We investigate a discriminatively trained model of person-object interactions for recognizing common human actions in still images. We build on the locally order-less spatial pyramid bag-of-features model, which was shown to perform extremely well on a range of object, scene and human action recognition tasks. We introduce three principal contributions. First, we replace the standard quantized ...

Aim The aim of this study was to describe the care-planning conference from the participants' and researchers' perspectives, focusing on exploring aspects of person-centred interactions. Design A single-instrumental, qualitative case study design was used describing a care-planning conference taking place in the home of an older woman and her daughter. Methods Data collection consisted of o...

Research is increasingly challenging the claim that distinct sources of social information-such as sex, race, and emotion-are processed in discrete fashion. Instead, there appear to be functionally relevant interactions that occur. In the present article, we describe research examining how cues conveyed by the human face, voice, and body interact to form the unified representations that guide o...

This paper introduces an approach that enables a design tool to learn first-person knowledge through interactions. A design tool of this kind embodies learning and adaptive behaviours. The contextual knowledge in using the tool to solve a particular design problem can be captured, made available and adapted to a designer’s decision-making when he or she is confronted with a similar or a new pro...

The human brain is excellent at integrating information from different sources across multiple sensory modalities. To examine one particularly important form of multisensory interaction, we manipulated the temporal correlation between visual and auditory stimuli in a first-person fisherman video game. Subjects saw rapidly swimming fish whose size oscillated, either at 6 or 8 Hz. Subjects catego...

The ability to predict social interactions between people has profound applications including targeted marketing and prediction of information diffusion and disease propagation. Previous work has shown that the location of an individual at any given time is highly predictable. This study examines the predictability of social interactions between people to determine whether interaction patterns ...

We describe a real-time computer vision and machine learning system for modeling and recognizing human actions and interactions. Two different domains are explored: recognition of two-handed motions in the martial art 'Tai Chi' , and multiple-person interactions in a visual surveillance task. Our system combines top-down with bottom-up information using a feedback loop, and is formulated with a...

We present a novel multi-person pose estimation framework, which extends pictorial structures (PS) to explicitly model interactions between people and to estimate their poses jointly. Interactions are modeled as occlusions between people. First, we propose an occlusion probability predictor, based on the location of persons automatically detected in the image, and incorporate the predictions as...