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

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.

Social Contexts, Agency, and Conflicts: Exploring Critical Aspects of Design for Future Smart Home Technologies

Smart devices are increasingly being designed for, and adopted in, the home environment. Prior scholarship has investigated the challenges that users face as they take up these devices in their homes. However, little is known about when and how users or potential users would prefer future domestic Internet of Things (IoT) to support their activities in home settings. To fill this gap, we conducted two co-design workshops, an in-home activity between the two sessions, and pre- and post-study interviews with 18 adult participants, who had diverse levels of prior experience of IoT use. Our findings contribute new insights into how smart home devices could adapt their behavior based on social contexts; how to re-imagine agency and support useful intelligibility; and how to resolve user-driven conflict by providing appropriate information about those with whom devices are shared. Finally, based on these findings, we discuss the implications of our work and provide a set of design considerations from which designers of future smart home technologies can benefit.

The Making of Meaning through Dyadic Haptic Affective Touch

Despite the importance of touch in human–human relations, research in affective tactile practices is in its infancy, lacking in-depth understanding needed to inform the design of remote digital touch communication. This article reports two qualitative studies that explore tactile affective communication in specific social contexts, and the bi-directional creation, sending and interpretation of digital touch messages using a purpose-built research tool, the Tactile Emoticon. The system comprises a pair of remotely connected mitts, which enable users in different locations to communicate through tactile messages, by orchestrating duration and level of three haptic sensations: vibration, pressure and temperature. Qualitative analysis shows the nuanced ways in which 68 participants configured these elements to make meaning from touch messages they sent and received. It points to the affect and emotion of touch, its sensoriality and ambiguity, the significance of context, social norms and expectations of touch participants. Findings suggest key design considerations for digital touch communication, where the emphasis shifts from generating ‘recognizable touches’ to tools that allow people to shape their touches and establish common understanding about their meaning.

Repeatability of endocrine traits and dominance rank in female guinea pigs

Background Glucocorticoids (e.g. cortisol) are associated with variation in social behavior, and previous studies have linked baseline as well as challenge-induced glucocorticoid concentrations to dominance status. It is known that cortisol response to an acute challenge is repeatable and correlates to social behavior in males of many mammal species. However, it is unclear whether these patterns are also consistent for females. The aim of this study was to investigate whether baseline and response cortisol concentrations are repeatable in female guinea pigs (Cavia aperea f. porcellus) and whether dominance rank is stable and correlated to baseline cortisol concentration and/or cortisol responsiveness. Results Our results show that cortisol responsiveness (after 1 h: R = 0.635, 95% CI = 0.229, 0.927; after 2 h: R = 0.764, 95% CI = 0.433, 0.951) and dominance rank (R = 0.709, 95% CI = 0.316, 0.935) of females were significantly repeatable after six weeks but not correlated. Baseline cortisol was not repeatable (R = 0, 95% CI = 0, 0.690) and also did not correlate to dominance rank. Furthermore, the difference in repeatability estimates of baseline and response values was due to high within-individual variance of baseline cortisol concentration; the amount of between-individual variance was similar for baseline cortisol and the two measures of cortisol responsiveness. Conclusions Females occupying different dominance ranks did not have long-term differences in cortisol concentrations, and cortisol responsiveness does not seem to be significantly involved in the maintenance of dominance rank. Overall, this study reveals the remarkable stability of cortisol responsiveness and dominance rank in a female rodent, and it remains an open question whether the magnitude of cortisol responsiveness is adaptive in social contexts for females.

Studying Up Machine Learning Data

Research in machine learning (ML) has argued that models trained on incomplete or biased datasets can lead to discriminatory outputs. In this commentary, we propose moving the research focus beyond bias-oriented framings by adopting a power-aware perspective to "study up" ML datasets. This means accounting for historical inequities, labor conditions, and epistemological standpoints inscribed in data. We draw on HCI and CSCW work to support our argument, critically analyze previous research, and point at two co-existing lines of work within our research community \,---\,one bias-centered, the other power-aware. We highlight the need for dialogue and cooperation in three areas: data quality, data work, and data documentation. In the first area, we argue that reducing societal problems to "bias" misses the context-based nature of data. In the second one, we highlight the corporate forces and market imperatives involved in the labor of data workers that subsequently shape ML datasets. Finally, we propose expanding current transparency-oriented efforts in dataset documentation to reflect the social contexts of data design and production.

Context-Dependent Gestural Laterality: A Multifactorial Analysis in Captive Red-Capped Mangabeys

Catarrhine primates gesture preferentially with their right hands, which led to the hypothesis of a gestural origin of human left-hemispheric specialization for language. However, the factors influencing this gestural laterality remain understudied in non-hominoid species, particularly in intraspecific contexts, although it may bring valuable insights into the proximate and ultimate causes of language lateralization. We present here a preliminary investigation of intraspecific gestural laterality in catarrhine monkeys, red-capped mangabeys (Cercocebus torquatus). We described the spontaneous production of brachio-manual intentional gestures in twenty-five captive subjects. Although we did not evidence any significant gestural lateralization neither at the individual- nor population-level, we found that mangabeys preferentially use their right hands to gesture in negative social contexts, such as aggressions, suggesting an effect of emotional lateralization, and that they adapt to the position of their receiver by preferentially using their ipsilateral hand to communicate. These results corroborate previous findings from ape studies. By contrast, factors related to gesture form and socio-demographic characteristics of signaler and receiver did not affect gestural laterality. To understand better the relationships between gestural laterality and brain lateralization from an evolutionary perspective, we suggest that the gestural communication of other monkey species should be examined with a multifactorial approach.

Prevention and Control of African Swine Fever in the Smallholder Pig Value Chain in Northern Uganda: Thematic Analysis of Stakeholders' Perceptions

African swine fever (ASF) is endemic in Uganda and considered a major constraint to pig production. In the absence of a vaccine, biosecurity is key for ASF prevention and control. To improve prevention and control on farm and community level there is need for more knowledge on current application of biosecurity practises, and better understanding of how pig value chain actors perceive prevention and control. To achieve this, a qualitative interview study involving focus group discussions (FGD) was conducted with actors from the smallholder pig value chain in northern Uganda. Six villages were purposively selected based on previous outbreaks of ASF, preliminary perceived willingness to control ASF, and the representation of several different value chain actors in the village. Results indicated that biosecurity practises such as basic hygiene routines including safe carcass handling, minimising direct and indirect contacts between pigs or between pigs and people, trade restrictions and sharing of disease information were implemented in some of the villages. Thematic analysis based on grounded theory revealed six categories of data relating to ASF prevention and control. Together these categories form a logical framework including both enablers and hindrances for ASF prevention and control. In summary participants mostly had positive perceptions of ASF biosecurity, describing measures as effective. Participants further possessed knowledge of ASF and its transmission, some of which was in line with known scientific knowledge and some not. Nevertheless, participants were hindered from preventing and controlling ASF due to biosecurity costs and a need to prioritise family livelihood over disease transmission risks, incompatibility of current biosecurity practises with local culture, traditions and social contexts and finally lack of access to veterinarians or, occasionally, low-quality veterinary services. The constraints could be addressed by applying participatory processes in designing biosecurity measures to ensure better adaptation to local cultural and social contexts.

Penerapan Text Network Analysis Dalam Menganalisis Pendapat Customer Product Patriot di Shopee

E-commerce has changed the buying and selling process and the way people interact via the internet. One company that uses e-commerce is PT Patriot Memory Indonesia. PT Patriot Memory Indonesia sells well-known computer peripherals, including the Solid State Drive (SSD). PT Patriot Memory Indonesia wants to analyze customer feedback regarding SSD products sold in e-commerce, namely Shopee by using Text Network Analysis (TNA) which is one part of social computing. Social computing is a science that focuses on social behavior and social contexts using computing systems. One of the tools of social computing, namely Text Network Analysis (TNA), is a research technique that focuses on identifying and comparing network relationships between words, sentences, and systems to model interactions that generate new knowledge or information. In this study, TextNetwork Analysis will show consumer perceptions through the feedback it provideson buyer reviews. The opinions expressed by consumers in buyer reviews can be analyzed so that they can connect each word and create associations of consumer perceptions of a product. Thus, it can be seen the aspects that must be addressed by the company to improve consumer perceptions. The problem analyzed is the development of social computing in analyzing big data. Can the company take advantage of this information so that they know the perceptions of their consumers through the information in the customer feedback at Shopee. Through Text Network Analysis in social computing, researchers will know the association of each word of consumer perception and can see the perception that has the highest degree of a product and see its relationship with other perceptions. This study looks at consumer perceptions of Patriot SSD products at Shopee. The results of this study can help provide customer feedback information to PT Patriot Memory Indonesia.

Targeted memory reactivation of face-name learning depends on ample and undisturbed slow-wave sleep

Face memory, including the ability to recall a person’s name, is of major importance in social contexts. Like many other memory functions, it may rely on sleep. We investigated whether targeted memory reactivation during sleep could improve associative and perceptual aspects of face memory. Participants studied 80 face-name pairs, and then a subset of spoken names with associated background music was presented unobtrusively during a daytime nap. This manipulation preferentially improved name recall and face recognition for those reactivated face-name pairs, as modulated by two factors related to sleep quality; memory benefits were positively correlated with the duration of stage N3 sleep (slow-wave sleep) and negatively correlated with measures of sleep disruption. We conclude that (a) reactivation of specific face-name memories during sleep can strengthen these associations and the constituent memories, and that (b) the effectiveness of this reactivation depends on uninterrupted N3 sleep.