Related papers: High-frequency near-eye ground truth for event-bas…
Many machine learning systems today are trained on large amounts of human-annotated data. Data annotation tasks that require a high level of competency make data acquisition expensive, while the resulting labels are often subjective,…
Given multiple datasets with different label spaces, the goal of this work is to train a single object detector predicting over the union of all the label spaces. The practical benefits of such an object detector are obvious and significant…
Event-based data are commonly encountered in edge computing environments where efficiency and low latency are critical. To interface with such data and leverage their rich temporal features, we propose a causal spatiotemporal convolutional…
In this survey I discuss ophthalmic neurophysiology and the experimental considerations that must be made to reduce possible noise in an eye-tracking data stream. I also review the history, experiments, technological benefits and…
Orchestrating parametric fitting of multicomponent spectra at scale is an essential yet underappreciated task in high-throughput quantification of materials and chemical composition. To automate the annotation process for spectroscopic and…
Mobile eye-tracking systems have been available for about a decade now and are becoming increasingly popular in different fields of application, including marketing, sociology, usability studies and linguistics. While the user-friendliness…
Visual object tracking acts as a pivotal component in various emerging video applications. Despite the numerous developments in visual tracking, existing deep trackers are still likely to fail when tracking against objects with dramatic…
This paper aims for high-performance offline LiDAR-based 3D object detection. We first observe that experienced human annotators annotate objects from a track-centric perspective. They first label the objects with clear shapes in a track,…
As an alternative sensing paradigm, dynamic vision sensors (DVS) have been recently explored to tackle scenarios where conventional sensors result in high data rate and processing time. This paper presents a hybrid event-frame approach for…
This paper addresses the limitations of current datasets for 3D vision tasks in terms of accuracy, size, realism, and suitable imaging modalities for photometrically challenging objects. We propose a novel annotation and acquisition…
Video salient object detection models trained on pixel-wise dense annotation have achieved excellent performance, yet obtaining pixel-by-pixel annotated datasets is laborious. Several works attempt to use scribble annotations to mitigate…
Optical flow estimation is a fundamental problem in computer vision, yet the reliance on expensive ground-truth annotations limits the scalability of supervised approaches. Although unsupervised and semi-supervised methods alleviate this…
Estimating eye-gaze from images alone is a challenging task, in large parts due to un-observable person-specific factors. Achieving high accuracy typically requires labeled data from test users which may not be attainable in real…
Event cameras contain emerging, neuromorphic vision sensors that capture local light intensity changes at each pixel, generating a stream of asynchronous events. This way of acquiring visual information constitutes a departure from…
We present the first purely event-based method for face detection using the high temporal resolution of an event-based camera. We will rely on a new feature that has never been used for such a task that relies on detecting eye blinks. Eye…
The recent development of online static map element (a.k.a. HD Map) construction algorithms has raised a vast demand for data with ground truth annotations. However, available public datasets currently cannot provide high-quality training…
High-speed vision sensing is essential for real-time perception in applications such as robotics, autonomous vehicles, and industrial automation. Traditional frame-based vision systems suffer from motion blur, high latency, and redundant…
With the surging inclination towards carrying out tasks on computational devices and digital mediums, any method that converts a task that was previously carried out manually, to a digitized version, is always welcome. Irrespective of the…
Existing tracking algorithms typically rely on low-frame-rate RGB cameras coupled with computationally intensive deep neural network architectures to achieve effective tracking. However, such frame-based methods inherently face challenges…
Point annotations are considerably more time-efficient than bounding box annotations. However, how to use cheap point annotations to boost the performance of semi-supervised object detection remains largely unsolved. In this work, we…