Abstract

We introduce MUGL, a novel deep neural model for large-scale, diverse generation of single and multi-person pose-based action sequences with locomotion. Our con- trollable approach enables variable-length generations cus- tomizable by action category, across more than 100 cate- gories. To enable intra/inter-category diversity, we model the latent generative space using a Conditional Gaussian Mixture Variational Autoencoder. To enable realistic gen- eration of actions involving locomotion, we decouple local pose and global trajectory components of the action se- quence. We incorporate duration-aware feature represen- tations to enable variable-length sequence generation. We use a hybrid pose sequence representation with 3D pose sequences sourced from videos and 3D Kinect-based se- quences of NTU-RGBD-120. To enable principled com- parison of generation quality, we employ suitably modi- fied strong baselines during evaluation. Although smaller and simpler compared to baselines, MUGL provides better quality generations, paving the way for practical and con- trollable large-scale human action generation.

Abstract

We consider a budgeted combinatorial multi-armed bandit setting where, in every round, the algorithm selects a super-arm consisting of one or more arms. The goal is to minimize the total expected regret after all rounds within a limited budget. Existing techniques in this literature either fix the budget per round or fix the number of arms pulled in each round. Our setting is more general where based on the remaining budget and remaining number of rounds, the algorithm can decide how many arms to be pulled in each round. First, we propose CBwK-Greedy-UCB algorithm, which uses a greedy technique, CBwK-Greedy, to allocate the arms to the rounds. Next, we propose a reduction of this problem to Bandits with Knapsacks (BwK) with a single pull. With this reduction, we propose CBwK-LP-UCB that uses PrimalDualBwK ingeniously. We rigorously prove regret bounds for CBwK-LP-UCB. We experimentally compare the two algorithms and observe that CBwK-Greedy- UCB performs incrementally better than CBwK-LP-UCB. We also show that for very high budgets, the regret goes to zero.

Abstract

XAlign: Cross-lingual Fact-to-Text Alignment and Generation for Low-Resource Languages Tushar Abhishek, Shivprasad Sagare, Bhavyajeet Singh, Anubhav Sharma, Manish Gupta∗ and Vasudeva Varma Information Retrieval and Extraction Lab, IIIT Hyderabad, India {tushar.abhishek,shivprasad.sagare,bhavyajeet.singh,anubhav.sharma}@research.iiit.ac.in, {manish.gupta,vv}@iiit.ac.in Abstract Multiple critical scenarios (like Wikipedia text generation given English Infoboxes) need au- tomated generation of descriptive text in low resource (LR) languages from English fact triples. Previous work has focused on English fact-to-text (F2T) generation. To the best of our knowledge, there has been no previous at- tempt on cross-lingual alignment or generation for LR languages. Building an effective cross- lingual F2T (XF2T) system requires alignment between English structured facts and LR sen- tences. We propose two unsupervised meth- ods for cross-lingual alignment. We contribute XALIGN, an XF2T dataset with 0.45M pairs across 8 languages, of which 5402 pairs have been manually annotated. We also train strong baseline XF2T generation models on XAlign dataset

Abstract

Building a quantum secure internet is one of the most important challenges in the field of quantum technologies [1,2]. It would ensure worldwide information-theoretically secure communication. The idea of quantum repeaters [3–5] gives hope that this dream will come true. However, the level of quantum security proposed originally in a seminal article by Bennett and Brassard [6] seems to be insufficient due to the fact that on the way between an honest manufacturer and an honest user, an active hacker can change with the inner workings of a quantum device, making it totally insecure [7]. Indeed, the hardware Trojan-horse attacks on random number generators are known [8], and the active hacking on quantum devices became a standard testing approach since the seminal attack by Makarov [9]. The idea of device-independent (DI) security overcomes this obstacle [7,10] (see also [11] and references therein). Although difficult to be done in practice, it has been demonstrated quite recently in several recent experiments [12–14]. In parallel, the study of the limitations of this approach in terms of upper bounds on the distillable key has been put forward [15–18]. However, these approaches focus on pointto-point quantum device-independent secure communication. In this paper we introduce the upper bounds on the performance of the device-independent conference key agreement (DI-CKA) [19,20]. The task of the conference agreement is to distribute to N > 2 honest parties the same secure key for one-time-pad encryption. A protocol achieving this task in a device-independent manner has been shown in Ref. [20]. We set an upper bound on the performance of such protocols in a network setting. We focus on physical behaviors with N users (for arbitrary N > 2), where each user is both the sender and receiver of the behavior treated as a black box. This situation is a special case of a network describable with a multiplex quantum channel where inputs and outputs are classical with quantum phenomena going inside the physical behavior [21]. All N trusted parties have the role of both the sender to and receiver from the channel and their goal is to obtain a secret key in a device-independent way against a quantum adversary. Aiming at upper bounds on the device-independent key, we narrow the consideration to the independent and identically distributed case. In this scenario, the honest parties share n identical devices. All the N parties set (classical) inputs x = (x1,..., xN ) to each of the n shared devices P(a|x) and receive (classical) outputs a = (a1,..., aN ) from each of them. We restrict our consideration to quantum devices. Such devices are realized by certain measurements M ≡ ⊗N i=1Mxi ai on quantum states ρA1,...,AN ≡ ρN(A). We define these devices (ρN(A),M) = Tr[ρN(A) ⊗N i=1 Mxi ai ]. In this work we provide upper bounds on the deviceindependent conference key distillation rates for arbitrary multipartite states. As the first main result, we introduce a multipartite generalization of the cc-squashed entanglement provided in Ref. [22] and developed in Ref. [18]. With a little abuse of notation with respect to that used in Refs. [16,18], for the sake of the reader, we will omit the fact that the measure is multipartite as well as reduce the abbreviation cc in its name and here call it just reduced c-squashed entanglement,

Abstract

Anatomical variabilities seen in longitudinal data or inter- subject data is usually described by the underlying deformation, cap- tured by non-rigid registration of these images. Stationary Velocity Field (SVF) based non-rigid registration algorithms are widely used for reg- istration. However, these methods cover only a limited degree of defor- mations. We address this limitation and define an approximate metric space for the manifold of diffeomorphisms G. We propose a method to break down the large deformation into finite set of small sequential defor- mations. This results in a broken geodesic path on G and its length now forms an approximate registration metric. We illustrate the method using a simple, intensity-based, log-demon implementation. Validation results of the proposed method show that it can capture large and complex de- formations while producing qualitatively better results than state-of-the- art methods. The results also demonstrate that the proposed registration metric is a good indicator of the degree of deformation.

Abstract

This article proposes Convolutional Neural Network based Auto Encoder (CNN-AE) to predict location dependent rate and coverage probability of a network from its topology. We train the CNN utilising BS location data of India, Brazil, Germany and the USA and compare its performance with stochastic geometry (SG) based analytical models. In comparison to the best-fitted SG- based model, CNN-AE improves the coverage and rate prediction errors by a margin of as large as 40% and 25% respectively. As an application, we propose a low complexity, provably convergent algorithm that, using trained CNN-AE, can compute locations of new BSs that need to be deployed in a network in order to satisfy pre-defined spatially heterogeneous performance goals.

Abstract

Typically, automatic syllable stress detection is posed as a supervised classification problem, for which, a classifier is trained using manually annotated (existing) syllable data and stress labels. However, in real testing scenarios, syllable data is estimated since manual annotation is not possible. Further, the estimation process could result in a mismatch between the lengths of the estimated and the existing syllable data causing no one- to-one correspondence between the estimated syllable data and the existing labels. Hence, the existing labels and estimated syllable data together cannot be used to train the classifier. This can be avoided by manually labeling the estimated syllable data, which, however, is impractical. In contrast, we, in this work, propose a method to obtain labels for estimated syllable data without using manual annotation. The proposed method considers a weighted version of the well-known Wagner–Fisher algorithm (WFA) to assign the existing labels to the estimated syllable data, where the weights are computed based on a set of three constraints defined in the proposed algorithm. Experiments on ISLE corpus show that the performance obtained on the test set for four different types of estimated syllable data are higher when the assigned labels and estimated syllable data are used for training compared to those when existing labels and existing syllable data are used. Also, the label assignment accuracy using the proposed method is found to be higher than that using a baseline scheme based on WFA.

Abstract

The current global health emergency in the form of the Coronavirus 2019 (COVID-19) pandemic has 16 highlighted the need for fast, accurate, and efficient drug discovery pipelines. Traditional drug 17 discovery projects relying on in vitro high-throughput screening (HTS) involve large investments and 18 sophisticated experimental set-ups, affordable only to big biopharmaceutical companies. In this 19 scenario, application of efficient state-of-the-art computational methods and modern artificial 20 intelligence (AI)-based algorithms for rapid screening of repurposable chemical space [approved drugs 21 and natural products (NPs) with proven pharmacokinetic profiles] to identify the initial leads is a 22 powerful option to save resources and time. Structure-based drug repurposing is a popular in silico 23 repurposing approach. In this review, we discuss traditional and modern AI-based computational 24 methods and tools applied at various stages for structure-based drug discovery (SBDD) pipelines. 25 Additionally, we highlight the role of generative m

Abstract

Recent efforts in multi-domain learning for semantic seg- mentation attempt to learn multiple geographical datasets in a universal, joint model. A simple fine-tuning experi- ment performed sequentially on three popular road scene segmentation datasets demonstrates that existing segmenta- tion frameworks fail at incrementally learning on a series of visually disparate geographical domains. When learning a new domain, the model catastrophically forgets previously learned knowledge. In this work, we pose the problem of multi-domain incremental learning for semantic segmenta- tion. Given a model trained on a particular geographical domain, the goal is to (i) incrementally learn a new geo- graphical domain, (ii) while retaining performance on the old domain, (iii) given that the previous domain’s dataset is not accessible. We propose a dynamic architecture that assigns universally shared, domain-invariant parameters to capture homogeneous semantic features present in all do- mains, while dedicated domain-specific parameters learn the statistics of each domain. Our novel optimization strat- egy helps achieve a good balance between retention of old knowledge (stability) and acquiring new knowledge (plas- ticity). We demonstrate the effectiveness of our proposed solution on domain incremental settings pertaining to real- world driving scenes from roads of Germany (Cityscapes), the United States (BDD100k), and India (IDD).

Abstract

Infographics communicate information using a combi- nation of textual, graphical and visual elements. This work explores the automatic understanding of infographic images by using a Visual Question Answering technique. To this end, we present InfographicVQA, a new dataset comprising a diverse collection of infographics and question-answer annotations. The questions require methods that jointly rea- son over the document layout, textual content, graphical el- ements, and data visualizations. We curate the dataset with an emphasis on questions that require elementary reason- ing and basic arithmetic skills. For VQA on the dataset, we evaluate two Transformer-based strong baselines. Both the baselines yield unsatisfactory results compared to near perfect human performance on the dataset. The results sug- gest that VQA on infographics—images that are designed to communicate information quickly and clearly to human brain—is ideal for benchmarking machine understanding of complex document images. The dataset is available for download at docvqa.org