pdf/1810.06889v1.pdf | |
| PWC | https://paperswithcode.com/paper/rotational-3d-texture-classification-using |
| Repo | |
| Framework | |
An Efficient Data Retrieval Parallel Reeb Graph Algorithm
| Title | An Efficient Data Retrieval Parallel Reeb Graph Algorithm |
| Authors | Mustafa Hajij, Paul Rosen |
| Abstract | The Reeb graph of a scalar function defined on a domain gives a topological meaningful summary of that domain. Reeb graphs have been shown in the past decade to be of great importance in geometric processing, image processing, computer graphics and computational topology. The demand to compute large data sets has increased in the last decade and hence the consideration of parallelization of topological computations. We propose a parallel Reeb graph algorithm on triangulated meshes with and without a boundary. Furthermore, we give a description for extracting the original manifold data from the Reeb graph structure. As an application, we show how our algorithm can be utilized in mesh segmentation algorithms. |
| Tasks | |
| Published | 2018-10-18 |
| URL | https://arxiv.org/abs/1810.08310v2 |
| https://arxiv.org/pdf/1810.08310v2.pdf | |
| PWC | https://paperswithcode.com/paper/an-efficient-data-retrieval-parallel-reeb |
| Repo | |
| Framework | |
Tight Bayesian Ambiguity Sets for Robust MDPs
| Title | Tight Bayesian Ambiguity Sets for Robust MDPs |
| Authors | Reazul Hasan Russel, Marek Petrik |
| Abstract | Robustness is important for sequential decision making in a stochastic dynamic environment with uncertain probabilistic parameters. We address the problem of using robust MDPs (RMDPs) to compute policies with provable worst-case guarantees in reinforcement learning. The quality and robustness of an RMDP solution is determined by its ambiguity set. Existing methods construct ambiguity sets that lead to impractically conservative solutions. In this paper, we propose RSVF, which achieves less conservative solutions with the same worst-case guarantees by 1) leveraging a Bayesian prior, 2) optimizing the size and location of the ambiguity set, and, most importantly, 3) relaxing the requirement that the set is a confidence interval. Our theoretical analysis shows the safety of RSVF, and the empirical results demonstrate its practical promise. |
| Tasks | Decision Making |
| Published | 2018-11-15 |
| URL | http://arxiv.org/abs/1811.06512v1 |
| http://arxiv.org/pdf/1811.06512v1.pdf | |
| PWC | https://paperswithcode.com/paper/tight-bayesian-ambiguity-sets-for-robust-mdps |
| Repo | |
| Framework | |
ABC Samplers
| Title | ABC Samplers |
| Authors | Y. Fan, S. A. Sisson |
| Abstract | This Chapter, “ABC Samplers”, is to appear in the forthcoming Handbook of Approximate Bayesian Computation (2018). It details the main ideas and algorithms used to sample from the ABC approximation to the posterior distribution, including methods based on rejection/importance sampling, MCMC and sequential Monte Carlo. |
| Tasks | |
| Published | 2018-02-26 |
| URL | http://arxiv.org/abs/1802.09650v1 |
| http://arxiv.org/pdf/1802.09650v1.pdf | |
| PWC | https://paperswithcode.com/paper/abc-samplers |
| Repo | |
| Framework | |
Active Learning for Deep Object Detection
| Title | Active Learning for Deep Object Detection |
| Authors | Clemens-Alexander Brust, Christoph Käding, Joachim Denzler |
| Abstract | The great success that deep models have achieved in the past is mainly owed to large amounts of labeled training data. However, the acquisition of labeled data for new tasks aside from existing benchmarks is both challenging and costly. Active learning can make the process of labeling new data more efficient by selecting unlabeled samples which, when labeled, are expected to improve the model the most. In this paper, we combine a novel method of active learning for object detection with an incremental learning scheme to enable continuous exploration of new unlabeled datasets. We propose a set of uncertainty-based active learning metrics suitable for most object detectors. Furthermore, we present an approach to leverage class imbalances during sample selection. All methods are evaluated systematically in a continuous exploration context on the PASCAL VOC 2012 dataset. |
| Tasks | Active Learning, Object Detection |
| Published | 2018-09-26 |
| URL | http://arxiv.org/abs/1809.09875v1 |
| http://arxiv.org/pdf/1809.09875v1.pdf | |
| PWC | https://paperswithcode.com/paper/active-learning-for-deep-object-detection |
| Repo | |
| Framework | |
Semantic bottleneck for computer vision tasks
| Title | Semantic bottleneck for computer vision tasks |
| Authors | Maxime Bucher, Stéphane Herbin, Frédéric Jurie |
| Abstract | This paper introduces a novel method for the representation of images that is semantic by nature, addressing the question of computation intelligibility in computer vision tasks. More specifically, our proposition is to introduce what we call a semantic bottleneck in the processing pipeline, which is a crossing point in which the representation of the image is entirely expressed with natural language , while retaining the efficiency of numerical representations. We show that our approach is able to generate semantic representations that give state-of-the-art results on semantic content-based image retrieval and also perform very well on image classification tasks. Intelligibility is evaluated through user centered experiments for failure detection. |
| Tasks | Content-Based Image Retrieval, Image Classification, Image Retrieval |
| Published | 2018-11-06 |
| URL | http://arxiv.org/abs/1811.02234v1 |
| http://arxiv.org/pdf/1811.02234v1.pdf | |
| PWC | https://paperswithcode.com/paper/semantic-bottleneck-for-computer-vision-tasks |
| Repo | |
| Framework | |
Multi-layer Relation Networks
| Title | Multi-layer Relation Networks |
| Authors | Marius Jahrens, Thomas Martinetz |
| Abstract | Relational Networks (RN) as introduced by Santoro et al. (2017) have demonstrated strong relational reasoning capabilities with a rather shallow architecture. Its single-layer design, however, only considers pairs of information objects, making it unsuitable for problems requiring reasoning across a higher number of facts. To overcome this limitation, we propose a multi-layer relation network architecture which enables successive refinements of relational information through multiple layers. We show that the increased depth allows for more complex relational reasoning by applying it to the bAbI 20 QA dataset, solving all 20 tasks with joint training and surpassing the state-of-the-art results. |
| Tasks | Relational Reasoning |
| Published | 2018-11-05 |
| URL | http://arxiv.org/abs/1811.01838v1 |
| http://arxiv.org/pdf/1811.01838v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-layer-relation-networks |
| Repo | |
| Framework | |
Proceedings of the 2018 XCSP3 Competition
| Title | Proceedings of the 2018 XCSP3 Competition |
| Authors | Christophe Lecoutre, Olivier Roussel |
| Abstract | This document represents the proceedings of the 2018 XCSP3 Competition. The results of this competition of constraint solvers were presented at CP’18, the 24th International Conference on Principles and Practice of Constraint Programming, held in Lille, France from 27th August 2018 to 31th August, 2018. |
| Tasks | |
| Published | 2018-12-17 |
| URL | http://arxiv.org/abs/1901.01830v1 |
| http://arxiv.org/pdf/1901.01830v1.pdf | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-2018-xcsp3-competition |
| Repo | |
| Framework | |
Discovery of Driving Patterns by Trajectory Segmentation
| Title | Discovery of Driving Patterns by Trajectory Segmentation |
| Authors | Sobhan Moosavi, Arnab Nandi, Rajiv Ramnath |
| Abstract | Telematics data is becoming increasingly available due to the ubiquity of devices that collect data during drives, for different purposes, such as usage based insurance (UBI), fleet management, navigation of connected vehicles, etc. Consequently, a variety of data-analytic applications have become feasible that extract valuable insights from the data. In this paper, we address the especially challenging problem of discovering behavior-based driving patterns from only externally observable phenomena (e.g. vehicle’s speed). We present a trajectory segmentation approach capable of discovering driving patterns as separate segments, based on the behavior of drivers. This segmentation approach includes a novel transformation of trajectories along with a dynamic programming approach for segmentation. We apply the segmentation approach on a real-word, rich dataset of personal car trajectories provided by a major insurance company based in Columbus, Ohio. Analysis and preliminary results show the applicability of approach for finding significant driving patterns. |
| Tasks | |
| Published | 2018-04-23 |
| URL | http://arxiv.org/abs/1804.08748v1 |
| http://arxiv.org/pdf/1804.08748v1.pdf | |
| PWC | https://paperswithcode.com/paper/discovery-of-driving-patterns-by-trajectory |
| Repo | |
| Framework | |
A Continuous, Full-scope, Spatio-temporal Tracking Metric based on KL-divergence
| Title | A Continuous, Full-scope, Spatio-temporal Tracking Metric based on KL-divergence |
| Authors | Terrence Adams |
| Abstract | A unified metric is given for the evaluation of object tracking systems. The metric is inspired by KL-divergence or relative entropy, which is commonly used to evaluate clustering techniques. Since tracking problems are fundamentally different from clustering, the components of KL-divergence are recast to handle various types of tracking errors (i.e., false alarms, missed detections, merges, splits). Scoring results are given on a standard tracking dataset (Oxford Town Centre Dataset), as well as several simulated scenarios. Also, this new metric is compared with several other metrics including the commonly used Multiple Object Tracking Accuracy metric. In the final section, advantages of this metric are given including the fact that it is continuous, parameter-less and comprehensive. |
| Tasks | Multiple Object Tracking, Object Tracking |
| Published | 2018-05-09 |
| URL | http://arxiv.org/abs/1805.03707v3 |
| http://arxiv.org/pdf/1805.03707v3.pdf | |
| PWC | https://paperswithcode.com/paper/a-continuous-full-scope-spatio-temporal |
| Repo | |
| Framework | |
The Unmanned Aerial Vehicle Benchmark: Object Detection and Tracking
| Title | The Unmanned Aerial Vehicle Benchmark: Object Detection and Tracking |
| Authors | Dawei Du, Yuankai Qi, Hongyang Yu, Yifan Yang, Kaiwen Duan, Guorong Li, Weigang Zhang, Qingming Huang, Qi Tian |
| Abstract | With the advantage of high mobility, Unmanned Aerial Vehicles (UAVs) are used to fuel numerous important applications in computer vision, delivering more efficiency and convenience than surveillance cameras with fixed camera angle, scale and view. However, very limited UAV datasets are proposed, and they focus only on a specific task such as visual tracking or object detection in relatively constrained scenarios. Consequently, it is of great importance to develop an unconstrained UAV benchmark to boost related researches. In this paper, we construct a new UAV benchmark focusing on complex scenarios with new level challenges. Selected from 10 hours raw videos, about 80,000 representative frames are fully annotated with bounding boxes as well as up to 14 kinds of attributes (e.g., weather condition, flying altitude, camera view, vehicle category, and occlusion) for three fundamental computer vision tasks: object detection, single object tracking, and multiple object tracking. Then, a detailed quantitative study is performed using most recent state-of-the-art algorithms for each task. Experimental results show that the current state-of-the-art methods perform relative worse on our dataset, due to the new challenges appeared in UAV based real scenes, e.g., high density, small object, and camera motion. To our knowledge, our work is the first time to explore such issues in unconstrained scenes comprehensively. |
| Tasks | Multiple Object Tracking, Object Detection, Object Tracking, Visual Tracking |
| Published | 2018-03-26 |
| URL | http://arxiv.org/abs/1804.00518v1 |
| http://arxiv.org/pdf/1804.00518v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-unmanned-aerial-vehicle-benchmark-object |
| Repo | |
| Framework | |
Know What Your Neighbors Do: 3D Semantic Segmentation of Point Clouds
| Title | Know What Your Neighbors Do: 3D Semantic Segmentation of Point Clouds |
| Authors | Francis Engelmann, Theodora Kontogianni, Jonas Schult, Bastian Leibe |
| Abstract | In this paper, we present a deep learning architecture which addresses the problem of 3D semantic segmentation of unstructured point clouds. Compared to previous work, we introduce grouping techniques which define point neighborhoods in the initial world space and the learned feature space. Neighborhoods are important as they allow to compute local or global point features depending on the spatial extend of the neighborhood. Additionally, we incorporate dedicated loss functions to further structure the learned point feature space: the pairwise distance loss and the centroid loss. We show how to apply these mechanisms to the task of 3D semantic segmentation of point clouds and report state-of-the-art performance on indoor and outdoor datasets. |
| Tasks | 3D Semantic Segmentation, Semantic Segmentation |
| Published | 2018-10-02 |
| URL | http://arxiv.org/abs/1810.01151v2 |
| http://arxiv.org/pdf/1810.01151v2.pdf | |
| PWC | https://paperswithcode.com/paper/know-what-your-neighbors-do-3d-semantic |
| Repo | |
| Framework | |
Semi-supervised Deep Representation Learning for Multi-View Problems
| Title | Semi-supervised Deep Representation Learning for Multi-View Problems |
| Authors | Vahid Noroozi, Sara Bahaadini, Lei Zheng, Sihong Xie, Weixiang Shao, Philip S. Yu |
| Abstract | While neural networks for learning representation of multi-view data have been previously proposed as one of the state-of-the-art multi-view dimension reduction techniques, how to make the representation discriminative with only a small amount of labeled data is not well-studied. We introduce a semi-supervised neural network model, named Multi-view Discriminative Neural Network (MDNN), for multi-view problems. MDNN finds nonlinear view-specific mappings by projecting samples to a common feature space using multiple coupled deep networks. It is capable of leveraging both labeled and unlabeled data to project multi-view data so that samples from different classes are separated and those from the same class are clustered together. It also uses the inter-view correlation between views to exploit the available information in both the labeled and unlabeled data. Extensive experiments conducted on four datasets demonstrate the effectiveness of the proposed algorithm for multi-view semi-supervised learning. |
| Tasks | Dimensionality Reduction, Learning Representation Of Multi-View Data, Representation Learning |
| Published | 2018-11-11 |
| URL | http://arxiv.org/abs/1811.04480v1 |
| http://arxiv.org/pdf/1811.04480v1.pdf | |
| PWC | https://paperswithcode.com/paper/semi-supervised-deep-representation-learning |
| Repo | |
| Framework | |
Adversarial Examples - A Complete Characterisation of the Phenomenon
| Title | Adversarial Examples - A Complete Characterisation of the Phenomenon |
| Authors | Alexandru Constantin Serban, Erik Poll, Joost Visser |
| Abstract | We provide a complete characterisation of the phenomenon of adversarial examples - inputs intentionally crafted to fool machine learning models. We aim to cover all the important concerns in this field of study: (1) the conjectures on the existence of adversarial examples, (2) the security, safety and robustness implications, (3) the methods used to generate and (4) protect against adversarial examples and (5) the ability of adversarial examples to transfer between different machine learning models. We provide ample background information in an effort to make this document self-contained. Therefore, this document can be used as survey, tutorial or as a catalog of attacks and defences using adversarial examples. |
| Tasks | |
| Published | 2018-10-02 |
| URL | http://arxiv.org/abs/1810.01185v2 |
| http://arxiv.org/pdf/1810.01185v2.pdf | |
| PWC | https://paperswithcode.com/paper/adversarial-examples-a-complete |
| Repo | |
| Framework | |
