Social Context-aware Person Search in Videos via Multi-modal Cues

2022 ◽  
Vol 40 (3) ◽  
pp. 1-25
Author(s):  
Dan Li ◽  
Tong Xu ◽  
Peilun Zhou ◽  
Weidong He ◽  
Yanbin Hao ◽  
...  

Person search has long been treated as a crucial and challenging task to support deeper insight in personalized summarization and personality discovery. Traditional methods, e.g., person re-identification and face recognition techniques, which profile video characters based on visual information, are often limited by relatively fixed poses or small variation of viewpoints and suffer from more realistic scenes with high motion complexity (e.g., movies). At the same time, long videos such as movies often have logical story lines and are composed of continuously developmental plots. In this situation, different persons usually meet on a specific occasion, in which informative social cues are performed. We notice that these social cues could semantically profile their personality and benefit person search task in two aspects. First, persons with certain relationships usually co-occur in short intervals; in case one of them is easier to be identified, the social relation cues extracted from their co-occurrences could further benefit the identification for the harder ones. Second, social relations could reveal the association between certain scenes and characters (e.g., classmate relationship may only exist among students), which could narrow down candidates into certain persons with a specific relationship. In this way, high-level social relation cues could improve the effectiveness of person search. Along this line, in this article, we propose a social context-aware framework, which fuses visual and social contexts to profile persons in more semantic perspectives and better deal with person search task in complex scenarios. Specifically, we first segment videos into several independent scene units and abstract out social contexts within these scene units. Then, we construct inner-personal links through a graph formulation operation for each scene unit, in which both visual cues and relation cues are considered. Finally, we perform a relation-aware label propagation to identify characters’ occurrences, combining low-level semantic cues (i.e., visual cues) and high-level semantic cues (i.e., relation cues) to further enhance the accuracy. Experiments on real-world datasets validate that our solution outperforms several competitive baselines.

2005 ◽  
Author(s):  
◽  
Christopher J. Amelung

Researchers have identified user presence, awareness, and a sense of community as important components of Computer Supported Collaborative Environments (CSCE) (Dourish and Bellotti, 1992; Erickson and Kellogg, 2003; Moody, 2000; Prinz, 1999). To support user actions and interactions sufficient to create and sustain a sense of community, recent CSCE have been developed with notification systems to provide activity notifications to users. However, these notification systems typically transmit generic notifications as actions occur and do not provide mechanisms for analyzing and providing notifications based on user preference or social context. A challenge facing developers of CSCE is to create a notification system for delivering awareness information based on the ever-changing preferences, interests, and social contexts of users. To address this challenge, this study articulated and advanced a theoretical framework for developers to use when integrating activity notifications into existing CSCE. The proposed framework is based on the importance of user preferences and social context and is derived from the Locales Framework (Fitzpatrick, 1998). The principles of this new development framework are Social Context, Awareness in Context, Activity Discovery, Trends in Activity, Meaning of Activity, and Notification Customization. To evaluate the concepts of this framework, this study developed a context-aware activity notification system for an existing CSCE based on the framework's proposed principles. During the development process, it was determined that not only could the Framework for Notification be used to provide notifications based on user preference and social context, but the use of the proposed Framework afforded a richer understanding of the collaborative needs of users for both the theorists discussing the implications of activity notifications and the developers working to provide those notifications.


2021 ◽  
Vol 75 (3) ◽  
Author(s):  
Nick A. R. Jones ◽  
Helen C. Spence-Jones ◽  
Mike Webster ◽  
Luke Rendell

Abstract Learning can enable rapid behavioural responses to changing conditions but can depend on the social context and behavioural phenotype of the individual. Learning rates have been linked to consistent individual differences in behavioural traits, especially in situations which require engaging with novelty, but the social environment can also play an important role. The presence of others can modulate the effects of individual behavioural traits and afford access to social information that can reduce the need for ‘risky’ asocial learning. Most studies of social effects on learning are focused on more social species; however, such factors can be important even for less-social animals, including non-grouping or facultatively social species which may still derive benefit from social conditions. Using archerfish, Toxotes chatareus, which exhibit high levels of intra-specific competition and do not show a strong preference for grouping, we explored the effect of social contexts on learning. Individually housed fish were assayed in an ‘open-field’ test and then trained to criterion in a task where fish learnt to shoot a novel cue for a food reward—with a conspecific neighbour visible either during training, outside of training or never (full, partial or no visible presence). Time to learn to shoot the novel cue differed across individuals but not across social context. This suggests that social context does not have a strong effect on learning in this non-obligatory social species; instead, it further highlights the importance that inter-individual variation in behavioural traits can have on learning. Significance statement Some individuals learn faster than others. Many factors can affect an animal’s learning rate—for example, its behavioural phenotype may make it more or less likely to engage with novel objects. The social environment can play a big role too—affecting learning directly and modifying the effects of an individual’s traits. Effects of social context on learning mostly come from highly social species, but recent research has focused on less-social animals. Archerfish display high intra-specific competition, and our study suggests that social context has no strong effect on their learning to shoot novel objects for rewards. Our results may have some relevance for social enrichment and welfare of this increasingly studied species, suggesting there are no negative effects of short- to medium-term isolation of this species—at least with regards to behavioural performance and learning tasks.


2021 ◽  
Vol 1 (1) ◽  
pp. 18-26
Author(s):  
Yossi Pratiwi ◽  
Sridelli Dakhi

Abstract.  Skilled in pragmatic language, means skilled in using language forms ( words, phrases and clauses appropriately according to the conditions, situations and social contexts behind it. Such pragmatic skills may be established if the situation, conditions and social context behind the use of the language can be adequately mastered. This study aims to describe the percentage of contributions to the mastery of sociolinguistic concepts with pragmatic skills. In line with the purpose of the study, sociolinguistic mastery data with pragmatic skills of 28 sample people netted with test instruments and analyzed with statistics r¬2.From the results of the analysis conducted, obtained a determination index of 0.78 which means; mastery of sociolinguistic concepts contributes 78% to the achievement of students' pragmatic skills. In accordance with the results of the above analysis, it can be concluded that mastery of sociolinguistic concepts is a variable of criteria that contributes very meaningfully to the improvement of pragmatic skills. Thus, the research hypothesis yaang said that the mastery of the concept of sociolinguistics contributes meaningfully to the development of pragmatic skills of students of SMP Negeri 1 Nias Selatan, the truth is proven


2007 ◽  
Vol 12 (1) ◽  
pp. 169-180 ◽  
Author(s):  
Fiona Gill

This paper examines the management of feminine identities in a women's rugby team in a rural British community. In so doing, the issue of new, and potentially problematic, forms of femininity are explored, with their attendant social consequences. The team, known as the Jesters, is situated in a social context which is dominantly masculine and heterosexist, with rigidly enforced gender roles. Due to their participation in rugby, a ‘man's game’, the Jesters are threatened with marginalisation for their apparent failure to conform to, and potential disruption of, established gender norms. This threat is managed through the performance of certain ‘inauthentic’ feminine identities (hyper-femininity and heterosexuality) on the part of the entire team. It is this ‘team identity’ which lies at the heart of this paper. This paper therefore examines the group dynamics of identity performance and negotiation. In negotiating ‘normal’ the Jesters are forced to confront changing gender norms and social contexts within the team itself. This paper also examines the difficulties faced by individuals when their own interests are opposed to the interests of the group of which they are a part. Although largely uncaring about the private lives of team members, the heterosexual members of the Jesters refuse to tolerate the performance of alternative versions of femininity when it may result in the exclusion of the team as a whole. This paper therefore examines the differing interests of heterosexual and lesbian femininities within a potentially marginalised group and some of the coping mechanisms adopted by both groups to develop a coherent team image.


2017 ◽  
Vol 117 (1) ◽  
pp. 388-402 ◽  
Author(s):  
Michael A. Cohen ◽  
George A. Alvarez ◽  
Ken Nakayama ◽  
Talia Konkle

Visual search is a ubiquitous visual behavior, and efficient search is essential for survival. Different cognitive models have explained the speed and accuracy of search based either on the dynamics of attention or on similarity of item representations. Here, we examined the extent to which performance on a visual search task can be predicted from the stable representational architecture of the visual system, independent of attentional dynamics. Participants performed a visual search task with 28 conditions reflecting different pairs of categories (e.g., searching for a face among cars, body among hammers, etc.). The time it took participants to find the target item varied as a function of category combination. In a separate group of participants, we measured the neural responses to these object categories when items were presented in isolation. Using representational similarity analysis, we then examined whether the similarity of neural responses across different subdivisions of the visual system had the requisite structure needed to predict visual search performance. Overall, we found strong brain/behavior correlations across most of the higher-level visual system, including both the ventral and dorsal pathways when considering both macroscale sectors as well as smaller mesoscale regions. These results suggest that visual search for real-world object categories is well predicted by the stable, task-independent architecture of the visual system. NEW & NOTEWORTHY Here, we ask which neural regions have neural response patterns that correlate with behavioral performance in a visual processing task. We found that the representational structure across all of high-level visual cortex has the requisite structure to predict behavior. Furthermore, when directly comparing different neural regions, we found that they all had highly similar category-level representational structures. These results point to a ubiquitous and uniform representational structure in high-level visual cortex underlying visual object processing.


2021 ◽  
Vol 2 ◽  
Author(s):  
A. Maneuvrier ◽  
L. M. Decker ◽  
P. Renaud ◽  
G. Ceyte ◽  
H. Ceyte

Field dependence–independence (FDI) is a psychological construct determining an individual’s approach of the perception–cognition coupling. In virtual reality (VR) context, several studies suggest that an individual’s perceptive style is susceptible to shift toward a more FI mode through down-weighting of conflicting visual cues. The present study proposes to investigate the potential flexible nature of FDI following a virtual immersion and to assess if this flexibility might be associated with the subjective experience of VR. 86 participants explored a real-world–like virtual environment for approximately 10 min. FDI levels were measured before and after the VR exposure using the rod-and-frame test. Their subjective experience of VR was measured a posteriori (cybersickness and sense of presence) and used in order to build two experimental groups via a cluster analysis. The results showed that only participants with a poor subjective experience of VR (i.e., a low level of sense of presence associated with a high level of cybersickness) significantly shifted to a more FI mode, which is discussed as a sensory re-weighting mechanism. Pragmatical applications are discussed, and future studies are outlined, based on the conclusion that FDI might be more flexible than we thought, which could shed light on the psychophysiology of VR.


2021 ◽  
Vol 17 (4) ◽  
pp. 41-59
Author(s):  
Deeba K. ◽  
Saravanaguru R. A. K.

Today, IoT-related applications play an important role in scientific world development. Context reasoning emphasizes the perception of various contexts by means of collection of IoT data which includes context-aware decision making. Context-aware computing is used to improve the abilities of smart devices and is increased by smart applications. In this paper, context-aware for the internet of things middleware (CAIM) architecture is used for developing a rule-based system using CA-RETE algorithm. The objective of context-aware systems are concentrated on 1) context reasoning methodologies and analyzing how the technologies will involve enhancing the high-level context data, 2) framework of context reasoning system, 3) implementation of CA-RETE algorithm for predicting gestational diabetes mellitus in healthcare applications.


This chapter begins with one cultural practice–surfing–that was developed to an extremely high level by indigenous peoples of Hawai'i over several millennia before it was appropriated by settler colonialists and exported globally. It asks what music associated with surfing reveals about the processes of colonization. Then the Polynesian Voyaging Society is presented as a case study. Originating during the Hawaiian Renaissance and the surfing community in the early 1970s, the project uses musicking as a catalyst for expressing human engagement with complex environmental and social contexts. It also provides a model for a decolonized future built on resilient, sustainable cultural and resource management.


Author(s):  
James S. Coleman

There are two broad intellectual streams in the description and explanation of social action. One, characteristic of the work of most sociologists, sees the actor as socialized and action as governed by social norms, rules, and obligations. The principal virtues of this intellectual stream lie in its ability to describe action in social context and to explain the way action is shaped, constrained, and redirected by the social context. The other intellectual stream, characteristic of the work of most economists, sees the actor as having goals independently arrived at, as acting independently, and as wholly self-interested. Its principal virtue lies in having a principle of action, that of maximizing utility. This principle of action, together with a single empirical generalization (declining marginal utility), has generated the extensive growth of neoclassical economic theory, as well as the growth of political philosophy of several varieties: utilitarianism, contractarianism, and natural rights. In earlier works (Coleman 1986a, 1986b), I have argued for and engaged in the development of a theoretical orientation in sociology that includes components from both these intellectual streams. It accepts the principle of rational or purposive action and attempts to show how that principle, in conjunction with particular social contexts, can account not only for the actions of individuals in particular contexts but also for the development of social organization. In the present paper, I introduce a conceptual tool for use in this theoretical enterprise: social capital. As background for introducing this concept, it is useful to see some of the criticisms of and attempts to modify the two intellectual streams. Both these intellectual streams have serious defects. The sociological stream has what may be a fatal flaw as a theoretical enterprise: the actor has no “engine of action.” The actor is shaped by the environment, but there are no internal springs of action that give the actor a purpose or direction. The very conception of action as wholly a product of the environment has led sociologists themselves to criticize this intellectual stream, as in Dennis Wrong’s (1961) “Oversocialized Conception of Man in Modern Sociology.”


2009 ◽  
Vol 74 (3) ◽  
pp. 423-447 ◽  
Author(s):  
Brian S. Robinson ◽  
Jennifer C. Ort ◽  
William A. Eldridge ◽  
Adrian L. Burke ◽  
Bertrand G. Pelletier

Large social aggregations are among the most highly organized events associated with mobile hunter-gatherers. The Bull Brook Paleoindian site in Ipswich, Massachusetts provides the strongest case for large-scale Paleoindian aggregation in North America, with 36 discrete concentrations of artifacts arranged in a large circle. Avocational archaeologists who salvaged the site in the 1950s interpreted it as a single occupation. Professionals first rejected and then revived this hypothesis, but the site remained insufficiently analyzed to evaluate. New research supports the single occupation hypothesis with a fully reconstructed site plan and the first complete analysis of artifact distributions. Clear spatial structure of activities within the ring-shaped site plan provides a window on social contexts that are also visible in smaller Paleoindian settlements.


Sign in / Sign up

Export Citation Format

Share Document