Related papers: Blind Users Accessing Their Training Images in Tea…
While metric learning is important for Person re-identification (RE-ID), a significant problem in visual surveillance for cross-view pedestrian matching, existing metric models for RE-ID are mostly based on supervised learning that requires…
Neuroprosthetic brain-computer interfaces function via an algorithm which decodes neural activity of the user into movements of an end effector, such as a cursor or robotic arm. In practice, the decoder is often learned by updating its…
We empirically investigate the camera bias of person re-identification (ReID) models. Previously, camera-aware methods have been proposed to address this issue, but they are largely confined to training domains of the models. We measure the…
Perception-based image analysis technologies can be used to help visually impaired people take better quality pictures by providing automated guidance, thereby empowering them to interact more confidently on social media. The photographs…
How interpretable are the features of leading vision models? The question is increasingly pressing as these models move from research benchmarks into high-stakes deployments, yet existing methods cannot answer it reliably. We close this gap…
Pre-training representations acquired via self-supervised learning could achieve high accuracy on even tasks with small training data. Unlike in vision and natural language processing domains, pre-training for IMU-based applications is…
Interactive Machine Teaching (IMT) systems allow non-experts to easily create Machine Learning (ML) models. However, existing vision-based IMT systems either ignore annotations on the objects of interest or require users to annotate in a…
Since early machine learning models, metrics such as accuracy and precision have been the de facto way to evaluate and compare trained models. However, a single metric number doesn't fully capture the similarities and differences between…
Reliable markerless motion tracking of people participating in a complex group activity from multiple moving cameras is challenging due to frequent occlusions, strong viewpoint and appearance variations, and asynchronous video streams. To…
High-resolution optical tactile sensors are increasingly used in robotic learning environments due to their ability to capture large amounts of data directly relating to agent-environment interaction. However, there is a high barrier of…
Visual icons provide immediate recognition of features on print maps but do not translate well for touch reading by people who are blind or have low vision due to the low fidelity of tactile perception. We explored 3D printed icons as an…
As handheld video cameras are now commonplace and available in every smartphone, images and videos can be recorded almost everywhere at anytime. However, taking a quick shot frequently yields a blurry result due to unwanted camera shake…
Visually impaired (VI) people often face challenges when performing everyday tasks and identify shopping for clothes as one of the most challenging. Many engage in online shopping, which eliminates some challenges of physical shopping.…
Teachers of the visually impaired (TVIs) regularly present tactile materials (tactile graphics, 3D models, and real objects) to students with vision impairments. Researchers have been increasingly interested in designing tools to support…
Personal devices (e.g. laptops, tablets, and mobile phones) are conventional in daily life and have the ability to store users' private data. The security problems related to these appliances have become a primary concern for both users and…
Compared to machines, humans are extremely good at classifying images into categories, especially when they possess prior knowledge of the categories at hand. If this prior information is not available, supervision in the form of teaching…
Shared control improves Human-Robot Interaction by reducing the user's workload and increasing the robot's autonomy. It allows robots to perform tasks under the user's supervision. Current eye-tracking-driven approaches face several…
Learning object detectors requires massive amounts of labeled training samples from the specific data source of interest. This is impractical when dealing with many different sources (e.g., in camera networks), or constantly changing ones…
Measures of face-identification proficiency are essential to ensure accurate and consistent performance by professional forensic face examiners and others who perform face-identification tasks in applied scenarios. Current proficiency tests…
Automatically understanding the contents of an image is a highly relevant problem in practice. In e-commerce and social media settings, for example, a common problem is to automatically categorize user-provided pictures. Nowadays, a…