Pairs Of Objects Research Articles

Parallel disentangling network for human–object interaction detection

Human–object interaction (HOI) detection aims to localize and classify triplets of human, object and interaction from a given image. Earlier two-stage methods suffer both from mutually independent training processes and the interference of redundant negative human–object pairs. Prevailing one-stage transformer-based methods are free from the above problems by tackling HOI in an end-to-end manner. However, one-stage transformer-based methods carry the unnecessary entanglements of the query for different tasks, i.e., human–object detection and interaction classification, and thus bring in poor performance. In this paper, we propose a new transformer-based approach that parallelly disentangles human–object detection and interaction classification in a triplet-wise manner. To make each query focus on one specific task clearly, we exhaustively disentangle HOI by parallelly expanding the naive query in vanilla transformer as triple explicit queries. Then, we introduce a semantic communication layer to preserve the consistent semantic association of each HOI through mixing the feature representations of each query triplet of the correspondence constraint. Extensive experiments demonstrate that our proposed framework outperforms the existing methods and achieves the state-of-the-art performance, with significant reduction in parameters and FLOPs.

Using Object-Based Verification to Assess Improvements in Forecasts of Convective Storms between Operational HRRR Versions 3 and 4

Abstract The object-based verification procedure described in a recent paper by Duda and Turner was expanded herein to compare forecasts of composite reflectivity and 6-h precipitation objects between the two most recent operational versions of the High-Resolution Rapid Refresh (HRRR) model, versions 3 and 4, over an expanded set of warm season cases in 2019 and 2020. In addition to analyzing all objects, a reduced set of forecast–observation object pairs was constructed by taking the best forecast match to a given observation object for the purposes of bias-reduction and unequivocal object comparison. Despite the apparent signal of improved scalar metrics such as the object-based threat score in HRRRv4 compared to HRRRv3, no statistically significant differences were found between the models. Nonetheless, many object attribute comparisons revealed indications of improved forecast performance in HRRRv4 compared to HRRRv3. For example, HRRRv4 had a reduced overforecasting bias for medium- and large-sized reflectivity objects, and all objects during the afternoon. HRRRv4 also better replicated the distribution of object complexity and aspect ratio. Results for 6-h precipitation also suggested superior performance in HRRRv4 over HRRRv3. However, HRRRv4 was worse with centroid displacement errors and more severely overforecast objects with a high maximum precipitation amount. Overall, this exercise revealed multiple forecast deficiencies in the HRRR, which enables developers to direct development efforts on detailed and specific endeavors to improve model forecasts. Significance Statement This work builds upon the authors’ prior work in assessing model forecast quality using an alternative verification method—object-based verification. In this paper we verified two versions of the same model (one an upgrade from the other) that were making forecasts covering the same time window, using the object-based verification method. We found that the updated model was not statistically significantly better, although there were indications it performed better in certain aspects such as capturing the change in the number of storms during the daytime. We were able to identify specific problem areas in the models, which helps us direct model developers in their efforts to further improve the model.

Entity–relation triple extraction based on relation sequence information

Data overlap is a significant challenge in the task of entity–relation triple extraction. This task includes two research lines, line one first identifies entities and then predicts relations while line two completely shuffles the order. The methods in line two are more conducive to the optimization of the data overlap problem. Recent works have made breakthroughs in dealing with overlapping data, but there are still some defects such as difficulty in convergence and poor performance on datasets with numerous relations. To solve the above problems, we adopt a two-step strategy of first extracting subjects, and then predicting relation–object pairs. Considering the absence of connectivity between the two steps in the conventional method, we adopt the relation sequence as input in both steps and propose the TERS model. The relation sequence can connect two steps and improve the single-step and comprehensive extraction capability of the model. The TERS model consists of two modules. The first module performs information interaction and filters invalid subjects through the Text Relation Attention method. The second module implements multiple iterations of information interaction through the Information Flow method. The combination of these two modules contributes to the strong entity–relation triple extraction capability of our model. We evaluate our method on three public datasets. Extensive experiments show that our TERS model outperforms previous state-of-the-art models in triple extraction and overlapping data processing. Compared with other two-step extraction models, the advantages of our model are more obvious.

Equal parallel and cone-beam projections: a curious property of D-symmetric object functions

In tomographic image reconstruction, the object density function is the unknown quantity whose projections are measured by the scanner. In the three-dimensional case, we define the D-reflection of such a density function as the object obtained by a particular weighted reflection about the plane z = D, and a D-symmetric function as one whose D-reflection is equal to itself. D-symmetric object functions have the curious property that their parallel projection onto the detector plane z = D is equal to their cone-beam projection onto the same detector with x-ray source location at the origin. Much more remarkable is the additional fact that for any fixed D-symmetric object, every oblique parallel projection onto this same detector plane equals the cone-beam projection for a corresponding source location. The mathematical proof is straight forward but not particularly enlightening, and we also provide here an alternative physical demonstration that explains the various weighting terms in the context of classical tomosynthesis. Furthermore, we clarify the distinction between the new formulation presented here, and the original formulation of Edholm and co-workers who obtained similar properties but for a pair of objects whose divergent and parallel projections matched, but with no D-symmetry. We do not claim any immediate imaging application or useful physics from these notions, but we briefly comment on consequences for methods that apply data consistency conditions in image reconstruction.

Too much to handle? Interference from distractors with similar affordances on target selection for handled objects.

The existence of handle affordances has been classically demonstrated using the Stimulus-Response Compatibility paradigm, with shorter response times when the orientation of the object handle and the response hand are compatible in comparison to incompatible. Yet the activation of handle affordances from visual objects has been investigated in very simple situations involving single stimulus and motor response. As natural perceptual scenes are usually composed of multiple objects that could activate multiple affordances, the consequence of multiple affordance activation on the perception and processing of a given object of the scene requires more investigation. The aim of this study was to determine the impact of distractor affordances on the processing of a target object in situations involving several familiar graspable objects. In two online experiments, 229 participants had to select a target object (the kitchen utensil or the tool) in a visual scene displaying a pair of objects. They performed left key presses when the target was on the left and right key presses when the target was on the right. Target handle orientation and response side could be compatible or incompatible. Critically, target and distractor objects had similar or dissimilar handle affordances, with handles oriented for left- or right-hand grasps. Results from the two experiments showed slower response times when target and distractor objects had similar handle affordances in comparison to dissimilar affordances, when participants performed right hand responses and when target orientation and response were compatible. Thus, affordance similarity between objects may interfere rather than facilitate object processing and slow down target selection. These findings are in line with models of affordance and object selection assuming automatic inhibition of distractors' affordances for appropriate object interaction.

The VLT MUSE NFM view of outflows and externally photoevaporating discs near the orion bar★

ABSTRACT We present Very Large Telescope/Multi-Unit Spectroscopic Explorer Narrow Field Mode observations of a pair of disc-bearing young stellar objects towards the Orion Bar: 203–504 and 203–506. Both of these discs are subject to external photoevaporation, where winds are launched from their outer regions due to environmental irradiation. Intriguingly, despite having projected separation from one another of only 1.65 arcsec(660 au at 400 pc), 203–504 has a classic teardrop shaped ‘proplyd’ morphology pointing towards θ2 Ori A (indicating irradiation by the EUV of that star, rather than $\rm \theta ^1$ Ori C) but 203–506 has no ionization front, indicating it is not irradiated by stellar EUV at all. However, 203–506 does show [C i] 8727 Å and [O i] 6300 Å in emission, indicating irradiation by stellar FUV. This explicitly demonstrates the importance of FUV irradiation in driving mass loss from discs. We conclude that shielding of 203–506 from EUV is most likely due to its position on the observers side of an ionized layer lying in the foreground of the Huygens Region. We demonstrate that the outflow HH 519, previously thought to be emanating from 203–504 is actually an irradiated cloud edge and identify a new compact outflow from that object approximately along our line of sight with a velocity ∼130 km s−1.

A new statistical method for the comparison of biplots with the same objects and variables

Ordinations are compared most commonly by Procrustes methods applicable to points belonging to the same domain, either the objects or the variables describing them. However, no published approach applies to biplots which visualize principal component ordinations of objects and variables simultaneously.To fill this gap, this paper provides a new procedure based on two fundamental, scale-invariant properties of biplots: the cosine of the angle between the vectors pointing to every pair of objects and variables and the mean of the relative length of the two vectors. The method applies to situations in which the number of objects is the same in all ordinations, the number of variables is also the same and, additionally, there is one-to-one correspondence between the points in the different ordinations. The new method is illustrated with two artificial examples and is also applied to the comparison of biplots obtained from real field data representing samples repeated in the same locations over time.It is demonstrated that the new method reveals the similarities and differences between alternative biplots obtained for a given set of objects and variables.We expect that, thanks to the widespread use of principal component analysis in science, the method will receive applications in any studies in which interest lies in the comparison of simultaneous ordinations of objects and variables.

Libertarianism and agentive experience

AbstractLibertarianism about free will conjoins the thesis that free will requires indeterminism with the thesis that we have free will. Here the claim that we have experiential evidence for the libertarian position is assessed. It is argued that, on a straightforward reading, the claim is false, for our experiences as agents don't support the claim that free will requires indeterminism. However, our experiences as agents may still have a role to play in an overall case for libertarianism, insofar as they give us some (defeasible) reason to think that we have free will. This latter claim is defended against a pair of objections that have been leveled against it.

Does that make sense? – The impact of semantic relationships between object pairs on the age-related associative memory deficit

Does that make sense? – The impact of semantic relationships between object pairs on the age-related associative memory deficit

Nonparametric clustering of RNA‐sequencing data

AbstractIdentification of clusters of co‐expressed genes in transcriptomic data is a difficult task. Most algorithms used for this purpose can be classified into two broad categories: distance‐based or model‐based approaches. Distance‐based approaches typically utilize a distance function between pairs of data objects and group similar objects together into clusters. Model‐based approaches are based on using the mixture‐modeling framework. Compared to distance‐based approaches, model‐based approaches offer better interpretability because each cluster can be explicitly characterized in terms of the proposed model. However, these models present a particular difficulty in identifying a correct multivariate distribution that a mixture can be based upon. In this manuscript, we review some of the approaches used to select a distribution for the needed mixture model first. Then, we propose avoiding this problem altogether by using a nonparametric MSL (maximum smoothed likelihood) algorithm. This algorithm was proposed earlier in statistical literature but has not been, to the best of our knowledge, applied to transcriptomics data. The salient feature of this approach is that it avoids explicit specification of distributions of individual biological samples altogether, thus making the task of a practitioner easier. We performed both a simulation study and an application of the proposed algorithm to two different real datasets. When used on a real dataset, the algorithm produces a large number of biologically meaningful clusters and performs at least as well as several other mixture‐based algorithms commonly used for RNA‐seq data clustering. Our results also show that this algorithm is capable of uncovering clustering solutions that may go unnoticed by several other model‐based clustering algorithms. Our code is publicly available on Github at https://github.com/Matematikoi/non_parametric_clustering

Adjunctive three-way concepts from positive and negative concepts in lattice-valued formal contexts

Three-way concept analysis is an integration of formal concept analysis and three-way decision, which has been found wide applications in knowledge representation, cognitive computing and decision sciences. There have been already a huge number of literature on theory and applications on such topics. Most researches on formal concept analysis focus, independently, on specific scenarios such as Boolean formal contexts and fuzzy formal contexts. In this paper, a unified framework for three-way concept analysis is built in lattice-valued formal contexts. The notions of positive concept and negative concept are given in a lattice-valued formal context based on an overlapping function, one of significant operators for information fusion. Two pairs of object induced adjunctive three-way concept operators and attribute induced adjunctive three-way concept operators are introduced. Their properties have been fully investigated. With those operators, the algebraic structures of adjunctive three-way concepts, their extensions and intensions have been explored. Specifically, the local structure within pairs of sub-concept and sup-concept has been finely characterized. The derived results provide ones a way to construct the complete lattice of a lattice-valued formal context or its sublattice by determining all pairs of sub-concept and sup-concept provided that an object fuzzy set or an attribute fuzzy set is given. A case analysis on a real world dataset from UCI repository is presented to verify the rationality and significance of obtained results.

Circumgalactic Lyα Nebulae in Overdense Quasar Pair Regions Observed with the Palomar Cosmic Web Imager

The recent discovery of enormous Lyα nebulae (ELANe), characterized by physical extents >200 kpc and Lyα luminosities >1044 erg s−1, provides a unique opportunity to study the intergalactic medium and circumgalactic medium in distant galaxies. Many existing ELANe detections are associated with local overdensities of active galactic nuclei (AGN). We have initiated a search for ELANe around regions containing pairs of quasi-stellar objects (QSOs) using the Palomar Cosmic Web Imager. The first study of this search, Cai et al., presented results of ELAN0101+0201, which was associated with a QSO pair at z = 2.45. In this study, all targets residing in QSO pair environments analyzed have Lyα detections, but only one of the four targets meets the classification criteria of an ELANe associated with a QSO pair region (z ∼ 2.87). The other three sample detections of Lyα nebulae do not meet the size and luminosity criteria to be classified as ELANe. We find kinematic evidence that the ELANe J1613 is possibly powered mostly by AGN outflows. The analysis of circularly averaged surface brightness profiles of emission from the Lyα regions shows that the Lyα emission around z ∼ 2 QSO pairs is consistent with emission around individual QSOs at z ∼ 2, which is fainter than that around z ∼ 3 QSOs. A larger sample of Lyα at z ∼ 2 will be needed to determine if there is evidence of redshift evolution when compared to nebular emissions at z ∼ 3 from other studies.

Optimizing Multiple Simultaneous Objectives for Voting and Facility Location

We study the classic facility location setting, where we are given n clients and m possible facility locations in some arbitrary metric space, and want to choose a location to build a facility. The exact same setting also arises in spatial social choice, where voters are the clients and the goal is to choose a candidate or outcome, with the distance from a voter to an outcome representing the cost of this outcome for the voter (e.g., based on their ideological differences). Unlike most previous work, we do not focus on a single objective to optimize (e.g., the total distance from clients to the facility, or the maximum distance, etc.), but instead attempt to optimize several different objectives simultaneously. More specifically, we consider the l-centrum family of objectives, which includes the total distance, max distance, and many others. We present tight bounds on how well any pair of such objectives (e.g., max and sum) can be simultaneously approximated compared to their optimum outcomes. In particular, we show that for any such pair of objectives, it is always possible to choose an outcome which simultaneously approximates both objectives within a factor of 1 plus square root of 2, and give a precise characterization of how this factor improves as the two objectives being optimized become more similar. For q>2 different centrum objectives, we show that it is always possible to approximate all q of these objectives within a small constant, and that this constant approaches 3 as q increases. Our results show that when optimizing only a few simultaneous objectives, it is always possible to form an outcome which is a significantly better than 3 approximation for all of these objectives.

Semi-supervised hierarchical ensemble clustering based on an innovative distance metric and constraint information

Agglomerative Hierarchical Clustering (AHC) is a bottom-up clustering strategy in which each object is originally a cluster, and more pairs of clusters are formed by traversing the hierarchy. It has been proven that there is no individual AHC clustering algorithm that can be efficient in all situations. In order to address this problem, ensemble clustering techniques have been introduced. These techniques combine the results of several output partitions to achieve a consensus with higher accuracy compared to an individual clustering algorithm. This paper proposes an AHC-based ensemble semi-supervised clustering algorithm to improve performance. In semi-supervised clustering, class membership information is used in some objects. Here, we introduce the Semi-Supervised Ensemble Hierarchical Clustering based on Constraints Information (SSEHCCI) algorithm. SSEHCCI is developed using several individual clustering algorithms based on AHC. SSEHCCI includes a flexible weighting policy to generate base partitions and uses the constraints information to configure the semi-supervised clustering. In addition, SSEHCCI uses an innovative distance measure to calculate the distance between each pair of objects. Experimental results show that SSEHCCI performs better than existing semi-supervised algorithms on some University of California Irvine (UCI) datasets. Specifically, we observed an average accuracy of SSEHCCI compared to SSDC and RSSC of 2.6% and 1.8%, respectively.

Trouble no more: how non-truth-functionality makes the alethic indeterminacy solution to the Liar Paradox viable

ABSTRACT Jay Newhard [2021. “Alethic Undecidability and Alethic Indeterminacy.” Synthese 199: 2563–2574. doi:10.1007/s11229-020-02900-z] proposes a novel solution to the Liar Paradox, which he calls the alethic indeterminacy solution to the Liar Paradox. Bradley Armour-Garb [2021. “Troubles for Alethic Indeterminacy.” Inquiry. doi:10.1080/0020174X.2021.1932166] raises a pair of objections to the alethic indeterminacy solution. Both objections are based upon the alethic indeterminacy solution’s alleged commitment that the truth conditions for a Liar Sentence are indeterminate, and therefore not true. In this paper, this alleged commitment is shown to be mistaken. The alethic indeterminacy solution is compatible with maintaining that the truth conditions for a Liar Sentence are a non-truth-functional biconditional which is true, and not indeterminate. Two independent accounts of non-truth-functional biconditionals are defended. The first account is based on the claim that indicative conditionals express a non-truth-functional dependency relation between consequent and antecedent. The second account is based upon connected sentences having interdependent truth conditions, which can occur with any polyadic connective. These accounts are fully general, not ad hoc measures. Each account solves both of Armour-Garb’s objections. With both objections met, the alethic indeterminacy solution is shown to be a viable solution to the Liar Paradox worth further development.

Multiple visual objects are represented differently in the human brain and convolutional neural networks

Objects in the real world usually appear with other objects. To form object representations independent of whether or not other objects are encoded concurrently, in the primate brain, responses to an object pair are well approximated by the average responses to each constituent object shown alone. This is found at the single unit level in the slope of response amplitudes of macaque IT neurons to paired and single objects, and at the population level in fMRI voxel response patterns in human ventral object processing regions (e.g., LO). Here, we compare how the human brain and convolutional neural networks (CNNs) represent paired objects. In human LO, we show that averaging exists in both single fMRI voxels and voxel population responses. However, in the higher layers of five CNNs pretrained for object classification varying in architecture, depth and recurrent processing, slope distribution across units and, consequently, averaging at the population level both deviated significantly from the brain data. Object representations thus interact with each other in CNNs when objects are shown together and differ from when objects are shown individually. Such distortions could significantly limit CNNs’ ability to generalize object representations formed in different contexts.

An understanding of falling bodies across schooling and experience based on the conceptual prevalence framework

In this article, we describe a study conducted online with 953 participants of varying levels of education and, when applicable, science/physics teaching experience. These participants were asked to solve a cognitive task in which many different pairs of objects were presented and to identify which, if any, would touch the ground first when dropped (in atmospheric or non-atmospheric environments). Recorded accuracies and response times allowed us to conduct an analysis based on the conceptual prevalence framework, which posits that the coexistence of conceptual and/or misconceptual resources can produce interference in response production. The results show that the influence of some of them decreases or, more surprisingly, increases with training. In fact, secondary and college physics teachers seem to cultivate some of them, and most likely have contributed to their spread. The implications for teaching and research are discussed.

Groupoids and skeletal categories form a pretorsion theory in [formula omitted

We describe a pretorsion theory in the category Cat of small categories: the torsion objects are the groupoids, while the torsion-free objects are the skeletal categories, i.e., those categories in which every isomorphism is an automorphism. We infer these results from two unexpected properties of coequalizers in Cat that identify pairs of objects: they are faithful and reflect isomorphisms.

Human–object interaction prediction in videos through gaze following

Understanding the human–object interactions (HOIs) from a video is essential to fully comprehend a visual scene. This line of research has been addressed by detecting HOIs from images and lately from videos. However, the video-based HOI anticipation task in the third-person view remains understudied. In this paper, we design a framework to detect current HOIs and anticipate future HOIs in videos. We propose to leverage human gaze information since people often fixate on an object before interacting with it. These gaze features together with the scene contexts and the visual appearances of human–object pairs are fused through a spatio-temporal transformer. To evaluate the model in the HOI anticipation task in a multi-person scenario, we propose a set of person-wise multi-label metrics. Our model is trained and validated on the VidHOI dataset, which contains videos capturing daily life and is currently the largest video HOI dataset. Experimental results in the HOI detection task show that our approach improves the baseline by a great margin of 36.3% relatively. Moreover, we conduct an extensive ablation study to demonstrate the effectiveness of our modifications and extensions to the spatio-temporal transformer. Our code is publicly available on .

Raster Intervals: An Approximation Technique for Polygon Intersection Joins

Many data science applications, most notably Geographic Information Systems, require the computation of spatial joins between large object collections. The objective is to find pairs of objects that intersect, i.e., share at least one common point. The intersection test is very expensive especially for polygonal objects. Therefore, the objects are typically approximated by their minimum bounding rectangles (MBRs) and the join is performed in two steps. In the filter step, all pairs of objects whose MBRs intersect are identified as candidates; in the refinement step, each of the candidate pairs is verified for intersection. The refinement step has been shown notoriously expensive, especially for polygon-polygon joins, constituting the bottleneck of the entire process. We propose a novel approximation technique for polygons, which (i) rasterizes them using a fine grid, (ii) models groups of nearby cells that intersect a polygon as an interval, and (iii) encodes each interval by a bitstring that captures the overlap of each cell in it with the polygon. We also propose an efficient intermediate filter, which is applied on the object approximations before the refinement step, to avoid it for numerous object pairs. Via experimentation with real data, we show that the end-to-end spatial join cost can be reduced by up to one order of magnitude with the help of our filter and by at least three times compared to using alternative intermediate filters.