Siamese network has been a de facto benchmark framework for 3D LiDAR obj...
The conjugate gradient method is a crucial first-order optimization meth...
Despite significant progress in Text-to-Image (T2I) generative models, e...
Class prototype construction and matching are core aspects of few-shot a...
Applying large-scale pre-trained visual models like CLIP to few-shot act...
Neural network quantization is a very promising solution in the field of...
Semantic scene completion (SSC) jointly predicts the semantics and geome...
Reliable LiDAR panoptic segmentation (LPS), including both semantic and
...
Recently, neural implicit surfaces have become popular for multi-view
re...
In this letter, a novel method for change detection is proposed using
ne...
Deep learning-based change detection using remote sensing images has rec...
In this paper, we consider Discretized Neural Networks (DNNs) consisting...
Spatial and temporal modeling is one of the most core aspects of few-sho...
Curve-based methods are one of the classic lane detection methods. They ...
Recently, the image-wise implicit neural representation of videos, NeRV,...
The visual world naturally exhibits a long-tailed distribution of open
c...
Referring image segmentation is a typical multi-modal task, which aims a...
Visual object tracking performance has been dramatically improved in rec...
The canonical approach to video action recognition dictates a neural mod...
Remarkable results have been achieved by DCNN based self-supervised dept...
Recently, Space-Time Memory Network (STM) based methods have achieved
st...
Depth completion aims to recover a dense depth map from a sparse depth m...
Recent years have witnessed the significant progress of action recogniti...
Due to the difficulty in generating the effective descriptors which are
...
This paper presents a novel end-to-end dynamic time-lapse video generati...
Corpus-based statistical analysis plays a significant role in linguistic...
Recent works have shown how realistic talking face images can be obtaine...
Small object detection remains an unsolved challenge because it is hard ...
Spatiotemporal and motion features are two complementary and crucial
inf...
Structured output support vector machine (SVM) based tracking algorithms...
Acquiring the accurate 3-D position of a target person around a robot
pr...