January 28, 2020

3268 words 16 mins read

Paper Group ANR 1001

Multi-user Augmented Reality Application for Video Communication in Virtual Space. Efficient Reward-Based Structural Plasticity on a SpiNNaker 2 Prototype. Strong Log-Concavity Does Not Imply Log-Submodularity. DeepAtom: A Framework for Protein-Ligand Binding Affinity Prediction. Schrödinger-ANI: An Eight-Element Neural Network Interaction Potentia …

Multi-user Augmented Reality Application for Video Communication in Virtual Space


Title	Multi-user Augmented Reality Application for Video Communication in Virtual Space
Authors	Kumar Mridul, M. Ramanathan, Kunal Ahirwar, Mansi Sharma
Abstract	Communication is the most useful tool to impart knowledge, understand ideas, clarify thoughts and expressions, organize plan and manage every single day-to-day activity. Although there are different modes of communication, physical barrier always affects the clarity of the message due to the absence of body language and facial expressions. These barriers are overcome by video calling, which is technically the most advance mode of communication at present. The proposed work concentrates around the concept of video calling in a more natural and seamless way using Augmented Reality (AR). AR can be helpful in giving the users an experience of physical presence in each other’s environment. Our work provides an entirely new platform for video calling, wherein the users can enjoy the privilege of their own virtual space to interact with the individual’s environment. Moreover, there is no limitation of sharing the same screen space. Any number of participants can be accommodated over a single conference without having to compromise the screen size.
Tasks
Published	2019-09-20
URL	https://arxiv.org/abs/1909.09529v1
PDF	https://arxiv.org/pdf/1909.09529v1.pdf
PWC	https://paperswithcode.com/paper/multi-user-augmented-reality-application-for
Repo
Framework

Efficient Reward-Based Structural Plasticity on a SpiNNaker 2 Prototype


Title	Efficient Reward-Based Structural Plasticity on a SpiNNaker 2 Prototype
Authors	Yexin Yan, David Kappel, Felix Neumaerker, Johannes Partzsch, Bernhard Vogginger, Sebastian Hoeppner, Steve Furber, Wolfgang Maass, Robert Legenstein, Christian Mayr
Abstract	Advances in neuroscience uncover the mechanisms employed by the brain to efficiently solve complex learning tasks with very limited resources. However, the efficiency is often lost when one tries to port these findings to a silicon substrate, since brain-inspired algorithms often make extensive use of complex functions such as random number generators, that are expensive to compute on standard general purpose hardware. The prototype chip of the 2nd generation SpiNNaker system is designed to overcome this problem. Low-power ARM processors equipped with a random number generator and an exponential function accelerator enable the efficient execution of brain-inspired algorithms. We implement the recently introduced reward-based synaptic sampling model that employs structural plasticity to learn a function or task. The numerical simulation of the model requires to update the synapse variables in each time step including an explorative random term. To the best of our knowledge, this is the most complex synapse model implemented so far on the SpiNNaker system. By making efficient use of the hardware accelerators and numerical optimizations the computation time of one plasticity update is reduced by a factor of 2. This, combined with fitting the model into to the local SRAM, leads to 62% energy reduction compared to the case without accelerators and the use of external DRAM. The model implementation is integrated into the SpiNNaker software framework allowing for scalability onto larger systems. The hardware-software system presented in this work paves the way for power-efficient mobile and biomedical applications with biologically plausible brain-inspired algorithms.
Tasks
Published	2019-03-20
URL	http://arxiv.org/abs/1903.08500v1
PDF	http://arxiv.org/pdf/1903.08500v1.pdf
PWC	https://paperswithcode.com/paper/efficient-reward-based-structural-plasticity
Repo
Framework

Strong Log-Concavity Does Not Imply Log-Submodularity


Title	Strong Log-Concavity Does Not Imply Log-Submodularity
Authors	Alkis Gotovos
Abstract	We disprove a recent conjecture regarding discrete distributions and their generating polynomials stating that strong log-concavity implies log-submodularity.
Tasks
Published	2019-10-25
URL	https://arxiv.org/abs/1910.11544v1
PDF	https://arxiv.org/pdf/1910.11544v1.pdf
PWC	https://paperswithcode.com/paper/strong-log-concavity-does-not-imply-log
Repo
Framework

DeepAtom: A Framework for Protein-Ligand Binding Affinity Prediction


Title	DeepAtom: A Framework for Protein-Ligand Binding Affinity Prediction
Authors	Yanjun Li, Mohammad A. Rezaei, Chenglong Li, Xiaolin Li, Dapeng Wu
Abstract	The cornerstone of computational drug design is the calculation of binding affinity between two biological counterparts, especially a chemical compound, i.e., a ligand, and a protein. Predicting the strength of protein-ligand binding with reasonable accuracy is critical for drug discovery. In this paper, we propose a data-driven framework named DeepAtom to accurately predict the protein-ligand binding affinity. With 3D Convolutional Neural Network (3D-CNN) architecture, DeepAtom could automatically extract binding related atomic interaction patterns from the voxelized complex structure. Compared with the other CNN based approaches, our light-weight model design effectively improves the model representational capacity, even with the limited available training data. With validation experiments on the PDBbind v.2016 benchmark and the independent Astex Diverse Set, we demonstrate that the less feature engineering dependent DeepAtom approach consistently outperforms the other state-of-the-art scoring methods. We also compile and propose a new benchmark dataset to further improve the model performances. With the new dataset as training input, DeepAtom achieves Pearson’s R=0.83 and RMSE=1.23 pK units on the PDBbind v.2016 core set. The promising results demonstrate that DeepAtom models can be potentially adopted in computational drug development protocols such as molecular docking and virtual screening.
Tasks	Drug Discovery, Feature Engineering
Published	2019-12-01
URL	https://arxiv.org/abs/1912.00318v1
PDF	https://arxiv.org/pdf/1912.00318v1.pdf
PWC	https://paperswithcode.com/paper/deepatom-a-framework-for-protein-ligand
Repo
Framework

Schrödinger-ANI: An Eight-Element Neural Network Interaction Potential with Greatly Expanded Coverage of Druglike Chemical Space


Title	Schrödinger-ANI: An Eight-Element Neural Network Interaction Potential with Greatly Expanded Coverage of Druglike Chemical Space
Authors	James M. Stevenson, Leif D. Jacobson, Yutong Zhao, Chuanjie Wu, Jon Maple, Karl Leswing, Edward Harder, Robert Abel
Abstract	We have developed a neural network potential energy function for use in drug discovery, with chemical element support extended from 41% to 94% of druglike molecules based on ChEMBL. We expand on the work of Smith et al., with their highly accurate network for the elements H, C, N, O, creating a network for H, C, N, O, S, F, Cl, P. We focus particularly on the calculation of relative conformer energies, for which we show that our new potential energy function has an RMSE of 0.70 kcal/mol for prospective druglike molecule conformers, substantially better than the previous state of the art. The speed and accuracy of this model could greatly accelerate the parameterization of protein-ligand binding free energy calculations for novel druglike molecules.
Tasks	Drug Discovery
Published	2019-11-22
URL	https://arxiv.org/abs/1912.05079v1
PDF	https://arxiv.org/pdf/1912.05079v1.pdf
PWC	https://paperswithcode.com/paper/schrodinger-ani-an-eight-element-neural
Repo
Framework

Analysis and a Solution of Momentarily Missed Detection for Anchor-based Object Detectors


Title	Analysis and a Solution of Momentarily Missed Detection for Anchor-based Object Detectors
Authors	Yusuke Hosoya, Masanori Suganuma, Takayuki Okatani
Abstract	The employment of convolutional neural networks has led to significant performance improvement on the task of object detection. However, when applying existing detectors to continuous frames in a video, we often encounter momentary miss-detection of objects, that is, objects are undetected exceptionally at a few frames, although they are correctly detected at all other frames. In this paper, we analyze the mechanism of how such miss-detection occurs. For the most popular class of detectors that are based on anchor boxes, we show the followings: i) besides apparent causes such as motion blur, occlusions, background clutters, etc., the majority of remaining miss-detection can be explained by an improper behavior of the detectors at boundaries of the anchor boxes; and ii) this can be rectified by improving the way of choosing positive samples from candidate anchor boxes when training the detectors.
Tasks	Object Detection
Published	2019-10-21
URL	https://arxiv.org/abs/1910.09212v2
PDF	https://arxiv.org/pdf/1910.09212v2.pdf
PWC	https://paperswithcode.com/paper/analysis-and-a-solution-of-momentarily-missed
Repo
Framework

Sub-Goal Trees – a Framework for Goal-Directed Trajectory Prediction and Optimization


Title	Sub-Goal Trees – a Framework for Goal-Directed Trajectory Prediction and Optimization
Authors	Tom Jurgenson, Edward Groshev, Aviv Tamar
Abstract	Many AI problems, in robotics and other domains, are goal-directed, essentially seeking a trajectory leading to some goal state. In such problems, the way we choose to represent a trajectory underlies algorithms for trajectory prediction and optimization. Interestingly, most all prior work in imitation and reinforcement learning builds on a sequential trajectory representation – calculating the next state in the trajectory given its predecessors. We propose a different perspective: a goal-conditioned trajectory can be represented by first selecting an intermediate state between start and goal, partitioning the trajectory into two. Then, recursively, predicting intermediate points on each sub-segment, until a complete trajectory is obtained. We call this representation a sub-goal tree, and building on it, we develop new methods for trajectory prediction, learning, and optimization. We show that in a supervised learning setting, sub-goal trees better account for trajectory variability, and can predict trajectories exponentially faster at test time by leveraging a concurrent computation. Then, for optimization, we derive a new dynamic programming equation for sub-goal trees, and use it to develop new planning and reinforcement learning algorithms. These algorithms, which are not based on the standard Bellman equation, naturally account for hierarchical sub-goal structure in a task. Empirical results on motion planning domains show that the sub-goal tree framework significantly improves both accuracy and prediction time.
Tasks	Motion Planning, Trajectory Prediction
Published	2019-06-12
URL	https://arxiv.org/abs/1906.05329v1
PDF	https://arxiv.org/pdf/1906.05329v1.pdf
PWC	https://paperswithcode.com/paper/sub-goal-trees-a-framework-for-goal-directed
Repo
Framework

The politics of deceptive borders: ‘biomarkers of deceit’ and the case of iBorderCtrl


Title	The politics of deceptive borders: ‘biomarkers of deceit’ and the case of iBorderCtrl
Authors	Javier Sánchez-Monedero, Lina Dencik
Abstract	This paper critically examines a recently developed proposal for a border control system called iBorderCtrl, designed to detect deception based on facial recognition technology and the measurement of micro-expressions, termed ‘biomarkers of deceit’. Funded under the European Commission’s Horizon 2020 programme, we situate our analysis in the wider political economy of ‘emotional AI’ and the history of deception detection technologies. We then move on to interrogate the design of iBorderCtrl using publicly available documents and assess the assumptions and scientific validation underpinning the project design. Finally, drawing on a Bayesian analysis we outline statistical fallacies in the foundational premise of mass screening and argue that it is very unlikely that the model that iBorderCtrl provides for deception detection would work in practice. By interrogating actual systems in this way, we argue that we can begin to question the very premise of the development of data-driven systems, and emotional AI and deception detection in particular, pushing back on the assumption that these systems are fulfilling the tasks they claim to be attending to and instead ask what function such projects carry out in the creation of subjects and management of populations. This function is not merely technical but, rather, we argue, distinctly political and forms part of a mode of governance increasingly shaping life opportunities and fundamental rights.
Tasks	Deception Detection
Published	2019-11-20
URL	https://arxiv.org/abs/1911.09156v3
PDF	https://arxiv.org/pdf/1911.09156v3.pdf
PWC	https://paperswithcode.com/paper/the-politics-of-deceptive-borders-biomarkers
Repo
Framework

Implicit Knowledge in Argumentative Texts: An Annotated Corpus


Title	Implicit Knowledge in Argumentative Texts: An Annotated Corpus
Authors	Maria Becker, Katharina Korfhage, Anette Frank
Abstract	When speaking or writing, people omit information that seems clear and evident, such that only part of the message is expressed in words. Especially in argumentative texts it is very common that (important) parts of the argument are implied and omitted. We hypothesize that for argument analysis it will be beneficial to reconstruct this implied information. As a starting point for filling such knowledge gaps, we build a corpus consisting of high-quality human annotations of missing and implied information in argumentative texts. To learn more about the characteristics of both the argumentative texts and the added information, we further annotate the data with semantic clause types and commonsense knowledge relations. The outcome of our work is a carefully de-signed and richly annotated dataset, for which we then provide an in-depth analysis by investigating characteristic distributions and correlations of the assigned labels. We reveal interesting patterns and intersections between the annotation categories and properties of our dataset, which enable insights into the characteristics of both argumentative texts and implicit knowledge in terms of structural features and semantic information. The results of our analysis can help to assist automated argument analysis and can guide the process of revealing implicit information in argumentative texts automatically.
Tasks
Published	2019-12-04
URL	https://arxiv.org/abs/1912.10161v1
PDF	https://arxiv.org/pdf/1912.10161v1.pdf
PWC	https://paperswithcode.com/paper/implicit-knowledge-in-argumentative-texts-an
Repo
Framework

Compressed Diffusion


Title	Compressed Diffusion
Authors	Scott Gigante, Jay S. Stanley III, Ngan Vu, David van Dijk, Kevin Moon, Guy Wolf, Smita Krishnaswamy
Abstract	Diffusion maps are a commonly used kernel-based method for manifold learning, which can reveal intrinsic structures in data and embed them in low dimensions. However, as with most kernel methods, its implementation requires a heavy computational load, reaching up to cubic complexity in the number of data points. This limits its usability in modern data analysis. Here, we present a new approach to computing the diffusion geometry, and related embeddings, from a compressed diffusion process between data regions rather than data points. Our construction is based on an adaptation of the previously proposed measure-based Gaussian correlation (MGC) kernel that robustly captures the local geometry around data points. We use this MGC kernel to efficiently compress diffusion relations from pointwise to data region resolution. Finally, a spectral embedding of the data regions provides coordinates that are used to interpolate and approximate the pointwise diffusion map embedding of data. We analyze theoretical connections between our construction and the original diffusion geometry of diffusion maps, and demonstrate the utility of our method in analyzing big datasets, where it outperforms competing approaches.
Tasks
Published	2019-01-31
URL	https://arxiv.org/abs/1902.00033v2
PDF	https://arxiv.org/pdf/1902.00033v2.pdf
PWC	https://paperswithcode.com/paper/compressed-diffusion
Repo
Framework

Triclustering of Gene Expression Microarray Data Using Coarse-Grained Parallel Genetic Algorithm


Title	Triclustering of Gene Expression Microarray Data Using Coarse-Grained Parallel Genetic Algorithm
Authors	Shubhankar Mohapatra, Moumita Sarkar, Anjali Mohapatra, Bhawani Sankar Biswal
Abstract	Microarray data analysis is one of the major area of research in the field computational biology. Numerous techniques like clustering, biclustering are often applied to microarray data to extract meaningful outcomes which play key roles in practical healthcare affairs like disease identification, drug discovery etc. But these techniques become obsolete when time as an another factor is considered for evaluation in such data. This problem motivates to use triclustering method on gene expression 3D microarray data. In this article, a new methodology based on coarse-grained parallel genetic approach is proposed to locate meaningful triclusters in gene expression data. The outcomes are quite impressive as they are more effective as compared to traditional state of the art genetic approaches previously applied for triclustering of 3D GCT microarray data.
Tasks	Drug Discovery
Published	2019-08-31
URL	https://arxiv.org/abs/1909.00237v1
PDF	https://arxiv.org/pdf/1909.00237v1.pdf
PWC	https://paperswithcode.com/paper/triclustering-of-gene-expression-microarray-1
Repo
Framework

Gated Graph Recursive Neural Networks for Molecular Property Prediction


Title	Gated Graph Recursive Neural Networks for Molecular Property Prediction
Authors	Hiroyuki Shindo, Yuji Matsumoto
Abstract	Molecule property prediction is a fundamental problem for computer-aided drug discovery and materials science. Quantum-chemical simulations such as density functional theory (DFT) have been widely used for calculating the molecule properties, however, because of the heavy computational cost, it is difficult to search a huge number of potential chemical compounds. Machine learning methods for molecular modeling are attractive alternatives, however, the development of expressive, accurate, and scalable graph neural networks for learning molecular representations is still challenging. In this work, we propose a simple and powerful graph neural networks for molecular property prediction. We model a molecular as a directed complete graph in which each atom has a spatial position, and introduce a recursive neural network with simple gating function. We also feed input embeddings for every layers as skip connections to accelerate the training. Experimental results show that our model achieves the state-of-the-art performance on the standard benchmark dataset for molecular property prediction.
Tasks	Drug Discovery, Molecular Property Prediction
Published	2019-08-31
URL	https://arxiv.org/abs/1909.00259v2
PDF	https://arxiv.org/pdf/1909.00259v2.pdf
PWC	https://paperswithcode.com/paper/gated-graph-recursive-neural-networks-for
Repo
Framework

Mimic and Fool: A Task Agnostic Adversarial Attack


Title	Mimic and Fool: A Task Agnostic Adversarial Attack
Authors	Akshay Chaturvedi, Utpal Garain
Abstract	At present, adversarial attacks are designed in a task-specific fashion. However, for downstream computer vision tasks such as image captioning, image segmentation etc., the current deep learning systems use an image classifier like VGG16, ResNet50, Inception-v3 etc. as a feature extractor. Keeping this in mind, we propose Mimic and Fool, a task agnostic adversarial attack. Given a feature extractor, the proposed attack finds an adversarial image which can mimic the image feature of the original image. This ensures that the two images give the same (or similar) output regardless of the task. We randomly select 1000 MSCOCO validation images for experimentation. We perform experiments on two image captioning models, Show and Tell, Show Attend and Tell and one VQA model, namely, end-to-end neural module network (N2NMN). The proposed attack achieves success rate of 74.0%, 81.0% and 89.6% for Show and Tell, Show Attend and Tell and N2NMN respectively. We also propose a slight modification to our attack to generate natural-looking adversarial images. In addition, it is shown that the proposed attack also works for invertible architecture. Since Mimic and Fool only requires information about the feature extractor of the model, it can be considered as a gray-box attack.
Tasks	Adversarial Attack, Image Captioning, Semantic Segmentation, Visual Question Answering
Published	2019-06-11
URL	https://arxiv.org/abs/1906.04606v1
PDF	https://arxiv.org/pdf/1906.04606v1.pdf
PWC	https://paperswithcode.com/paper/mimic-and-fool-a-task-agnostic-adversarial
Repo
Framework

StarNet: Pedestrian Trajectory Prediction using Deep Neural Network in Star Topology


Title	StarNet: Pedestrian Trajectory Prediction using Deep Neural Network in Star Topology
Authors	Yanliang Zhu, Deheng Qian, Dongchun Ren, Huaxia Xia
Abstract	Pedestrian trajectory prediction is crucial for many important applications. This problem is a great challenge because of complicated interactions among pedestrians. Previous methods model only the pairwise interactions between pedestrians, which not only oversimplifies the interactions among pedestrians but also is computationally inefficient. In this paper, we propose a novel model StarNet to deal with these issues. StarNet has a star topology which includes a unique hub network and multiple host networks. The hub network takes observed trajectories of all pedestrians to produce a comprehensive description of the interpersonal interactions. Then the host networks, each of which corresponds to one pedestrian, consult the description and predict future trajectories. The star topology gives StarNet two advantages over conventional models. First, StarNet is able to consider the collective influence among all pedestrians in the hub network, making more accurate predictions. Second, StarNet is computationally efficient since the number of host network is linear to the number of pedestrians. Experiments on multiple public datasets demonstrate that StarNet outperforms multiple state-of-the-arts by a large margin in terms of both accuracy and efficiency.
Tasks	Trajectory Prediction
Published	2019-06-05
URL	https://arxiv.org/abs/1906.01797v2
PDF	https://arxiv.org/pdf/1906.01797v2.pdf
PWC	https://paperswithcode.com/paper/starnet-pedestrian-trajectory-prediction
Repo
Framework

Self-Supervised Learning from Web Data for Multimodal Retrieval


Title	Self-Supervised Learning from Web Data for Multimodal Retrieval
Authors	Raul Gomez, Lluis Gomez, Jaume Gibert, Dimosthenis Karatzas
Abstract	Self-Supervised learning from multimodal image and text data allows deep neural networks to learn powerful features with no need of human annotated data. Web and Social Media platforms provide a virtually unlimited amount of this multimodal data. In this work we propose to exploit this free available data to learn a multimodal image and text embedding, aiming to leverage the semantic knowledge learnt in the text domain and transfer it to a visual model for semantic image retrieval. We demonstrate that the proposed pipeline can learn from images with associated textwithout supervision and analyze the semantic structure of the learnt joint image and text embedding space. We perform a thorough analysis and performance comparison of five different state of the art text embeddings in three different benchmarks. We show that the embeddings learnt with Web and Social Media data have competitive performances over supervised methods in the text based image retrieval task, and we clearly outperform state of the art in the MIRFlickr dataset when training in the target data. Further, we demonstrate how semantic multimodal image retrieval can be performed using the learnt embeddings, going beyond classical instance-level retrieval problems. Finally, we present a new dataset, InstaCities1M, composed by Instagram images and their associated texts that can be used for fair comparison of image-text embeddings.
Tasks	Image Retrieval
Published	2019-01-07
URL	http://arxiv.org/abs/1901.02004v1
PDF	http://arxiv.org/pdf/1901.02004v1.pdf
PWC	https://paperswithcode.com/paper/self-supervised-learning-from-web-data-for
Repo
Framework