Paper Group ANR 284
Poisoning Behavioral Malware Clustering. Feature Dimensionality Reduction for Video Affect Classification: A Comparative Study. Helping or Hurting? Predicting Changes in Users’ Risk of Self-Harm Through Online Community Interactions. Multimodal Explanations by Predicting Counterfactuality in Videos. Sensitivity based Neural Networks Explanations. N …
Poisoning Behavioral Malware Clustering
Title | Poisoning Behavioral Malware Clustering |
Authors | Battista Biggio, Konrad Rieck, Davide Ariu, Christian Wressnegger, Igino Corona, Giorgio Giacinto, Fabio Roli |
Abstract | Clustering algorithms have become a popular tool in computer security to analyze the behavior of malware variants, identify novel malware families, and generate signatures for antivirus systems. However, the suitability of clustering algorithms for security-sensitive settings has been recently questioned by showing that they can be significantly compromised if an attacker can exercise some control over the input data. In this paper, we revisit this problem by focusing on behavioral malware clustering approaches, and investigate whether and to what extent an attacker may be able to subvert these approaches through a careful injection of samples with poisoning behavior. To this end, we present a case study on Malheur, an open-source tool for behavioral malware clustering. Our experiments not only demonstrate that this tool is vulnerable to poisoning attacks, but also that it can be significantly compromised even if the attacker can only inject a very small percentage of attacks into the input data. As a remedy, we discuss possible countermeasures and highlight the need for more secure clustering algorithms. |
Tasks | |
Published | 2018-11-25 |
URL | http://arxiv.org/abs/1811.09985v1 |
http://arxiv.org/pdf/1811.09985v1.pdf | |
PWC | https://paperswithcode.com/paper/poisoning-behavioral-malware-clustering |
Repo | |
Framework | |
Feature Dimensionality Reduction for Video Affect Classification: A Comparative Study
Title | Feature Dimensionality Reduction for Video Affect Classification: A Comparative Study |
Authors | Chenfeng Guo, Dongrui Wu |
Abstract | Affective computing has become a very important research area in human-machine interaction. However, affects are subjective, subtle, and uncertain. So, it is very difficult to obtain a large number of labeled training samples, compared with the number of possible features we could extract. Thus, dimensionality reduction is critical in affective computing. This paper presents our preliminary study on dimensionality reduction for affect classification. Five popular dimensionality reduction approaches are introduced and compared. Experiments on the DEAP dataset showed that no approach can universally outperform others, and performing classification using the raw features directly may not always be a bad choice. |
Tasks | Dimensionality Reduction |
Published | 2018-08-08 |
URL | http://arxiv.org/abs/1808.02956v1 |
http://arxiv.org/pdf/1808.02956v1.pdf | |
PWC | https://paperswithcode.com/paper/feature-dimensionality-reduction-for-video |
Repo | |
Framework | |
Helping or Hurting? Predicting Changes in Users’ Risk of Self-Harm Through Online Community Interactions
Title | Helping or Hurting? Predicting Changes in Users’ Risk of Self-Harm Through Online Community Interactions |
Authors | Luca Soldaini, Timothy Walsh, Arman Cohan, Julien Han, Nazli Goharian |
Abstract | In recent years, online communities have formed around suicide and self-harm prevention. While these communities offer support in moment of crisis, they can also normalize harmful behavior, discourage professional treatment, and instigate suicidal ideation. In this work, we focus on how interaction with others in such a community affects the mental state of users who are seeking support. We first build a dataset of conversation threads between users in a distressed state and community members offering support. We then show how to construct a classifier to predict whether distressed users are helped or harmed by the interactions in the thread, and we achieve a macro-F1 score of up to 0.69. |
Tasks | |
Published | 2018-04-19 |
URL | http://arxiv.org/abs/1804.07253v1 |
http://arxiv.org/pdf/1804.07253v1.pdf | |
PWC | https://paperswithcode.com/paper/helping-or-hurting-predicting-changes-in |
Repo | |
Framework | |
Multimodal Explanations by Predicting Counterfactuality in Videos
Title | Multimodal Explanations by Predicting Counterfactuality in Videos |
Authors | Atsushi Kanehira, Kentaro Takemoto, Sho Inayoshi, Tatsuya Harada |
Abstract | This study addresses generating counterfactual explanations with multimodal information. Our goal is not only to classify a video into a specific category, but also to provide explanations on why it is not categorized to a specific class with combinations of visual-linguistic information. Requirements that the expected output should satisfy are referred to as counterfactuality in this paper: (1) Compatibility of visual-linguistic explanations, and (2) Positiveness/negativeness for the specific positive/negative class. Exploiting a spatio-temporal region (tube) and an attribute as visual and linguistic explanations respectively, the explanation model is trained to predict the counterfactuality for possible combinations of multimodal information in a post-hoc manner. The optimization problem, which appears during training/inference, can be efficiently solved by inserting a novel neural network layer, namely the maximum subpath layer. We demonstrated the effectiveness of this method by comparison with a baseline of the action recognition datasets extended for this task. Moreover, we provide information-theoretical insight into the proposed method. |
Tasks | Temporal Action Localization |
Published | 2018-12-04 |
URL | https://arxiv.org/abs/1812.01263v2 |
https://arxiv.org/pdf/1812.01263v2.pdf | |
PWC | https://paperswithcode.com/paper/multimodal-explanations-by-predicting |
Repo | |
Framework | |
Sensitivity based Neural Networks Explanations
Title | Sensitivity based Neural Networks Explanations |
Authors | Enguerrand Horel, Virgile Mison, Tao Xiong, Kay Giesecke, Lidia Mangu |
Abstract | Although neural networks can achieve very high predictive performance on various different tasks such as image recognition or natural language processing, they are often considered as opaque “black boxes”. The difficulty of interpreting the predictions of a neural network often prevents its use in fields where explainability is important, such as the financial industry where regulators and auditors often insist on this aspect. In this paper, we present a way to assess the relative input features importance of a neural network based on the sensitivity of the model output with respect to its input. This method has the advantage of being fast to compute, it can provide both global and local levels of explanations and is applicable for many types of neural network architectures. We illustrate the performance of this method on both synthetic and real data and compare it with other interpretation techniques. This method is implemented into an open-source Python package that allows its users to easily generate and visualize explanations for their neural networks. |
Tasks | |
Published | 2018-12-03 |
URL | http://arxiv.org/abs/1812.01029v1 |
http://arxiv.org/pdf/1812.01029v1.pdf | |
PWC | https://paperswithcode.com/paper/sensitivity-based-neural-networks |
Repo | |
Framework | |
Neural Morphological Tagging for Estonian
Title | Neural Morphological Tagging for Estonian |
Authors | Alexander Tkachenko, Kairit Sirts |
Abstract | We develop neural morphological tagging and disambiguation models for Estonian. First, we experiment with two neural architectures for morphological tagging - a standard multiclass classifier which treats each morphological tag as a single unit, and a sequence model which handles the morphological tags as sequences of morphological category values. Secondly, we complement these models with the analyses generated by a rule-based Estonian morphological analyser (MA) VABAMORF , thus performing a soft morphological disambiguation. We compare two ways of supplementing a neural morphological tagger with the MA outputs: firstly, by adding the combined analyses embeddings to the word representation input to the neural tagging model, and secondly, by adopting an attention mechanism to focus on the most relevant analyses generated by the MA. Experiments on three Estonian datasets show that our neural architectures consistently outperform the non-neural baselines, including HMM-disambiguated VABAMORF, while augmenting models with MA outputs results in a further performance boost for both models. |
Tasks | Morphological Tagging |
Published | 2018-10-16 |
URL | http://arxiv.org/abs/1810.06908v1 |
http://arxiv.org/pdf/1810.06908v1.pdf | |
PWC | https://paperswithcode.com/paper/neural-morphological-tagging-for-estonian |
Repo | |
Framework | |
3D multirater RCNN for multimodal multiclass detection and characterisation of extremely small objects
Title | 3D multirater RCNN for multimodal multiclass detection and characterisation of extremely small objects |
Authors | Carole H. Sudre, Beatriz Gomez Anson, Silvia Ingala, Chris D. Lane, Daniel Jimenez, Lukas Haider, Thomas Varsavsky, Lorna Smith, H. Rolf Jäger, M. Jorge Cardoso |
Abstract | Extremely small objects (ESO) have become observable on clinical routine magnetic resonance imaging acquisitions, thanks to a reduction in acquisition time at higher resolution. Despite their small size (usually $<$10 voxels per object for an image of more than $10^6$ voxels), these markers reflect tissue damage and need to be accounted for to investigate the complete phenotype of complex pathological pathways. In addition to their very small size, variability in shape and appearance leads to high labelling variability across human raters, resulting in a very noisy gold standard. Such objects are notably present in the context of cerebral small vessel disease where enlarged perivascular spaces and lacunes, commonly observed in the ageing population, are thought to be associated with acceleration of cognitive decline and risk of dementia onset. In this work, we redesign the RCNN model to scale to 3D data, and to jointly detect and characterise these important markers of age-related neurovascular changes. We also propose training strategies enforcing the detection of extremely small objects, ensuring a tractable and stable training process. |
Tasks | |
Published | 2018-12-21 |
URL | http://arxiv.org/abs/1812.09046v1 |
http://arxiv.org/pdf/1812.09046v1.pdf | |
PWC | https://paperswithcode.com/paper/3d-multirater-rcnn-for-multimodal-multiclass |
Repo | |
Framework | |
ENG: End-to-end Neural Geometry for Robust Depth and Pose Estimation using CNNs
Title | ENG: End-to-end Neural Geometry for Robust Depth and Pose Estimation using CNNs |
Authors | Thanuja Dharmasiri, Andrew Spek, Tom Drummond |
Abstract | Recovering structure and motion parameters given a image pair or a sequence of images is a well studied problem in computer vision. This is often achieved by employing Structure from Motion (SfM) or Simultaneous Localization and Mapping (SLAM) algorithms based on the real-time requirements. Recently, with the advent of Convolutional Neural Networks (CNNs) researchers have explored the possibility of using machine learning techniques to reconstruct the 3D structure of a scene and jointly predict the camera pose. In this work, we present a framework that achieves state-of-the-art performance on single image depth prediction for both indoor and outdoor scenes. The depth prediction system is then extended to predict optical flow and ultimately the camera pose and trained end-to-end. Our motion estimation framework outperforms the previous motion prediction systems and we also demonstrate that the state-of-the-art metric depths can be further improved using the knowledge of pose. |
Tasks | Depth Estimation, Motion Estimation, motion prediction, Optical Flow Estimation, Pose Estimation, Simultaneous Localization and Mapping |
Published | 2018-07-16 |
URL | http://arxiv.org/abs/1807.05705v2 |
http://arxiv.org/pdf/1807.05705v2.pdf | |
PWC | https://paperswithcode.com/paper/eng-end-to-end-neural-geometry-for-robust |
Repo | |
Framework | |
Closing the Calibration Loop: An Inside-out-tracking Paradigm for Augmented Reality in Orthopedic Surgery
Title | Closing the Calibration Loop: An Inside-out-tracking Paradigm for Augmented Reality in Orthopedic Surgery |
Authors | Jonas Hajek, Mathias Unberath, Javad Fotouhi, Bastian Bier, Sing Chun Lee, Greg Osgood, Andreas Maier, Mehran Armand, Nassir Navab |
Abstract | In percutaneous orthopedic interventions the surgeon attempts to reduce and fixate fractures in bony structures. The complexity of these interventions arises when the surgeon performs the challenging task of navigating surgical tools percutaneously only under the guidance of 2D interventional X-ray imaging. Moreover, the intra-operatively acquired data is only visualized indirectly on external displays. In this work, we propose a flexible Augmented Reality (AR) paradigm using optical see-through head mounted displays. The key technical contribution of this work includes the marker-less and dynamic tracking concept which closes the calibration loop between patient, C-arm and the surgeon. This calibration is enabled using Simultaneous Localization and Mapping of the environment of the operating theater. In return, the proposed solution provides in situ visualization of pre- and intra-operative 3D medical data directly at the surgical site. We demonstrate pre-clinical evaluation of a prototype system, and report errors for calibration and target registration. Finally, we demonstrate the usefulness of the proposed inside-out tracking system in achieving “bull’s eye” view for C-arm-guided punctures. This AR solution provides an intuitive visualization of the anatomy and can simplify the hand-eye coordination for the orthopedic surgeon. |
Tasks | Calibration, Simultaneous Localization and Mapping |
Published | 2018-03-22 |
URL | http://arxiv.org/abs/1803.08610v1 |
http://arxiv.org/pdf/1803.08610v1.pdf | |
PWC | https://paperswithcode.com/paper/closing-the-calibration-loop-an-inside-out |
Repo | |
Framework | |
Face Detection Using Improved Faster RCNN
Title | Face Detection Using Improved Faster RCNN |
Authors | Changzheng Zhang, Xiang Xu, Dandan Tu |
Abstract | Faster RCNN has achieved great success for generic object detection including PASCAL object detection and MS COCO object detection. In this report, we propose a detailed designed Faster RCNN method named FDNet1.0 for face detection. Several techniques were employed including multi-scale training, multi-scale testing, light-designed RCNN, some tricks for inference and a vote-based ensemble method. Our method achieves two 1th places and one 2nd place in three tasks over WIDER FACE validation dataset (easy set, medium set, hard set). |
Tasks | Face Detection, Object Detection |
Published | 2018-02-06 |
URL | http://arxiv.org/abs/1802.02142v1 |
http://arxiv.org/pdf/1802.02142v1.pdf | |
PWC | https://paperswithcode.com/paper/face-detection-using-improved-faster-rcnn |
Repo | |
Framework | |
Squeeze-and-Excitation on Spatial and Temporal Deep Feature Space for Action Recognition
Title | Squeeze-and-Excitation on Spatial and Temporal Deep Feature Space for Action Recognition |
Authors | Gaoyun An, Wen Zhou, Yuxuan Wu, Zhenxing Zheng, Yongwen Liu |
Abstract | Spatial and temporal features are two key and complementary information for human action recognition. In order to make full use of the intra-frame spatial characteristics and inter-frame temporal relationships, we propose the Squeeze-and-Excitation Long-term Recurrent Convolutional Networks (SE-LRCN) for human action recognition. The Squeeze and Excitation operations are used to implement the feature recalibration. In SE-LRCN, Squeeze-and-Excitation ResNet-34 (SE-ResNet-34) network is adopted to extract spatial features to enhance the dependencies and importance of feature channels of pixel granularity. We also propose the Squeeze-and-Excitation Long Short-Term Memory (SE-LSTM) network to model the temporal relationship, and to enhance the dependencies and importance of feature channels of frame granularity. We evaluate the proposed model on two challenging benchmarks, HMDB51 and UCF101, and the proposed SE-LRCN achieves the competitive results with the state-of-the-art. |
Tasks | Temporal Action Localization |
Published | 2018-06-02 |
URL | http://arxiv.org/abs/1806.00631v2 |
http://arxiv.org/pdf/1806.00631v2.pdf | |
PWC | https://paperswithcode.com/paper/squeeze-and-excitation-on-spatial-and |
Repo | |
Framework | |
Comparison Training for Computer Chinese Chess
Title | Comparison Training for Computer Chinese Chess |
Authors | Wen-Jie Tseng, Jr-Chang Chen, I-Chen Wu, Tinghan Wei |
Abstract | This paper describes the application of comparison training (CT) for automatic feature weight tuning, with the final objective of improving the evaluation functions used in Chinese chess programs. First, we propose an n-tuple network to extract features, since n-tuple networks require very little expert knowledge through its large numbers of features, while simulta-neously allowing easy access. Second, we propose a novel evalua-tion method that incorporates tapered eval into CT. Experiments show that with the same features and the same Chinese chess program, the automatically tuned comparison training feature weights achieved a win rate of 86.58% against the weights that were hand-tuned. The above trained version was then improved by adding additional features, most importantly n-tuple features. This improved version achieved a win rate of 81.65% against the trained version without additional features. |
Tasks | |
Published | 2018-01-23 |
URL | http://arxiv.org/abs/1801.07411v1 |
http://arxiv.org/pdf/1801.07411v1.pdf | |
PWC | https://paperswithcode.com/paper/comparison-training-for-computer-chinese |
Repo | |
Framework | |
IntelligentCrowd: Mobile Crowdsensing via Multi-agent Reinforcement Learning
Title | IntelligentCrowd: Mobile Crowdsensing via Multi-agent Reinforcement Learning |
Authors | Yize Chen, Hao Wang |
Abstract | The prosperity of smart mobile devices has made mobile crowdsensing (MCS) a promising paradigm for completing complex sensing and computation tasks. In the past, great efforts have been made on the design of incentive mechanisms and task allocation strategies from MCS platform’s perspective to motivate mobile users’ participation. However, in practice, MCS participants face many uncertainties coming from their sensing environment as well as other participants’ strategies, and how do they interact with each other and make sensing decisions is not well understood. In this paper, we take MCS participants’ perspective to derive an online sensing policy to maximize their payoffs via MCS participation. Specifically, we model the interactions of mobile users and sensing environments as a multi-agent Markov decision process. Each participant cannot observe others’ decisions, but needs to decide her effort level in sensing tasks only based on local information, e.g., its own record of sensed signals’ quality. To cope with the stochastic sensing environment, we develop an intelligent crowdsensing algorithm IntelligentCrowd by leveraging the power of multi-agent reinforcement learning (MARL). Our algorithm leads to the optimal sensing policy for each user to maximize the expected payoff against stochastic sensing environments, and can be implemented at individual participant’s level in a distributed fashion. Numerical simulations demonstrate that IntelligentCrowd significantly improves users’ payoffs in sequential MCS tasks under various sensing dynamics. |
Tasks | Multi-agent Reinforcement Learning |
Published | 2018-09-20 |
URL | https://arxiv.org/abs/1809.07830v2 |
https://arxiv.org/pdf/1809.07830v2.pdf | |
PWC | https://paperswithcode.com/paper/intelligentcrowd-mobile-crowdsensing-via |
Repo | |
Framework | |
Knowledge-guided Semantic Computing Network
Title | Knowledge-guided Semantic Computing Network |
Authors | Guangming Shi, Zhongqiang Zhang, Dahua Gao, Xuemei Xie, Yihao Feng, Xinrui Ma, Danhua Liu |
Abstract | It is very useful to integrate human knowledge and experience into traditional neural networks for faster learning speed, fewer training samples and better interpretability. However, due to the obscured and indescribable black box model of neural networks, it is very difficult to design its architecture, interpret its features and predict its performance. Inspired by human visual cognition process, we propose a knowledge-guided semantic computing network which includes two modules: a knowledge-guided semantic tree and a data-driven neural network. The semantic tree is pre-defined to describe the spatial structural relations of different semantics, which just corresponds to the tree-like description of objects based on human knowledge. The object recognition process through the semantic tree only needs simple forward computing without training. Besides, to enhance the recognition ability of the semantic tree in aspects of the diversity, randomicity and variability, we use the traditional neural network to aid the semantic tree to learn some indescribable features. Only in this case, the training process is needed. The experimental results on MNIST and GTSRB datasets show that compared with the traditional data-driven network, our proposed semantic computing network can achieve better performance with fewer training samples and lower computational complexity. Especially, Our model also has better adversarial robustness than traditional neural network with the help of human knowledge. |
Tasks | Object Recognition |
Published | 2018-09-29 |
URL | http://arxiv.org/abs/1810.00139v1 |
http://arxiv.org/pdf/1810.00139v1.pdf | |
PWC | https://paperswithcode.com/paper/knowledge-guided-semantic-computing-network |
Repo | |
Framework | |
Learning to Update for Object Tracking with Recurrent Meta-learner
Title | Learning to Update for Object Tracking with Recurrent Meta-learner |
Authors | Bi Li, Wenxuan Xie, Wenjun Zeng, Wenyu Liu |
Abstract | Model update lies at the heart of object tracking. Generally, model update is formulated as an online learning problem where a target model is learned over the online training set. Our key innovation is to \emph{formulate the model update problem in the meta-learning framework and learn the online learning algorithm itself using large numbers of offline videos}, i.e., \emph{learning to update}. The learned updater takes as input the online training set and outputs an updated target model. As a first attempt, we design the learned updater based on recurrent neural networks (RNNs) and demonstrate its application in a template-based tracker and a correlation filter-based tracker. Our learned updater consistently improves the base trackers and runs faster than realtime on GPU while requiring small memory footprint during testing. Experiments on standard benchmarks demonstrate that our learned updater outperforms commonly used update baselines including the efficient exponential moving average (EMA)-based update and the well-designed stochastic gradient descent (SGD)-based update. Equipped with our learned updater, the template-based tracker achieves state-of-the-art performance among realtime trackers on GPU. |
Tasks | Meta-Learning, Object Tracking |
Published | 2018-06-19 |
URL | http://arxiv.org/abs/1806.07078v3 |
http://arxiv.org/pdf/1806.07078v3.pdf | |
PWC | https://paperswithcode.com/paper/learning-to-update-for-object-tracking-with |
Repo | |
Framework | |