Camera manipulation confounds the use of object recognition applications by blind people. This is exacerbated when photos from this population are also used to train models, as with teachable machines, where out-of-frame or partially included objects against cluttered backgrounds degrade performance. Leveraging prior evidence on the ability of blind people to coordinate hand movements using proprioception, we propose a deep learning system that jointly models hand segmentation and object localization for object classification. We investigate the utility of hands as a natural interface for including and indicating the object of interest in the camera frame. We confirm the potential of this approach by analyzing existing datasets from people with visual impairments for object recognition. With a new publicly available egocentric dataset and an extensive error analysis, we provide insights into this approach in the context of teachable recognizers.

Two-dimensional (2D) materials with a layered structure are excellent candidates in the field of lubrication due to their unique physical and chemical properties, including weak interlayer interaction and large specific surface area. For the last few decades, graphene has received lots of attention due to its excellent properties. Besides graphene, various new 2D materials (including MoS2, WS2, WSe2, NbSe2, NbTe2, ReS2, TaS2 and h-BN etc.) are found to exhibit a low coefficient of friction at the macro- and even micro-scales, which may lead to widespread application in the field of lubrication and anti-wear. This article focuses on the latest development trend in 2D materials in the field of tribology. The review begins with a summary of widely accepted nano-scale friction mechanisms contain surface friction mechanism and interlayer friction mechanism. The following sections report the applications of 2D materials in lubrication and anti-wear as lubricant additives, solid lubricants, and composite lubricating materials. Finally, the research prospects of 2D materials in tribology are presented.

Superhydrophobic (SHPo) surfaces can provide high condensation heat transfer due to facilitated droplet removal. However, such high performance has been limited to low supersaturation conditions due to surface flooding. Here, we quantify flooding resistance defined as the rate of increase in the fraction of water-filled cavities with respect to the supersaturation level. Based on the quantitative understanding of surface flooding, we suggest effective anti-flooding strategies through tailoring the nanoscale coating heterogeneity and structure length scale. Experimental verification is conducted using CuO nanostructures having different length scales combined with hydrophobic coatings with different nanoscale heterogeneities. The proposed antiflooding SHPo can provide a ∼130% enhanced average heat transfer coefficient with ∼14% larger supersaturation range for droplet jumping compared to a previous CuO SHPo. The proposed anti-flooding parameter and the scalable SHPo will help develop high-performance condensers for real-world applications operating in a wide range of supersaturation levels.

Blind people have limited access to information about their surroundings, which is important for ensuring one's safety, managing social interactions, and identifying approaching pedestrians. With advances in computer vision, wearable cameras can provide equitable access to such information. However, the always-on nature of these assistive technologies poses privacy concerns for parties that may get recorded. We explore this tension from both perspectives, those of sighted passersby and blind users, taking into account camera visibility, in-person versus remote experience, and extracted visual information. We conduct two studies: an online survey with MTurkers (N=206) and an in-person experience study between pairs of blind (N=10) and sighted (N=40) participants, where blind participants wear a working prototype for pedestrian detection and pass by sighted participants. Our results suggest that both of the perspectives of users and bystanders and the several factors mentioned above need to be carefully considered to mitigate potential social tensions.

To ensure that AI-infused systems work for disabled people, we need to bring accessibility datasets sourced from this community in the development lifecycle. However, there are many ethical and privacy concerns limiting greater data inclusion, making such datasets not readily available. We present a pair of studies where 13 blind participants engage in data capturing activities and reflect with and without probing on various factors that influence their decision to share their data via an AI dataset. We see how different factors influence blind participants' willingness to share study data as they assess risk-benefit tradeoffs. The majority support sharing of their data to improve technology but also express concerns over commercial use, associated metadata, and the lack of transparency about the impact of their data. These insights have implications for the development of responsible practices for stewarding accessibility datasets, and can contribute to broader discussions in this area. CCS CONCEPTS• Human-centered computing → Human computer interaction (HCI); Accessibility; • Social and professional topics → People with disabilities; • Security and privacy → Human and societal aspects of security and privacy.

Teachable interfaces can empower end-users to attune machine learning systems to their idiosyncratic characteristics and environment by explicitly providing pertinent training examples. While facilitating control, their effectiveness can be hindered by the lack of expertise or misconceptions. We investigate how users may conceptualize, experience, and reflect on their engagement in machine teaching by deploying a mobile teachable testbed in Amazon Mechanical Turk. Using a performance-based payment scheme, Mechanical Turkers (N = 100) are called to train, test, and re-train a robust recognition model in real-time with a few snapshots taken in their environment. We find that participants incorporate diversity in their examples drawing from parallels to how humans recognize objects independent of size, viewpoint, location, and illumination. Many of their misconceptions relate to consistency and model capabilities for reasoning. With limited variation and edge cases in testing, the majority of them do not change strategies on a second training attempt.

No abstract

No abstract