More Like this

1. Blind Users Accessing Their Training Images in Teachable Object Recognizers

   https://doi.org/10.1145/3517428.3544824  

   Hong, Jonggi ; Gandhi, Jaina ; Essuah Mensah, Ernest ; Zeraati, Farnaz Z. ; Jarjue, Ebrima H. ; Lee, K. ; Kacorri, Hernisa ( October 2022 , ACM SIGACCESS Conference on Computers and Accessibility (ASSETS))

   Teachable object recognizers provide a solution for a very practical need for blind people – instance level object recognition. They assume one can visually inspect the photos they provide for training, a critical and inaccessible step for those who are blind. In this work, we engineer data descriptors that address this challenge. They indicate in real time whether the object in the photo is cropped or too small, a hand is included, the photos is blurred, and how much photos vary from each other. Our descriptors are built into open source testbed iOS app, called MYCam. In a remote user study in (N = 12) blind participants’ homes, we show how descriptors, even when error-prone, support experimentation and have a positive impact in the quality of training set that can translate to model performance though this gain is not uniform. Participants found the app simple to use indicating that they could effectively train it and that the descriptors were useful. However, many found the training being tedious, opening discussions around the need for balance between information, time, and cognitive load. 

   more » « less
2. PoseASL: An RGBD Dataset of American Sign Language

   https://doi.org/10.17910/b7.1279  

   Huenerfauth, Matt ( January 2021 , Databrary)

   The PoseASL dataset consists of color and depth videos collected from ASL signers at the Linguistic and Assistive Technologies Laboratory under the direction of Matt Huenerfauth, as part of a collaborative research project with researchers at the Rochester Institute of Technology, Boston University, and the University of Pennsylvania. Access: After becoming an authorized user of Databrary, please contact Matt Huenerfauth if you have difficulty accessing this volume. We have collected a new dataset consisting of color and depth videos of fluent American Sign Language signers performing sequences ASL signs and sentences. Given interest among sign-recognition and other computer-vision researchers in red-green-blue-depth (RBGD) video, we release this dataset for use by the research community. In addition to the video files, we share depth data files from a Kinect v2 sensor, as well as additional motion-tracking files produced through post-processing of this data. Organization of the Dataset: The dataset is organized into sub-folders, with codenames such as "P01" or "P16" etc. These codenames refer to specific human signers who were recorded in this dataset. Please note that there was no participant P11 nor P14; those numbers were accidentally skipped during the process of making appointments to collect video stimuli. Task: During the recording session, the participant was met by a member of our research team who was a native ASL signer. No other individuals were present during the data collection session. After signing the informed consent and video release document, participants responded to a demographic questionnaire. Next, the data-collection session consisted of English word stimuli and cartoon videos. The recording session began with showing participants stimuli consisting of slides that displayed English word and photos of items, and participants were asked to produce the sign for each (PDF included in materials subfolder). Next, participants viewed three videos of short animated cartoons, which they were asked to recount in ASL: - Canary Row, Warner Brothers Merrie Melodies 1950 (the 7-minute video divided into seven parts) - Mr. Koumal Flies Like a Bird, Studio Animovaneho Filmu 1969 - Mr. Koumal Battles his Conscience, Studio Animovaneho Filmu 1971 The word list and cartoons were selected as they are identical to the stimuli used in the collection of the Nicaraguan Sign Language video corpora - see: Senghas, A. (1995). Children’s Contribution to the Birth of Nicaraguan Sign Language. Doctoral dissertation, Department of Brain and Cognitive Sciences, MIT. Demographics: All 14 of our participants were fluent ASL signers. As screening, we asked our participants: Did you use ASL at home growing up, or did you attend a school as a very young child where you used ASL? All the participants responded affirmatively to this question. A total of 14 DHH participants were recruited on the Rochester Institute of Technology campus. Participants included 7 men and 7 women, aged 21 to 35 (median = 23.5). All of our participants reported that they began using ASL when they were 5 years old or younger, with 8 reporting ASL use since birth, and 3 others reporting ASL use since age 18 months. Filetypes: *.avi, *_dep.bin: The PoseASL dataset has been captured by using a Kinect 2.0 RGBD camera. The output of this camera system includes multiple channels which include RGB, depth, skeleton joints (25 joints for every video frame), and HD face (1,347 points). The video resolution produced in 1920 x 1080 pixels for the RGB channel and 512 x 424 pixels for the depth channels respectively. Due to limitations in the acceptable filetypes for sharing on Databrary, it was not permitted to share binary *_dep.bin files directly produced by the Kinect v2 camera system on the Databrary platform. If your research requires the original binary *_dep.bin files, then please contact Matt Huenerfauth. *_face.txt, *_HDface.txt, *_skl.txt: To make it easier for future researchers to make use of this dataset, we have also performed some post-processing of the Kinect data. To extract the skeleton coordinates of the RGB videos, we used the Openpose system, which is capable of detecting body, hand, facial, and foot keypoints of multiple people on single images in real time. The output of Openpose includes estimation of 70 keypoints for the face including eyes, eyebrows, nose, mouth and face contour. The software also estimates 21 keypoints for each of the hands (Simon et al, 2017), including 3 keypoints for each finger, as shown in Figure 2. Additionally, there are 25 keypoints estimated for the body pose (and feet) (Cao et al, 2017; Wei et al, 2016). Reporting Bugs or Errors: Please contact Matt Huenerfauth to report any bugs or errors that you identify in the corpus. We appreciate your help in improving the quality of the corpus over time by identifying any errors. Acknowledgement: This material is based upon work supported by the National Science Foundation under award 1749376: "Collaborative Research: Multimethod Investigation of Articulatory and Perceptual Constraints on Natural Language Evolution." 

   more » « less
3. Task-Driven convolutional recurrent models of the visual system.

   Nayebi, A ; Bear, D ; Kubilius, J ; Kar, K ; Ganguli, S ; Sussillo, D ; DiCarlo, JJ ; Yamins, DL. ( July 2018 , Advances in Neural Information Processing Systems 2018)

   Feed-forward convolutional neural networks (CNNs) are currently state-of-the-art for object classification tasks such as ImageNet. Further, they are quantitatively accurate models of temporally-averaged responses of neurons in the primate brain's visual system. However, biological visual systems have two ubiquitous architectural features not shared with typical CNNs: local recurrence within cortical areas, and long-range feedback from downstream areas to upstream areas. Here we explored the role of recurrence in improving classification performance. We found that standard forms of recurrence (vanilla RNNs and LSTMs) do not perform well within deep CNNs on the ImageNet task. In contrast, novel cells that incorporated two structural features, bypassing and gating, were able to boost task accuracy substantially. We extended these design principles in an automated search over thousands of model architectures, which identified novel local recurrent cells and long-range feedback connections useful for object recognition. Moreover, these task-optimized ConvRNNs matched the dynamics of neural activity in the primate visual system better than feedforward networks, suggesting a role for the brain's recurrent connections in performing difficult visual behaviors. 

   more » « less
4. Beyond Surveys: Using Visual Data to Evidence Achievement of Proposed Learning Objectives

   Guillemard, L. ( June 2023 , 2023 ASEE Annual Conference & Exposition)

   Visual qualitative methodologies enhance the richness of data and makes participants experts on the object of interest. Visual data brings another dimension to the evaluation process, besides surveys and interviews, as well as depth and breadth to participants reactions to specific program activities. Visual data consists of images, such as photos, drawings, artwork, among others. Exploring a different approach to assess impact of an educational activity, an exercise was designed where participants were asked to take photos to document a site visit to an area impacted by a swarm of earthquakes in 2019. The exercise required taking five photos of either objects, persons, scenery, structures, or any other thing that captured their attention during the visit and write a reflective essay to answer three questions: 1) How do these photos represent your site visit experience? 2) Based on the content of your photos, write about what you learned, discovered, new knowledge acquired, emotions, changes in your way of thinking, etc., and 3) What did you learned or discovered from doing this exercise? Twenty-two undergraduate engineering and architecture students from the RISE-UP Program, enrolled in a curricular sequence in design and construction of resilient and sustainable structures, completed the exercise. Analyses of obtained data includes frequency of captured images and content analysis of reflective essays to determine instances where each of the four proposed learning objectives was present. Results show that across essays, 32% of the essays include text that demonstrate impact related to the first objective, 59% for the second, 73% for the third, and 86% for the fourth objective. Forty-five percent of essays included text considered relevant but not related to an objective. Personal, social, and career insights were categorized as unintended results. Photos taken by students represent what they considered relevant during the visit and also evidence the achievement of the proposed learning objectives. In general, three mayor categories emerged from the content in photos: 1) photos related to the design and construction of the structure and specific damage observed from earthquakes; 2) photos of classmates, professors, and group activities; and 3) other photos that do not share a theme. Both photos and essays demonstrate that the learning objectives were successfully achieved and encourage the use of visual data as an alternative for the evaluation of educational activities. 

   more » « less
5. “Every Website Is a Puzzle!” : Facilitating Access to Common Website Features for People with Visual Impairments

   https://doi.org/10.1145/3519032  

   Barbosa, Natã M. ; Hayes, Jordan ; Kaushik, Smirity ; Wang, Yang ( September 2022 , ACM Transactions on Accessible Computing)

   Navigating unfamiliar websites is challenging for users with visual impairments. Although many websites offer visual cues to facilitate access to pages/features most websites are expected to have (e.g., log in at the top right), such visual shortcuts are not accessible to users with visual impairments. Moreover, although such pages serve the same functionality across websites (e.g., to log in, to sign up), the location, wording, and navigation path of links to these pages vary from one website to another. Such inconsistencies are challenging for users with visual impairments, especially for users of screen readers, who often need to linearly listen to content of pages to figure out how to access certain website features. To study how to improve access to main website features, we iteratively designed and tested a command-based approach for main features of websites via a browser extension powered by machine learning and human input. The browser extension gives users a way to access high-level website features (e.g., log in, find stores, contact) via keyboard commands. We tested the browser extension in a lab setting with 15 Internet users, including 9 users with visual impairments and 6 without. Our study showed that commands for main website features can greatly improve the experience of users with visual impairments. People without visual impairments also found command-based access helpful when visiting unfamiliar, cluttered, or infrequently visited websites, suggesting that this approach can support users with visual impairments while also benefiting other user groups (i.e., universal design). Our study reveals concerns about the handling of unsupported commands and the availability and trustworthiness of human input. We discuss how websites, browsers, and assistive technologies could incorporate a command-based paradigm to enhance web accessibility and provide more consistency on the web to benefit users with varied abilities when navigating unfamiliar or complex websites. 

   more » « less