Current 3D open-vocabulary scene understanding methods mostly utilize
we...
Vectorized high-definition (HD) maps contain detailed information about
...
Semi-supervised learning is attracting blooming attention, due to its su...
In this work, we propose SAM3D, a novel framework that is able to predic...
Multi-view 3D object detection is becoming popular in autonomous driving...
In recent years, transformer-based detectors have demonstrated remarkabl...
When a small number of poisoned samples are injected into the training
d...
In this paper, we formally address universal object detection, which aim...
Open-vocabulary image segmentation is attracting increasing attention du...
Interactive segmentation enables users to extract masks by providing sim...
Current point cloud segmentation architectures suffer from limited long-...
Referring image segmentation segments an image from a language expressio...
Remote photoplethysmography (rPPG), which aims at measuring heart activi...
Optimization in multi-task learning (MTL) is more challenging than
singl...
Deep Neural Networks (DNNs) are vulnerable to the black-box adversarial
...
Modern retrieval system often requires recomputing the representation of...
As a pioneering work exploring transformer architecture for 3D point clo...
Deep neural network-based image classifications are vulnerable to advers...
Unsupervised domain adaptation in semantic segmentation has been raised ...
Existing automatic data augmentation (DA) methods either ignore updating...
Interactive segmentation allows users to extract target masks by making
...
3D point cloud segmentation has made tremendous progress in recent years...
Referring image segmentation is a fundamental vision-language task that ...
Remote photoplethysmography (rPPG), which aims at measuring heart activi...
Deep neural network-based image classification can be misled by adversar...
In this paper, we present a conceptually simple, strong, and efficient
f...
Tracking objects of interest in a video is one of the most popular and w...
Semantic segmentation has made tremendous progress in recent years. Howe...
Face anti-spoofing (FAS) plays a vital role in securing face recognition...
Knowledge distillation transfers knowledge from the teacher network to t...
We introduce Position Adaptive Convolution (PAConv), a generic convoluti...
2D image representations are in regular grids and can be processed
effic...
Most recent semantic segmentation methods adopt a fully-convolutional ne...
In this paper, we present a conceptually simple, strong, and efficient
f...
Training semantic segmentation models requires a large amount of finely
...
State-of-the-art semantic segmentation methods require sufficient labele...
Recent work has shown that self-attention can serve as a basic building ...
Instance segmentation is an important task for scene understanding. Comp...
Adversarial training is promising for improving robustness of deep neura...
We achieve 3D semantic scene labeling by exploring semantic relation bet...
Albeit intensively studied, false prediction and unclear boundaries are ...
In this paper, we propose a unified panoptic segmentation network (UPSNe...
Disparity estimation for binocular stereo images finds a wide range of
a...
Scene parsing is challenging for unrestricted open vocabulary and divers...