Monocular depth estimation is an ill-posed problem as the same 2D image ...
Evaluating the performance of perception modules in autonomous driving i...
In order to deal with the sparse and unstructured raw point clouds, LiDA...
Motion forecasting is a key module in an autonomous driving system. Due ...
The SportsMOT competition aims to solve multiple object tracking of athl...
To safely navigate in various complex traffic scenarios, autonomous driv...
By ensuring differential privacy in the learning algorithms, one can
rig...
Traffic light recognition, as a critical component of the perception mod...
This article aims to use graphic engines to simulate a large number of
t...
This article is a discussion of Zanella and Roberts' paper: Multilevel l...
The Multiple-try Metropolis (MTM) method is an interesting extension of ...
Reconstruction of human clothing is an important task and often relies o...
3D multi-object tracking in LiDAR point clouds is a key ingredient for
s...
Safety is a critical concern for the next generation of autonomy that is...
Deep convolutional neural networks have been widely employed as an effec...
Autonomous driving can benefit from motion behavior comprehension when
i...
Existing work on object detection often relies on a single form of
annot...
One central question for video action recognition is how to model motion...
Although a significant progress has been witnessed in supervised person
...
Phrase grounding, the problem of associating image regions to caption wo...
In comparison with person re-identification (ReID), which has been widel...
The AI City Challenge was created to accelerate intelligent video analys...
The vulnerability of artificial intelligence (AI) and machine learning (...
This paper presents the Neural Network Verification (NNV) software tool,...
Weakly supervised learning has emerged as a compelling tool for object
d...
Deep neural networks have been widely applied as an effective approach t...
Ubiquitous systems with End-Edge-Cloud architecture are increasingly bei...
We simulate data using a graphic engine to augment real-world datasets, ...
Dancing to music is an instinctive move by humans. Learning to model the...
Average precision (AP) is a widely used metric to evaluate detection acc...
Recurrent neural networks (RNNs) are omnipresent in sequence modeling ta...
In this paper, we propose Spatio-TEmporal Progressive (STEP) action
dete...
Person re-identification (re-id) remains challenging due to significant
...
Urban traffic optimization using traffic cameras as sensors is driving t...
Internet of Things (IoT) have motivated a paradigm shift in the developm...
In this paper, we address the challenging problem of spatial and tempora...
This survey presents an overview of verification techniques for autonomo...
We investigate two crucial and closely related aspects of CNNs for optic...
In this paper, we address the challenging problem of effi- cient tempora...
We present a compact but effective CNN model for optical flow, called
PW...
Visual signals in a video can be divided into content and motion. While
...