Related papers: Fast projections of two-dimensional light patterns…
Predicting pedestrian crossing intentions is crucial for the navigation of mobile robots and intelligent vehicles. Although recent deep learning-based models have shown significant success in forecasting intentions, few consider incomplete…
As the perception range of LiDAR expands, LiDAR-based 3D object detection contributes ever-increasingly to the long-range perception in autonomous driving. Mainstream 3D object detectors often build dense feature maps, where the cost is…
In autonomous driving, vision-centric 3D object detection recognizes and localizes 3D objects from RGB images. However, due to high annotation costs and diverse outdoor scenes, training data often fails to cover all possible test scenarios,…
Uncertainties in machine learning are a significant roadblock for its application in safety-critical cyber-physical systems (CPS). One source of uncertainty arises from distribution shifts in the input data between training and test…
Optical coherence tomography (OCT) is a prevalent non-invasive imaging method which provides high resolution volumetric visualization of retina. However, its inherent defect, the speckle noise, can seriously deteriorate the tissue…
Deep learning-based dense object detectors have achieved great success in the past few years and have been applied to numerous multimedia applications such as video understanding. However, the current training pipeline for dense detectors…
Optical interferometry has made tremendous development in fundamentals and applications of light. Traditional optical interferometry using simplex plane phase light just allows one dimensional measurement, but incapable of retrieving…
A key challenge for LiDAR-based 3D object detection is to capture sufficient features from large scale 3D scenes especially for distant or/and occluded objects. Albeit recent efforts made by Transformers with the long sequence modeling…
Multi-object tracking (MOT) is a rising topic in video processing technologies and has important application value in consumer electronics. Currently, tracking-by-detection (TBD) is the dominant paradigm for MOT, which performs target…
The highest three-dimensional (3D) resolution possible in in-vivo retinal imaging is achieved by combining optical coherence tomography (OCT) and adaptive optics (AO). However, this combination brings important limitations, such as small…
Acousto-optic imaging (AOI) is a non-invasive method that uses acoustic modulation to map the light fluence inside biological tissue. In many AOI implementations, ultrasound pulses are used in a time-gated measurement to perform…
Optical diffraction tomography (ODT) has emerged as a powerful label-free three-dimensional (3D) bioimaging techniques for observing living cells and thin tissue layers. We report a new reflection-mode ODT (rODT) method for imaging thick…
We introduce powerful ideas from Hyperdimensional Computing into the challenging field of Out-of-Distribution (OOD) detection. In contrast to most existing work that performs OOD detection based on only a single layer of a neural network,…
Dynamic imaging through time-varying scattering media is ubiquitous in real-world settings, yet it remains a defining unsolved problem as rapid spatiotemporal fluctuations overwhelm standard reconstruction pipelines that often rely on…
We introduce asynchronous dynamic decoder, which adopts an efficient A* algorithm to incorporate big language models in the one-pass decoding for large vocabulary continuous speech recognition. Unlike standard one-pass decoding with…
Optical coherence tomography (OCT) is a micrometer-scale, volumetric imaging modality that has become a clinical standard in ophthalmology. OCT instruments image by raster-scanning a focused light spot across the retina, acquiring…
Deep learning has emerged as an effective solution for solving the task of object detection in images but at the cost of requiring large labeled datasets. To mitigate this cost, semi-supervised object detection methods, which consist in…
We present DEF-oriCORN, a framework for language-directed manipulation tasks. By leveraging a novel object-based scene representation and diffusion-model-based state estimation algorithm, our framework enables efficient and robust…
Cooperative perception via communication among intelligent traffic agents has great potential to improve the safety of autonomous driving. However, limited communication bandwidth, localization errors and asynchronized capturing time of…
To achieve high degree of quantum noise squeezing, an optical cavity is often employed to enhance the interaction time between light and matter. Here, we propose to utilize the effect of coherent population trapping (CPT) to directly…