The rapid development of 3D object detection systems for self-driving ca...
Discovering evolutionary traits that are heritable across species on the...
The uncertainty quantification of prediction models (e.g., neural networ...
Segmenting object parts such as cup handles and animal bodies is importa...
Weakly Supervised Semantic Segmentation (WSSS) with only image-level
sup...
Personalized federated learning (PFL) aims to harness the collective wis...
Out-of-distribution (OOD) detection aims to identify test examples that ...
For a self-driving car to operate reliably, its perceptual system must
g...
Batch Normalization (BN) is commonly used in modern deep neural networks...
This study focuses on embodied agents that can follow natural language
i...
Intermediate features of a pre-trained model have been shown informative...
A self-driving car must be able to reliably handle adverse weather condi...
The ability to read and reason about texts in an image is often lacking ...
Advances in perception for self-driving cars have accelerated in recent ...
The effectiveness of unsupervised domain adaptation degrades when there ...
In most of the literature on federated learning (FL), neural networks ar...
Current 3D object detectors for autonomous driving are almost entirely
t...
Self-driving cars must detect vehicles, pedestrians, and other traffic
p...
We study the problem of developing autonomous agents that can follow hum...
Accurately segmenting teeth and identifying the corresponding anatomical...
Shape and pose estimation is a critical perception problem for a self-dr...
Federated learning is promising for its ability to collaboratively train...
Few-shot learning (FSL) aims to train a strong classifier using limited
...
Model-agnostic meta-learning (MAML) is arguably the most popular
meta-le...
Zero-shot learning aims to recognize unseen objects using their semantic...
Neural networks trained with class-imbalanced data are known to perform
...
Self-driving cars must detect other vehicles and pedestrians in 3D to pl...
Object frequencies in daily scenes follow a long-tailed distribution. Ma...
Federated learning aims to leverage users' own data and computational
re...
Semi-supervised domain adaptation (SSDA) aims to adapt models from a lab...
Existing approaches to depth or disparity estimation output a distributi...
In the domain of autonomous driving, deep learning has substantially imp...
Reliable and accurate 3D object detection is a necessity for safe autono...
In this work, we consider the problem of searching people in an unconstr...
Recent years have witnessed an abundance of new publications and approac...
Person re-identification aims to identify a person from an image collect...
In this work, we introduce VQA 360, a novel task of visual question answ...
We investigate learning a ConvNet classifier with class-imbalanced data....
Few-shot learners aim to recognize new object classes based on a small n...
Object segmentation in three-dimensional (3-D) point clouds is a critica...
Natural images are virtually surrounded by low-density misclassified reg...
Visual question answering (Visual QA) has attracted significant attentio...
Detecting objects such as cars and pedestrians in 3D plays an indispensa...
3D object detection is an essential task in autonomous driving. Recent
t...
Zero-shot learning (ZSL) enables solving a task without the need to see ...
We investigate the problem of cross-dataset adaptation for visual questi...
We propose a novel probabilistic model for visual question answering (Vi...
Visual question answering (QA) has attracted a lot of attention lately, ...
Leveraging class semantic descriptions and examples of known objects,
ze...
We propose a novel supervised learning technique for summarizing videos ...