Related papers: SliceType: Fast Gaze Typing with a Merging Keyboar…
Gaze estimation, the task of predicting where an individual is looking, is a critical task with direct applications in areas such as human-computer interaction and virtual reality. Estimating the direction of looking in unconstrained…
Pushing forward the compute efficacy frontier in deep learning is critical for tasks that require frequent model re-training or workloads that entail training a large number of models. We introduce SliceOut -- a dropout-inspired scheme…
When humans perform complex insertion tasks such as pushing a cup into a cupboard, routing a cable, or putting a key in a lock, they wiggle the object and adapt the process through tactile feedback. A similar robotic approach has not been…
This work presents Squeeze, an efficient compact fractal processing scheme for tensor core GPUs. By combining discrete-space transformations between compact and expanded forms, one can do data-parallel computation on a fractal with…
Automatic unknown word detection techniques can enable new applications for assisting English as a Second Language (ESL) learners, thus improving their reading experiences. However, most modern unknown word detection methods require…
Intent detection and slot filling are two main tasks in natural language understanding and play an essential role in task-oriented dialogue systems. The joint learning of both tasks can improve inference accuracy and is popular in recent…
Determining the direction in which a person is looking is an important problem in a wide range of HCI applications. In this paper we describe a highly accurate algorithm that performs gaze estimation using an affordable and widely available…
Gaze object detection and gaze following are fundamental tasks for interpreting human gaze behavior or intent. However, most previous methods usually solve these two tasks separately, and their prediction of gaze objects and gaze following…
This article explores the use of a location-aware mid-air gesture-based command triplet syntax to interact with a smart space. The syntax, inspired by human language, is built as a vocative case with an imperative structure. In a sentence…
Face swapping combines one face's identity with another face's non-appearance attributes (expression, head pose, lighting) to generate a synthetic face. This technology is rapidly improving, but falls flat when reconstructing some…
With the escalated demand of human-machine interfaces for intelligent systems, development of gaze controlled system have become a necessity. Gaze, being the non-intrusive form of human interaction, is one of the best suited approach.…
In this letter, we propose a new method, Multi-Clue Gaze (MCGaze), to facilitate video gaze estimation via capturing spatial-temporal interaction context among head, face, and eye in an end-to-end learning way, which has not been well…
We present our current research on the implementation of gaze as an efficient and usable pointing modality supplementary to speech, for interacting with augmented objects in our daily environment or large displays, especially immersive…
We present GazeGen, a user interaction system that generates visual content (images and videos) for locations indicated by the user's eye gaze. GazeGen allows intuitive manipulation of visual content by targeting regions of interest with…
Speed and consistency of target-shifting play a crucial role in human ability to perform complex tasks. Shifting our gaze between objects of interest quickly and consistently requires changes both in depth and direction. Gaze changes in…
Efficiently entering information into a computer is key to enjoying the benefits of computing. This paper describes three intelligent user interfaces: handwriting recognition, adaptive menus, and predictive fillin. In the context of adding…
Motivation: Spliced alignment refers to the alignment of messenger RNA (mRNA) or protein sequences to eukaryotic genomes. It plays a critical role in gene annotation and the study of gene functions. Accurate spliced alignment demands…
Interactive segmentation enables users to extract masks by providing simple annotations to indicate the target, such as boxes, clicks, or scribbles. Among these interaction formats, scribbles are the most flexible as they can be of…
Self-attention has become increasingly popular in a variety of sequence modeling tasks from natural language processing to recommendation, due to its effectiveness. However, self-attention suffers from quadratic computational and memory…
Python type annotations enable static type checking, but most code remains untyped because manual annotation is time-consuming and tedious. Past approaches to automatic type inference fall short: static methods struggle with dynamic…