People In Scenes Research Articles

Social robots as depictions of social agents.

Social robots serve people as tutors, caretakers, receptionists, companions, and other social agents. People know that the robots are mechanical artifacts, yet they interact with them as if they were actual agents. How is this possible? The proposal here is that people construe social robots not as social agents per se, but as depictions of social agents. They interpret them much as they interpret ventriloquist dummies, hand puppets, virtual assistants, and other interactive depictions of people and animals. Depictions as a class consist of three physical scenes with part-by-part mappings between them: (a) a base scene (the raw physical artifact), (b) the depiction proper (the artifact construed as a depiction), and (c) the scene depicted (the scene people are to imagine). With social robots, evidence shows people form the same three scenes plus mappings: They perceive the raw machinery of a robot, construe it as a depiction of a character, and, using the depiction as a guide, engage in the pretense that they are interacting with the character depicted. With social robots, people also recognize three classes of agents - the characters depicted, the intended recipients of the depictions (those who view or interact with the robots), and the authorities responsible for the robots (the designers, makers, and owners). Construing social robots as depictions, we argue, accounts for many phenomena not covered by alternative models.

Towards dense people detection with deep learning and depth images

This paper describes a novel DNN-based system, named PD3net, that detects multiple people from a single depth image, in real time. The proposed neural network processes a depth image and outputs a likelihood map in image coordinates, where each detection corresponds to a Gaussian-shaped local distribution, centered at each person’s head. This likelihood map encodes both the number of detected people as well as their position in the image, from which the 3D position can be computed. The proposed DNN includes spatially separated convolutions to increase performance, and runs in real-time with low budget GPUs. We use synthetic data for initially training the network, followed by fine tuning with a small amount of real data. This allows adapting the network to different scenarios without needing large and manually labeled image datasets. Due to that, the people detection system presented in this paper has numerous potential applications in different fields, such as capacity control, automatic video-surveillance, people or groups behavior analysis, healthcare or monitoring and assistance of elderly people in ambient assisted living environments. In addition, the use of depth information does not allow recognizing the identity of people in the scene, thus enabling their detection while preserving their privacy. The proposed DNN has been experimentally evaluated and compared with other state-of-the-art approaches, including both classical and DNN-based solutions, under a wide range of experimental conditions. The achieved results allows concluding that the proposed architecture and the training strategy are effective, and the network generalize to work with scenes different from those used during training. We also demonstrate that our proposal outperforms existing methods and can accurately detect people in scenes with significant occlusions.

Aesthetic Preferences for Eastern and Western Traditional Visual Art: Identity Matters.

Western and Chinese artists have different traditions in representing the world in their paintings. While Western artists start since the Renaissance to represent the world with a central perspective and focus on salient objects in a scene, Chinese artists concentrate on context information in their paintings, mainly before the mid-19th century. We investigated whether the different typical representations influence the aesthetic preference for traditional Chinese and Western paintings in the different cultural groups. Traditional Chinese and Western paintings were presented randomly for an aesthetic evaluation to Chinese and Western participants. Both Chinese and Western paintings included two categories: landscapes and people in different scenes. Results showed a significant interaction between the source of the painting and the cultural group. For Chinese and Western paintings, a reversed pattern of aesthetic preference was observed: while Chinese participants gave higher aesthetic scores to traditional Chinese paintings than to Western paintings, Western participants tended to give higher aesthetic scores to traditional Western paintings than to Chinese paintings. We interpret this observation as indicator that personal identity is supported and enriched within cultural belongingness. Another important finding was that landscapes were more preferable than people in a scene across different cultural groups indicating a universal principle of preferences for landscapes. Thus, our results suggest that, on the one hand, the way that artists represent the world in their paintings influences the way that culturally embedded viewers perceive and appreciate paintings, but on the other hand, independent of the cultural background, anthropological universals are disclosed by the preference of landscapes.

Is Boundary Extension effected by the position and orientation of people in scenes?

Is Boundary Extension effected by the position and orientation of people in scenes?

Finding people in scenes: neural decoding target presence during search of dynamic scenes

Finding people in scenes: neural decoding target presence during search of dynamic scenes

A Causal Role for the Extrastriate Body Area in Detecting People in Real-World Scenes

People are extremely efficient at detecting relevant objects in complex natural scenes. In three experiments, we used functional magnetic resonance imaging-guided transcranial magnetic stimulation (TMS) to investigate the role of the extrastriate body area (EBA) in the detection of people in scenes. In Experiment 1, participants reported, in different blocks, whether people or cars were present in a briefly presented scene. Detection (d-prime) of people, but not of cars, was impaired after TMS over right EBA (rEBA; five pulses at -200, -100, 0, 100, 200 ms) compared with sham stimulation. In Experiment 2, we applied TMS either before (-200, -100 ms) or after (+100, +200) the scene onset. Poststimulus EBA stimulation impaired people detection relative to prestimulus EBA stimulation, while timing had no effect during sham stimulation. In Experiment 3, we examined anatomical specificity by comparing TMS over EBA with TMS over scene-selective transverse occipital sulcus (TOS). Two scenes were presented side by side, and response times to detect which scene contained people (or cars) were measured. For people detection, but not for car detection, response times during EBA stimulation were significantly slower than during TOS stimulation. Furthermore, rEBA stimulation led to an equivalent slowing of response times to left and right lateralized targets. These findings are the first to demonstrate the causal involvement of a category-selective human brain region in detecting its preferred stimulus category in natural scenes. They shed light on the nature of such regions, and help us understand how we efficiently extract socially relevant information from a complex input.

Eyeing the eyes in social scenes: Evidence for top-down control of stimulus selection in simultanagnosia

Simultanagnosia is a disorder of visual attention resulting from bilateral parieto-occipital lesions. Healthy individuals look at eyes to infer people's attentional states, but simultanagnosics allocate abnormally few fixations to eyes in scenes. It is unclear why simultanagnosics fail to fixate eyes, but it might reflect that they are (a) unable to locate and fixate them, or (b) do not prioritize attentional states. We compared eye movements of simultanagnosic G.B. to those of healthy subjects viewing scenes normally or through a restricted window of vision. They described scenes and explicitly inferred attentional states of people in scenes. G.B. and subjects viewing scenes through a restricted window made few fixations on eyes when describing scenes, yet increased fixations on eyes when inferring attention. Thus G.B. understands that eyes are important for inferring attentional states and can exert top-down control to seek out and process the gaze of others when attentional states are of interest.

SCOOP: A Real-Time Sparsity Driven People Localization Algorithm

Detecting and tracking people in scenes monitored by cameras is an important step in many application scenarios such as surveillance, urban planning or behavioral studies to name a few. The amount of data produced by camera feeds is so large that it is also vital that these steps be performed with the utmost computational efficiency and often even real-time. We propose SCOOP, a novel algorithm that reliably localizes people in camera feeds, using only the output of a simple background removal technique. SCOOP can handle a single or many video feeds. At the heart of our technique there is a sparse model for binary motion detection maps that we solve with a novel greedy algorithm based on set covering. We study the convergence and performance of the algorithm under various degradation models such as noisy observations and crowded environments, and we provide mathematical and experimental evidence of both its efficiency and robustness using standard datasets. This clearly shows that SCOOP is a viable alternative to existing state-of-the-art people localization algorithms, with the marked advantage of real-time computations.

Independent Effects of Local and Global Binocular Disparity on the Perceived Convexity of Stereoscopically Presented Faces in Scenes

Evidence suggests that experiencing the hollow-face illusion involves perceptual reversal of the binocular disparities associated with the face even though the rest of the scene appears unchanged. This suggests stereoscopic processing of object shape may be independent of scene-based processing of the layout of objects in depth. We investigated the effects of global scene-based and local object-based disparity on the compellingness of the perceived convexity of the face. We took stereoscopic photographs of people in scenes, and independently reversed the binocular disparities associated with the head and scene. Participants rated perceived convexity of a natural disparity ("convex") or reversed disparity ("concave") face shown either in its original context with reversed or natural disparities or against a black background. Faces with natural disparity were rated as more convincingly convex independent of the background, showing that the local disparities can affect perceived convexity independent of disparities across the rest of the image. However, the apparent convexity of the faces was also greater in natural disparity scenes compared to either a reversed disparity scene or a zero disparity black background. This independent effect of natural scene disparity suggests that the 'solidity' associated with natural scene disparities spread to enhance the perceived convexity of the face itself. Together, these findings suggest that global and local disparity exert independent and additive effects upon the perceived convexity of the face.

Attention to social stimuli and facial identity recognition skills in autism spectrum disorder

Previous research suggests that individuals with autism spectrum disorder (ASD) have a reduced preference for viewing social stimuli in the environment and impaired facial identity recognition. Here, we directly tested a link between these two phenomena in 13 ASD children and 13 age-matched typically developing (TD) controls. Eye movements were recorded while participants passively viewed visual scenes containing people and objects. Participants also completed independent matching tasks for faces and objects. Behavioural data showed that participants with ASD were impaired on both face- and object-matching tasks relative to TD controls. Eye-tracking data revealed that both groups showed a strong bias to orient towards people. TD children spent proportionally more time looking at people than objects; however, there was no difference in viewing times between people and objects in the ASD group. In the ASD group, an individual's preference for looking first at the people in scenes was associated with level of face recognition ability. Further research is required to determine whether a causal relationship exists between these factors.

Semantic and perceptual dimensions of people in scenes for image indexing

Semantic and perceptual dimensions of people in scenes for image indexing

On Space-Time Interest Points

Local image features or interest points provide compact and abstract representations of patterns in an image. In this paper, we extend the notion of spatial interest points into the spatio-temporal domain and show how the resulting features often reflect interesting events that can be used for a compact representation of video data as well as for interpretation of spatio-temporal events. To detect spatio-temporal events, we build on the idea of the Harris and Förstner interest point operators and detect local structures in space-time where the image values have significant local variations in both space and time. We estimate the spatio-temporal extents of the detected events by maximizing a normalized spatio-temporal Laplacian operator over spatial and temporal scales. To represent the detected events, we then compute local, spatio-temporal, scale-invariant N-jets and classify each event with respect to its jet descriptor. For the problem of human motion analysis, we illustrate how a video representation in terms of local space-time features allows for detection of walking people in scenes with occlusions and dynamic cluttered backgrounds.

Perception of Animals and Cardiovascular Responses During Verbalization With an Animal Present

AbstractThe presence of animals has been associated with decreased physiological responses to stressors. Not all individuals respond equally to the presence of friendly animals. The current study was designed to examine whether attitudes toward animals are related to individuals' physiological responses when an animal is present. The relationship of individuals' perceptions of animals to their blood pressure and heart rate responses during verbalization in the presence of a dog were examined among urban college students (n=218). Lockwood's projective Animal Thematic Apperception Test (ATAT) was used to assess subjects' attitudes toward animals and people in scenes containing animals and identical scenes without animals. The significant period by perception interactions in analyses of variance with repeated measures revealed that cardiovascular responses to verbalization with an animal present were significantly lower for individuals who perceived scenes with animals more positively than for individuals wh...