Multiple Objects Of Interest Research Articles

"Thunders of White Silence": Racialized Ways of Seeing and "Hiram Powers' Greek Slave"

"Thunders of White Silence":Racialized Ways of Seeing and "Hiram Powers' Greek Slave" Tricia Lootens (bio) Victorian poetry, visuality, race, racialization: where better to explore these topics' convergence than in this special issue of Victorian Poetry? Now, as students of Victorian studies are increasingly challenging disciplinary traditions of refusing to "see" race, perhaps especially where poetry is concerned,1 visuality's relations to poetics seem poised to emerge as invaluable resources for moving beyond long-standing, if often tacit, training in evasive, exclusionary reading.2 Here, in turning towards those relations, I'll be tracing a sharp, idiosyncratic line through an increasingly rich, expansive constellation of critical and poetic writings and disciplinary fields.3 "What is 'Victorian poetry'? How do we know? And who are "we"?: blunt as these questions are, they carry a gathering urgency. They drive conversations at once speculative, structural, passionately theoretical—and, in all these things, distinctly everyday.4 Here, I'd like to approach such conversations from odd angles, in part through a series of sharply defined invitational gestures. Each plays out through some form of materializing visualization; all have been inspired by Kyla Wazana Tompkins's recent questions to readers of PMLA. "How promiscuously sensual can we be in relation to the literary?" Tompkins asks: "What is the place of literature in the forming, schooling, and historical disciplining of the senses? Here I would call for a deeply disciplinary interdisciplinarity or even antidisciplinarity, by which I mean a close listening to our multiple objects of interest as they travel across history, across borders, and between media."5 "More, more, more;" Tompkins goes on to urge: "can we not make and have more than we do now?" (p. 422). ________ Intense, intimate, and still largely unexplored, connections between antislavery poetics and Victorian visual culture strike straight to the heart of nineteenth-century textuality.6 Consider, for example, one instance in shockingly plain [End Page 493] view. No Victorian image of the Middle Passage now draws more attention than J. M. W. Turner's 1840 Slavers Throwing Overboard the Dead and Dying—Typhon Coming On.7 Still, what have Victorian literary scholars made of Turner's poetry? Very little, despite Turner's self-presentation, through the official 1840 Royal Academy Exhibition catalogue, as a poet-painter. Catalogue in hand, first-time viewers would have approached Turner's notorious image literally bearing these printed lines: Aloft all hands, strike the top-masts and belay;Yon angry setting sun and fierce-edged clouds Declare the Typhon's coming. Before it sweep your decks, throw overboard The dead and dying—ne'er heed their chains. Hope, Hope, fallacious Hope! Where is thy market now? MS. Fallacies of Hope.8 Outside Victorian poetic studies, this strange, disturbing catalog entry has hardly been secret. By 1964, the art historian Jerrold Ziff could already refer to it as showcasing "perhaps Turner's most famous (or infamous?) lines of poetry" (p. 341); in 2020, Laura Brace, a specialist in history, politics, and international diplomatic relations, was still setting Turner's verse, astutely analyzed, at the center of an ambitious revisiting of interdisciplinary controversies around Turner's painting.9 The pattern is an old one: repeatedly, scholars in other fields, not least art history, have led the way in addressing questions of race and enslavement in Victorian poetry. Where might literary specialists move in following their leads? In part, perhaps, toward the very origins of British poetry's relations to abolitionist iconography. Among art historians, after all, two works by George Morland, Execrable Human Traffick (1788) and European Ship Wrecked on the Coast of Africa (1788–1790), now stand as the "first explicitly anti-slavery paintings in Western art."10 Among literary specialists, these same paintings have yet to claim their place as precedents for antislavery iconography's deep historical links to verse. Still, they might. For however clearly the painter's friend William Collins may have overstated in attributing inspiration for Morland's painted scenes to his own poem The Slave Trade, by the time Morland's images came into print, they did so on pages shaped by excerpts from Collins's verse (Gamer, pp. 306–308). To read Turner in light of...

Semantic-Aware Dense Representation Learning for Remote Sensing Image Change Detection

Supervised deep learning models depend on massive labeled data. Unfortunately, it is time-consuming and labor-intensive to collect and annotate bitemporal samples containing desired changes. Transfer learning from pre-trained models is effective to alleviate label insufficiency in remote sensing (RS) change detection (CD). We explore the use of semantic information during pre-training. Different from traditional supervised pre-training that learns the mapping from image to label, we incorporate semantic supervision into the self-supervised learning (SSL) framework. Typically, multiple objects of interest (e.g., buildings) are distributed in various locations in an uncurated RS image. Instead of manipulating image-level representations via global pooling, we introduce point-level supervision on per-pixel embeddings to learn spatially-sensitive features, thus benefiting downstream dense CD. To achieve this, we obtain multiple points via class-balanced sampling on the overlapped area between views using the semantic mask. We learn an embedding space where background and foreground points are pushed apart, and spatially aligned points across views are pulled together. Our intuition is the resulting semantically discriminative representations invariant to irrelevant changes (illumination and unconcerned land covers) may help change recognition. We collect large-scale image-mask pairs freely available in the RS community for pre-training. Extensive experiments on three CD datasets verify the effectiveness of our method. Ours significantly outperforms ImageNet pre-training, in-domain supervision, and several SSL methods. Empirical results indicate our pre-training improves the generalization and data efficiency of the CD model. Notably, we achieve competitive results using 20% training data than baseline (random initialization) using 100% data. Our code is available.

Measuring vertical displacement using laser lines and cameras

Measuring displacements in model tests typically involves contact-based sensors such as linear potentiometers, where contact between two moving parts occurs at the sensing point. The sensor's finite mass, the limited stiffness of the beams and the clamping mechanism, and the slippage and hinging of the sensor body could affect the object's response and lead to measurement errors. Also, the physical mounting rack required to hold these sensors often obstructs the view and makes significant areas unavailable for conducting some other essential investigations. The advancement in high-speed, high-resolution and reasonably priced rugged cameras makes it feasible to obtain better displacement measurements by image analysis. This paper introduces a non-contact method that works by video recording the projection of laser lines on a test object to measure static and dynamic vertical displacements. The technique produces a continuous settlement distribution along the laser line passing through multiple objects of interest. This paper presents the theory for converting laser line images to displacements. The new method's validity is demonstrated by comparing the results from other measurement techniques: hand measurements, linear potentiometers and three-dimensional stereophotogrammetry.

Multilabel Aerial Image Classification With a Concept Attention Graph Neural Network

Compared with natural images, aerial images collected by satellite sensors/aerial cameras can provide a much larger field of view and often contain multiple objects of interest (multiple labels). There are certain limitations of existing multilabel aerial image classification methods. First, label correlations were often ignored in previous MAIC work, and thus, multilabel classifiers failed to be self-adapted. Second, existing multilabeled data sets for aerial images only cover limited images with fixed labels. Therefore, the underlying semantic correlations of labels cannot be fully included, while such correlation information is implicitly used as common knowledge by human beings. To tackle these concerns, we propose a novel multilabel classification method for aerial images. Our contributions are twofold. First, as the first attempt, label correlations are inferred from both the specific data set and ConceptNet (a popular knowledge graph for common sense). Second, based on graph neural network (GNN), we propose a novel end-to-end aerial image classification model, named the multiple label concept graph (ML-CG). ML-CG builds a concept graph to describe the semantic correlations from both the label set and the ConceptNet. We also incorporate both semantic attention and label attention in the GNN to better extract meaningful information of image labels. Compared with state-of-the-art methods, the effectiveness of the proposed method is demonstrated on both the commonly used UCM data set and a recently proposed DFC15 data set with high image resolution.

A model that adopts human fixations explains individual differences in multiple object tracking

In many settings “keep your eye on the ball” is good advice. People fixate important objects to obtain high quality information. Perhaps equally often, however, we engage with multiple important, moving, and unpredictable objects. Where should we fixate in these situations, and where do we? Do we for example appropriately center fixations to manage spatial non-uniformity in our visual system? And do we fixate empty space strategically to gain as much information as possible about multiple objects of interest? We explored these issues in the context of Multiple Object Tracking (MOT), wherein observers track several moving objects (targets) within a larger set of moving objects (nontargets), all the objects physically indistinguishable from one another. Among the features that make MOT an interesting paradigm is that it cannot be accommodated by continuous gaze to one important object, because there are multiple such objects in a given trial. Instead, it demands sustained processing of inputs from an entire display and iterated inferences about target versus nontarget identities. MOT therefore demands a strategic interaction between eye movements and cognition: the observer should seek fixation locations that minimize the aggregate probability of confusing any target with any nontarget. Individuals who meet this fixation challenge should perform the task better than those who meet the challenge less effectively. Here we describe a probabilistic model that implements the basic computations needed to do MOT, estimating the positions of targets, predicting their future positions, and inferring correspondences between new inputs and represented targets. The quality of the input received by the model depends on its fixation location at a given moment. We simulated a group of fifty participants who all performed the same MOT trials, with the model adopting each observer's fixation locations in the respective simulations. The model reliably predicted individual participant tracking performances and their relative rankings within the cohort. The results suggest that an individual's relative capability in this cognitively demanding task is in part determined by his/her utilization of eye fixations to control the quality and relevance of incoming visual input.

Image editing by object-aware optimal boundary searching and mixed-domain composition

When combining very different images which often contain complex objects and backgrounds, producing consistent compositions is a challenging problem requiring seamless image editing. In this paper, we propose a general approach, called object-aware image editing, to obtain consistency in structure, color, and texture in a unified way. Our approach improves upon previous gradient-domain composition in three ways. Firstly, we introduce an iterative optimization algorithm to minimize mismatches on the boundaries when the target region contains multiple objects of interest. Secondly, we propose a mixed-domain consistency metric for measuring gradients and colors, and formulate composition as a unified minimization problem that can be solved with a sparse linear system. In particular, we encode texture consistency using a patch-based approach without searching and matching. Thirdly, we adopt an object-aware approach to separately manipulate the guidance gradient fields for objects of interest and backgrounds of interest, which facilitates a variety of seamless image editing applications. Our unified method outperforms previous state-of-the-art methods in preserving global texture consistency in addition to local structure continuity.

Joint Exploration and Tracking: JET

Exploration and tracking by a team of robots have traditionally been considered as two separate problems solved in two phases: explore then track. This letter solves the multi-robot multi-object exploration and tracking problems simultaneously. A hierarchical architecture is used to coordinate robotic agents in the tracking of multiple objects of interest (OIs) while simultaneously allowing the task to remain computationally efficient. The primary contributions of this letter are probabilistic guarantees on tracking performance, automatic discovery of new OIs, a seamless transition from exploration to tracking, and the automatic balancing of exploration and tracking.

Multiscale model-based feature extraction in structural texture images

We deal with the problem of time-efficient extraction of structural features in a large class of structural texture images. The proposed approach of multiscale morphological texture modeling describes explicitly and concisely both shape and intensity parameters in the structural texture model. The modeling is based on a morphological skeletal representation of structural texture cells as objects of interest and the genomic growth of a texture region starting from a seed cell. This representation offers the advantage of concise description of texture cells as compared to the existing edge-based or contour-based approaches. A computationally efficient estimation of the structural texture parameters for texture segmentation tasks is proposed. The model parameter estimation and subsequent feature extraction rely on cell localization and scale-based locally adaptive binarization of the localized cells using isotropic matched filtering. The multiscale isotropic matched filter (MIMF) provides a scale- and orientation-invariant detection of structural cells regarded as multiple objects of interest in texture regions. Results of experiments pertaining to the parameter estimation from synthetic and real texture images as well as the segmentation of texture regions based on structural features are also provided.

Object tracking through adaptive correlation

Current Air Force interests include a desire to track an object based on its shape once it has been designated as a target. The use of a correlation-based system to track an object through a series of images based on templates derived from previous image frames is discussed. The ability to track is extended to sequences that include multiple objects of interest within the field of view. This is accomplished by comparing the height and shape of the template autocorrelation to the peaks in the correlation of the template with the next scene. The result is to identify the region in the next scene that best matches the designated target. In addition to correlation plane postprocessing, an adaptive window is used to determine the template size to reduce the effects of correlator walkoff. The image sequences used were taken from a forward-looking infrared sensor mounted on board a DC-3 aircraft. The images contain a T-55 tank and both an M-113 and a TAB-71 armored personnel carrier moving in a columnized formation along a dirt road. This research presents techniques to (1) track targets in the presence of other, and sometimes brighter, targets of similar shape, (2) to maintain small tracking errors, and (3) to reduce the effects of correlator walk-off.