Abstract

We propose the ViNet architecture for audiovisual saliency prediction. ViNet is a fully convolutional encoder-decoder architecture. The encoder uses visual features from a network trained for action recognition, and the decoder infers a saliency map via trilinear interpolation and 3D convolutions, combining features from multiple hierarchies. The overall architecture of ViNet is conceptually simple; it is causal and runs in real-time (60 fps). ViNet does not use audio as input and still outperforms the state-of-the-art audio-visual saliency prediction models on nine different datasets (three visual-only and six audio-visual datasets). ViNet also surpasses human performance on the CC, SIM and AUC metrics for the AVE dataset, and to our knowledge, it is the first model to do so. We also explore a variation of ViNet architecture by augmenting audio features into the decoder. To our surprise, upon sufficient training, the network becomes agnostic to the input audio and provides the same output irrespective of the input. Interestingly, we also observe similar behaviour in the previous state-of-the-art models [1] for audio-visual saliency prediction. Our findings contrast with previous works on deep learning-based audio-visual saliency prediction, suggesting a clear avenue for future explorations incorporating audio in a more effective manner. The code and pre-trained models are

Abstract

We consider the problem of learning low-rank tensors from partial observations with structural constraints, and propose a novel factorization of such tensors, which leads to a simpler optimization problem. The resulting problem is an optimization problem on manifolds. We develop first-order and second-order Riemannian optimization algorithms to solve it. The duality gap for the resulting problem is derived, and we experimentally verify the correctness of the proposed algorithm. We demonstrate the algorithm on nonnegative constraints and Hankel constraints

Abstract

The paper introduces the novel Modular Pipe Climber III with a Three-Output Open Differential (3-OOD) mechanism to eliminate slipping of the tracks due to the changing cross-sections of the pipe. This will be achieved in any orientation of the robot. Previous pipe climbers use three-wheel/track modules, each with an individual driving mechanism to achieve stable traversing. Slipping of tracks is prevalent in such robots when it encounters the pipe turns. Thus, active control of each module’s speed is employed to mitigate the slip, thereby requiring substantial control effort. The proposed pipe climber implements the 3-OOD to address this issue by allowing the robot to mechanically modulate the track speeds as it encounters a turn. The proposed 3-OOD is the first three-output differential to realize the functional abilities of a traditional two-output differential.

Abstract

In this paper, we explore Probabilistic Inverse Velocity Obstacle (PIVO) as an alternative to probabilistic versions of Velocity Obstacles (PVO) for free flying quadrotor systems. Inverse Velocity Obstacles compute effective controls from a sequence of observations on other agents without the need to access ego state information. As a direct consequence of this the ego state noise is not entailed in probabilistic formulations bringing in verifiable advantages in the form of reduced path lengths, less conservative maneuvers, reduced occurrences of stopping/hovering to let others pass. These advantages are vividly tabulated in this paper, showcasing the efficacy of PIVO as an alternative to probabilistic versions of Velocity Obstacles. In particular we show the benefits of PIVO over PVO in relation to sample complexity as well as overall trajectory lengths. We also show the efficacy of our probabilistic formulation in handling non-parametric and often multimodal noise distributions.

Abstract

Discourse parsing, which involves understand- ing the structure, information flow, and mod- eling the coherence of a given text, is an im- portant task in natural language processing. It forms the basis of several natural language pro- cessing tasks such as question-answering, text summarization, and sentiment analysis. Dis- course unit segmentation is one of the funda- mental tasks in discourse parsing and refers to identifying the elementary units of text that combine to form a coherent text. In this pa- per, we present a transformer based approach towards the automated identification of dis- course unit segments and connectives. Early approaches towards segmentation relied on rule-based systems using POS tags and other syntactic information to identify discourse seg- ments. Recently, transformer based neural sys- tems have shown promising results in this do- main. Our system, SegFormers, employs this transformer based approach to perform multi- lingual discourse segmentation and connective identification across 16 datasets encompassing 11 languages and 3 different annotation frame- works. We evaluate the system based on F1 scores for both tasks, with the best system re- porting the highest F1 score of 97.02% for the treebanked English RST-DT dataset

Abstract

We present our work in using enhanced sampling method of metadynamics in combination with machine learning techniques to speed-up the exploration of all relevantphase space of biomolecular systems that keeps the two related tasks separate: (a) collective variable should cluster configurations into correct states, that is, classify states accurately and (b) collective variable should improve the local sampling in the ‘current free energy basin’, that is, shape the collective variable in line with the data collected (regression). We demonstrate the method on the alanine tetrapeptide system in explicit solvent. We use Elliptic Envelope (EE) classifier to identify outliers from a particular class, and each class will use a different fully-connected autoencoder (ANC) whose bottleneck layer (latent variable) will be used as collective variable in Well-Tempred Metadynamics simulation to generate more data. Comparison against benchmark indicate that the proposed scheme can traverse all relevant phase space

Abstract

Research and fabrication of micro devices hold the key to low power devices, sensors and lab-on-a-chip systems which are in much need today for diagnosis, IOT etc. Cost of setting up a fabrication laboratory and conducting photolithography is high due to need of expensive equipment. We present a design of low-cost UV exposure system which can be used for both high resolution and low resolution photolithography. In first part, we present the study of irradiance distribution patterns of different UV LED arrangements. We use uniformity as a criterion for selecting the arrangement that gives the best illumination uniformity in largest area. The maximum, minimum and average exposure energy and uniformity have been presented. Using these results, we present an optimal system design for UV photolithography. The novelty of our work is simulating the UV exposure system for different parameters for making an optimal choice for a versatile system (high energy & low energy), different uniformity for different resolution to save power and have better control.

Abstract

Sexism, a prejudice that causes enormous suffering, manifests in blatant as well as subtle ways. As sexist content towards women is increasingly spread on social networks, the automatic detection and categorization of these tweets/posts can help social scientists and policymakers in research, thereby combating sexism. In this paper, we explore the problem of detecting whether a Twitter/Gab post is sexist or not. We further discriminate the detected sexist post into one of the fine-grained sexism categories. We propose a neural model for this sexism detection and classification that can combine representations obtained using RoBERTa model and linguistic features such as Empath, Hurtlex, and Perspective API by involving recurrent components. We also leverage the unlabeled sexism data to infuse the domain-specific transformer model into our framework. Our proposed framework also features a knowledge module comprised of emoticon and hashtag representations to infuse the external knowledge-specific features into the learning process. Several proposed methods outperform various baselines across several standard metrics.

Abstract

Machine learning (ML) methods enable computers to address problems by learning from existing data. Such applications are becoming commonplace in molecular sciences. Interest in applying ML techniques across chemical compound space, from predicting properties to designing molecules and materials is in the surge. Especially, ML models have started to accelerate computational chemistry, and are often as accurate as state‐of‐the‐art electronic/atomistic models. Being an integral part of the ML architecture, representation of a molecular entity, uniquely encoded, plays a crucial role to what extent an ML model would be accurately predicting the desired property. This review aims to demonstrate a hierarchy of representations which has been introduced, to capture all degrees of freedom of a molecule or an atom the best, to map the quantum mechanical properties. We discuss their diverse applications how …

Abstract

This article describes an experiment to evaluate the impact of different types of ellipses discussed in theoretical linguistics on Neural Machine Translation (NMT), using English to Hindi/Telugu as source and target languages. Evaluation with manual methods shows that most of the errors made by Google NMT are located in the clause containing the ellipsis, the frequency of such errors is slightly more in Telugu than Hindi, and the translation adequacy shows improvement when ellipses are reconstructed with their antecedents. These findings not only confirm the importance of ellipses and their resolution for MT, but also hint toward a possible correlation between the translation of discourse devices like ellipses with the morphological incongruity of the source and target. We also observe that not all ellipses are translated poorly and benefit from reconstruction, advocating for a disparate treatment of different ellipses in MT research.