No abstract

Detection and interpretation of human activities have emerged as a challenging healthcare problem in areas such as assisted living and remote monitoring. Besides traditional approaches that rely on wearable devices and camera systems, WiFi based technologies are evolving as a promising solution for indoor monitoring and activity recognition. This is, in part, due to the pervasive nature of WiFi in residential settings such as homes and care facilities, and unobtrusive nature of WiFi based sensing. Advanced signal processing techniques can accurately extract WiFi channel status information (CSI) using commercial off-theshelf (COTS) devices or bespoke hardware. This includes phase variations, frequency shifts and signal levels. In this paper, we describe the healthcare application of Doppler shifts in the WiFi CSI, caused by human activities which take place in the signal coverage area. The technique is shown to recognize different types of human activities and behaviour and be very suitable for applications in healthcare. Three experimental case studies are presented to illustrate the capabilities of WiFi CSI Doppler sensing in assisted living and residential care environments. We also discuss the potential opportunities and practical challenges for real-world scenarios.

Human-object interaction (HOI) detection aims to detect and recognise how people interact with the objects that surround them. This is challenging as different interaction categories are often distinguished only by very subtle visual differences in the scene. In this paper we introduce two methods to amplify key cues in the image, and also a method to combine these and other cues when considering the interaction between a human and an object. First, we introduce an encoding mechanism for representing the fine-grained spatial layout of the human and object (a subtle cue) and also semantic context (a cue, represented by text embeddings of surrounding objects). Second, we use plausible future movements of humans and objects as a cue to constrain the space of possible interactions. Third, we use a gate and memory architecture as a fusion module to combine the cues. We demonstrate that these three improvements lead to a performance which exceeds prior HOI methods across standard benchmarks by a considerable margin.

No abstract

No abstract

Unsupervised Domain Adaptation (UDA) aims to transfer domain knowledge from existing well-defined tasks to new ones where labels are unavailable. In the real-world applications, as the domain (task) discrepancies are usually uncontrollable, it is significantly motivated to match the feature distributions even if the domain discrepancies are disparate. Additionally, as no label is available in the target domain, how to successfully adapt the classifier from the source to the target domain still remains an open question. In this paper, we propose the Re-weighted Adversarial Adaptation Network (RAAN) to reduce the feature distribution divergence and adapt the classifier when domain discrepancies are disparate. Specifically, to alleviate the need of common supports in matching the feature distribution, we choose to minimize optimal transport (OT) based Earth-Mover (EM) distance and reformulate it to a minimax objective function. Utilizing this, RAAN can be trained in an end-to-end and adversarial manner. To further adapt the classifier, we propose to match the label distribution and embed it into the adversarial training. Finally, after extensive evaluation of our method using UDA datasets of varying difficulty, RAAN achieved the state-of-the-art results and outperformed other methods by a large margin when the domain shifts are disparate.

No abstract

No abstract