Paper Group ANR 24
An Expectation Maximization Framework for Yule-Simon Preferential Attachment Models. Original Loop-closure Detection Algorithm for Monocular vSLAM. Extract with Order for Coherent Multi-Document Summarization. Deep 360 Pilot: Learning a Deep Agent for Piloting through 360° Sports Video. A Parallelizable Acceleration Framework for Packing Linear Pro …
An Expectation Maximization Framework for Yule-Simon Preferential Attachment Models
| Title | An Expectation Maximization Framework for Yule-Simon Preferential Attachment Models |
| Authors | Lucas Roberts, Denisa Roberts |
| Abstract | In this paper we develop an Expectation Maximization(EM) algorithm to estimate the parameter of a Yule-Simon distribution. The Yule-Simon distribution exhibits the “rich get richer” effect whereby an 80-20 type of rule tends to dominate. These distributions are ubiquitous in industrial settings. The EM algorithm presented provides both frequentist and Bayesian estimates of the $\lambda$ parameter. By placing the estimation method within the EM framework we are able to derive Standard errors of the resulting estimate. Additionally, we prove convergence of the Yule-Simon EM algorithm and study the rate of convergence. An explicit, closed form solution for the rate of convergence of the algorithm is given. |
| Tasks | |
| Published | 2017-10-23 |
| URL | http://arxiv.org/abs/1710.08511v3 |
| http://arxiv.org/pdf/1710.08511v3.pdf | |
| PWC | https://paperswithcode.com/paper/an-expectation-maximization-framework-for |
| Repo | |
| Framework | |
Original Loop-closure Detection Algorithm for Monocular vSLAM
| Title | Original Loop-closure Detection Algorithm for Monocular vSLAM |
| Authors | Andrey Bokovoy, Konstantin Yakovlev |
| Abstract | Vision-based simultaneous localization and mapping (vSLAM) is a well-established problem in mobile robotics and monocular vSLAM is one of the most challenging variations of that problem nowadays. In this work we study one of the core post-processing optimization mechanisms in vSLAM, e.g. loop-closure detection. We analyze the existing methods and propose original algorithm for loop-closure detection, which is suitable for dense, semi-dense and feature-based vSLAM methods. We evaluate the algorithm experimentally and show that it contribute to more accurate mapping while speeding up the monocular vSLAM pipeline to the extent the latter can be used in real-time for controlling small multi-rotor vehicle (drone). |
| Tasks | Loop Closure Detection, Simultaneous Localization and Mapping |
| Published | 2017-07-15 |
| URL | http://arxiv.org/abs/1707.04771v1 |
| http://arxiv.org/pdf/1707.04771v1.pdf | |
| PWC | https://paperswithcode.com/paper/original-loop-closure-detection-algorithm-for |
| Repo | |
| Framework | |
Extract with Order for Coherent Multi-Document Summarization
| Title | Extract with Order for Coherent Multi-Document Summarization |
| Authors | Mir Tafseer Nayeem, Yllias Chali |
| Abstract | In this work, we aim at developing an extractive summarizer in the multi-document setting. We implement a rank based sentence selection using continuous vector representations along with key-phrases. Furthermore, we propose a model to tackle summary coherence for increasing readability. We conduct experiments on the Document Understanding Conference (DUC) 2004 datasets using ROUGE toolkit. Our experiments demonstrate that the methods bring significant improvements over the state of the art methods in terms of informativity and coherence. |
| Tasks | Document Summarization, Multi-Document Summarization |
| Published | 2017-06-12 |
| URL | http://arxiv.org/abs/1706.06542v1 |
| http://arxiv.org/pdf/1706.06542v1.pdf | |
| PWC | https://paperswithcode.com/paper/extract-with-order-for-coherent-multi |
| Repo | |
| Framework | |
Deep 360 Pilot: Learning a Deep Agent for Piloting through 360° Sports Video
| Title | Deep 360 Pilot: Learning a Deep Agent for Piloting through 360° Sports Video |
| Authors | Hou-Ning Hu, Yen-Chen Lin, Ming-Yu Liu, Hsien-Tzu Cheng, Yung-Ju Chang, Min Sun |
| Abstract | Watching a 360{\deg} sports video requires a viewer to continuously select a viewing angle, either through a sequence of mouse clicks or head movements. To relieve the viewer from this “360 piloting” task, we propose “deep 360 pilot” – a deep learning-based agent for piloting through 360{\deg} sports videos automatically. At each frame, the agent observes a panoramic image and has the knowledge of previously selected viewing angles. The task of the agent is to shift the current viewing angle (i.e. action) to the next preferred one (i.e., goal). We propose to directly learn an online policy of the agent from data. We use the policy gradient technique to jointly train our pipeline: by minimizing (1) a regression loss measuring the distance between the selected and ground truth viewing angles, (2) a smoothness loss encouraging smooth transition in viewing angle, and (3) maximizing an expected reward of focusing on a foreground object. To evaluate our method, we build a new 360-Sports video dataset consisting of five sports domains. We train domain-specific agents and achieve the best performance on viewing angle selection accuracy and transition smoothness compared to [51] and other baselines. |
| Tasks | |
| Published | 2017-05-04 |
| URL | http://arxiv.org/abs/1705.01759v1 |
| http://arxiv.org/pdf/1705.01759v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-360-pilot-learning-a-deep-agent-for |
| Repo | |
| Framework | |
A Parallelizable Acceleration Framework for Packing Linear Programs
| Title | A Parallelizable Acceleration Framework for Packing Linear Programs |
| Authors | Palma London, Shai Vardi, Adam Wierman, Hanling Yi |
| Abstract | This paper presents an acceleration framework for packing linear programming problems where the amount of data available is limited, i.e., where the number of constraints m is small compared to the variable dimension n. The framework can be used as a black box to speed up linear programming solvers dramatically, by two orders of magnitude in our experiments. We present worst-case guarantees on the quality of the solution and the speedup provided by the algorithm, showing that the framework provides an approximately optimal solution while running the original solver on a much smaller problem. The framework can be used to accelerate exact solvers, approximate solvers, and parallel/distributed solvers. Further, it can be used for both linear programs and integer linear programs. |
| Tasks | |
| Published | 2017-11-17 |
| URL | http://arxiv.org/abs/1711.06656v1 |
| http://arxiv.org/pdf/1711.06656v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-parallelizable-acceleration-framework-for |
| Repo | |
| Framework | |
Single-Shot Object Detection with Enriched Semantics
| Title | Single-Shot Object Detection with Enriched Semantics |
| Authors | Zhishuai Zhang, Siyuan Qiao, Cihang Xie, Wei Shen, Bo Wang, Alan L. Yuille |
| Abstract | We propose a novel single shot object detection network named Detection with Enriched Semantics (DES). Our motivation is to enrich the semantics of object detection features within a typical deep detector, by a semantic segmentation branch and a global activation module. The segmentation branch is supervised by weak segmentation ground-truth, i.e., no extra annotation is required. In conjunction with that, we employ a global activation module which learns relationship between channels and object classes in a self-supervised manner. Comprehensive experimental results on both PASCAL VOC and MS COCO detection datasets demonstrate the effectiveness of the proposed method. In particular, with a VGG16 based DES, we achieve an mAP of 81.7 on VOC2007 test and an mAP of 32.8 on COCO test-dev with an inference speed of 31.5 milliseconds per image on a Titan Xp GPU. With a lower resolution version, we achieve an mAP of 79.7 on VOC2007 with an inference speed of 13.0 milliseconds per image. |
| Tasks | Object Detection, Semantic Segmentation |
| Published | 2017-12-01 |
| URL | http://arxiv.org/abs/1712.00433v2 |
| http://arxiv.org/pdf/1712.00433v2.pdf | |
| PWC | https://paperswithcode.com/paper/single-shot-object-detection-with-enriched |
| Repo | |
| Framework | |
Complex and Holographic Embeddings of Knowledge Graphs: A Comparison
| Title | Complex and Holographic Embeddings of Knowledge Graphs: A Comparison |
| Authors | Théo Trouillon, Maximilian Nickel |
| Abstract | Embeddings of knowledge graphs have received significant attention due to their excellent performance for tasks like link prediction and entity resolution. In this short paper, we are providing a comparison of two state-of-the-art knowledge graph embeddings for which their equivalence has recently been established, i.e., ComplEx and HolE [Nickel, Rosasco, and Poggio, 2016; Trouillon et al., 2016; Hayashi and Shimbo, 2017]. First, we briefly review both models and discuss how their scoring functions are equivalent. We then analyze the discrepancy of results reported in the original articles, and show experimentally that they are likely due to the use of different loss functions. In further experiments, we evaluate the ability of both models to embed symmetric and antisymmetric patterns. Finally, we discuss advantages and disadvantages of both models and under which conditions one would be preferable to the other. |
| Tasks | Entity Resolution, Knowledge Graph Embeddings, Knowledge Graphs, Link Prediction |
| Published | 2017-07-05 |
| URL | http://arxiv.org/abs/1707.01475v2 |
| http://arxiv.org/pdf/1707.01475v2.pdf | |
| PWC | https://paperswithcode.com/paper/complex-and-holographic-embeddings-of |
| Repo | |
| Framework | |
Context-Aware Generative Adversarial Privacy
| Title | Context-Aware Generative Adversarial Privacy |
| Authors | Chong Huang, Peter Kairouz, Xiao Chen, Lalitha Sankar, Ram Rajagopal |
| Abstract | Preserving the utility of published datasets while simultaneously providing provable privacy guarantees is a well-known challenge. On the one hand, context-free privacy solutions, such as differential privacy, provide strong privacy guarantees, but often lead to a significant reduction in utility. On the other hand, context-aware privacy solutions, such as information theoretic privacy, achieve an improved privacy-utility tradeoff, but assume that the data holder has access to dataset statistics. We circumvent these limitations by introducing a novel context-aware privacy framework called generative adversarial privacy (GAP). GAP leverages recent advancements in generative adversarial networks (GANs) to allow the data holder to learn privatization schemes from the dataset itself. Under GAP, learning the privacy mechanism is formulated as a constrained minimax game between two players: a privatizer that sanitizes the dataset in a way that limits the risk of inference attacks on the individuals’ private variables, and an adversary that tries to infer the private variables from the sanitized dataset. To evaluate GAP’s performance, we investigate two simple (yet canonical) statistical dataset models: (a) the binary data model, and (b) the binary Gaussian mixture model. For both models, we derive game-theoretically optimal minimax privacy mechanisms, and show that the privacy mechanisms learned from data (in a generative adversarial fashion) match the theoretically optimal ones. This demonstrates that our framework can be easily applied in practice, even in the absence of dataset statistics. |
| Tasks | |
| Published | 2017-10-26 |
| URL | http://arxiv.org/abs/1710.09549v3 |
| http://arxiv.org/pdf/1710.09549v3.pdf | |
| PWC | https://paperswithcode.com/paper/context-aware-generative-adversarial-privacy |
| Repo | |
| Framework | |
Am I Done? Predicting Action Progress in Videos
| Title | Am I Done? Predicting Action Progress in Videos |
| Authors | Federico Becattini, Tiberio Uricchio, Lorenzo Seidenari, Lamberto Ballan, Alberto Del Bimbo |
| Abstract | In this paper we deal with the problem of predicting action progress in videos. We argue that this is an extremely important task since it can be valuable for a wide range of interaction applications. To this end we introduce a novel approach, named ProgressNet, capable of predicting when an action takes place in a video, where it is located within the frames, and how far it has progressed during its execution. To provide a general definition of action progress, we ground our work in the linguistics literature, borrowing terms and concepts to understand which actions can be the subject of progress estimation. As a result, we define a categorization of actions and their phases. Motivated by the recent success obtained from the interaction of Convolutional and Recurrent Neural Networks, our model is based on a combination of the Faster R-CNN framework, to make frame-wise predictions, and LSTM networks, to estimate action progress through time. After introducing two evaluation protocols for the task at hand, we demonstrate the capability of our model to effectively predict action progress on the UCF-101 and J-HMDB datasets. |
| Tasks | Action Detection, Temporal Localization |
| Published | 2017-05-04 |
| URL | https://arxiv.org/abs/1705.01781v4 |
| https://arxiv.org/pdf/1705.01781v4.pdf | |
| PWC | https://paperswithcode.com/paper/am-i-done-predicting-action-progress-in |
| Repo | |
| Framework | |
Verification of Binarized Neural Networks via Inter-Neuron Factoring
| Title | Verification of Binarized Neural Networks via Inter-Neuron Factoring |
| Authors | Chih-Hong Cheng, Georg Nührenberg, Chung-Hao Huang, Harald Ruess |
| Abstract | We study the problem of formal verification of Binarized Neural Networks (BNN), which have recently been proposed as a energy-efficient alternative to traditional learning networks. The verification of BNNs, using the reduction to hardware verification, can be even more scalable by factoring computations among neurons within the same layer. By proving the NP-hardness of finding optimal factoring as well as the hardness of PTAS approximability, we design polynomial-time search heuristics to generate factoring solutions. The overall framework allows applying verification techniques to moderately-sized BNNs for embedded devices with thousands of neurons and inputs. |
| Tasks | |
| Published | 2017-10-09 |
| URL | http://arxiv.org/abs/1710.03107v2 |
| http://arxiv.org/pdf/1710.03107v2.pdf | |
| PWC | https://paperswithcode.com/paper/verification-of-binarized-neural-networks-via |
| Repo | |
| Framework | |
Generative OpenMax for Multi-Class Open Set Classification
| Title | Generative OpenMax for Multi-Class Open Set Classification |
| Authors | ZongYuan Ge, Sergey Demyanov, Zetao Chen, Rahil Garnavi |
| Abstract | We present a conceptually new and flexible method for multi-class open set classification. Unlike previous methods where unknown classes are inferred with respect to the feature or decision distance to the known classes, our approach is able to provide explicit modelling and decision score for unknown classes. The proposed method, called Gener- ative OpenMax (G-OpenMax), extends OpenMax by employing generative adversarial networks (GANs) for novel category image synthesis. We validate the proposed method on two datasets of handwritten digits and characters, resulting in superior results over previous deep learning based method OpenMax Moreover, G-OpenMax provides a way to visualize samples representing the unknown classes from open space. Our simple and effective approach could serve as a new direction to tackle the challenging multi-class open set classification problem. |
| Tasks | Image Generation |
| Published | 2017-07-24 |
| URL | http://arxiv.org/abs/1707.07418v1 |
| http://arxiv.org/pdf/1707.07418v1.pdf | |
| PWC | https://paperswithcode.com/paper/generative-openmax-for-multi-class-open-set |
| Repo | |
| Framework | |
The Generalized Cross Validation Filter
| Title | The Generalized Cross Validation Filter |
| Authors | Giulio Bottegal, Gianluigi Pillonetto |
| Abstract | Generalized cross validation (GCV) is one of the most important approaches used to estimate parameters in the context of inverse problems and regularization techniques. A notable example is the determination of the smoothness parameter in splines. When the data are generated by a state space model, like in the spline case, efficient algorithms are available to evaluate the GCV score with complexity that scales linearly in the data set size. However, these methods are not amenable to on-line applications since they rely on forward and backward recursions. Hence, if the objective has been evaluated at time $t-1$ and new data arrive at time t, then O(t) operations are needed to update the GCV score. In this paper we instead show that the update cost is $O(1)$, thus paving the way to the on-line use of GCV. This result is obtained by deriving the novel GCV filter which extends the classical Kalman filter equations to efficiently propagate the GCV score over time. We also illustrate applications of the new filter in the context of state estimation and on-line regularized linear system identification. |
| Tasks | |
| Published | 2017-06-08 |
| URL | http://arxiv.org/abs/1706.02495v1 |
| http://arxiv.org/pdf/1706.02495v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-generalized-cross-validation-filter |
| Repo | |
| Framework | |
Number game
| Title | Number game |
| Authors | Go Sugimoto |
| Abstract | CLARIN (Common Language Resources and Technology Infrastructure) is regarded as one of the most important European research infrastructures, offering and promoting a wide array of useful services for (digital) research in linguistics and humanities. However, the assessment of the users for its core technical development has been highly limited, therefore, it is unclear if the community is thoroughly aware of the status-quo of the growing infrastructure. In addition, CLARIN does not seem to be fully materialised marketing and business plans and strategies despite its strong technical assets. This article analyses the web traffic of the Virtual Language Observatory, one of the main web applications of CLARIN and a symbol of pan-European re-search cooperation, to evaluate the users and performance of the service in a transparent and scientific way. It is envisaged that the paper can raise awareness of the pressing issues on objective and transparent operation of the infrastructure though Open Evaluation, and the synergy between marketing and technical development. It also investigates the “science of web analytics” in an attempt to document the research process for the purpose of reusability and reproducibility, thus to find universal lessons for the use of a web analytics, rather than to merely produce a statistical report of a particular website which loses its value outside its context. |
| Tasks | |
| Published | 2017-06-14 |
| URL | http://arxiv.org/abs/1706.05089v1 |
| http://arxiv.org/pdf/1706.05089v1.pdf | |
| PWC | https://paperswithcode.com/paper/number-game |
| Repo | |
| Framework | |
Interpreting Shared Deep Learning Models via Explicable Boundary Trees
| Title | Interpreting Shared Deep Learning Models via Explicable Boundary Trees |
| Authors | Huijun Wu, Chen Wang, Jie Yin, Kai Lu, Liming Zhu |
| Abstract | Despite outperforming the human in many tasks, deep neural network models are also criticized for the lack of transparency and interpretability in decision making. The opaqueness results in uncertainty and low confidence when deploying such a model in model sharing scenarios, when the model is developed by a third party. For a supervised machine learning model, sharing training process including training data provides an effective way to gain trust and to better understand model predictions. However, it is not always possible to share all training data due to privacy and policy constraints. In this paper, we propose a method to disclose a small set of training data that is just sufficient for users to get the insight of a complicated model. The method constructs a boundary tree using selected training data and the tree is able to approximate the complicated model with high fidelity. We show that traversing data points in the tree gives users significantly better understanding of the model and paves the way for trustworthy model sharing. |
| Tasks | Decision Making |
| Published | 2017-09-12 |
| URL | http://arxiv.org/abs/1709.03730v1 |
| http://arxiv.org/pdf/1709.03730v1.pdf | |
| PWC | https://paperswithcode.com/paper/interpreting-shared-deep-learning-models-via |
| Repo | |
| Framework | |
Scalable Planning with Tensorflow for Hybrid Nonlinear Domains
| Title | Scalable Planning with Tensorflow for Hybrid Nonlinear Domains |
| Authors | Ga Wu, Buser Say, Scott Sanner |
| Abstract | Given recent deep learning results that demonstrate the ability to effectively optimize high-dimensional non-convex functions with gradient descent optimization on GPUs, we ask in this paper whether symbolic gradient optimization tools such as Tensorflow can be effective for planning in hybrid (mixed discrete and continuous) nonlinear domains with high dimensional state and action spaces? To this end, we demonstrate that hybrid planning with Tensorflow and RMSProp gradient descent is competitive with mixed integer linear program (MILP) based optimization on piecewise linear planning domains (where we can compute optimal solutions) and substantially outperforms state-of-the-art interior point methods for nonlinear planning domains. Furthermore, we remark that Tensorflow is highly scalable, converging to a strong plan on a large-scale concurrent domain with a total of 576,000 continuous action parameters distributed over a horizon of 96 time steps and 100 parallel instances in only 4 minutes. We provide a number of insights that clarify such strong performance including observations that despite long horizons, RMSProp avoids both the vanishing and exploding gradient problems. Together these results suggest a new frontier for highly scalable planning in nonlinear hybrid domains by leveraging GPUs and the power of recent advances in gradient descent with highly optimized toolkits like Tensorflow. |
| Tasks | |
| Published | 2017-04-25 |
| URL | http://arxiv.org/abs/1704.07511v3 |
| http://arxiv.org/pdf/1704.07511v3.pdf | |
| PWC | https://paperswithcode.com/paper/scalable-planning-with-tensorflow-for-hybrid |
| Repo | |
| Framework | |
