Deep learning-based methods have been extensively explored for automatic...
Scene Graph Generation (SGG) plays a pivotal role in downstream
vision-l...
Anomaly detection (AD), aiming to find samples that deviate from the tra...
With the rapid development of the image generation technologies, the
mal...
Recently, the pure camera-based Bird's-Eye-View (BEV) perception provide...
This paper focuses on an important type of black-box attacks, i.e.,
tran...
Inspired by recent advances in diffusion models, which are reminiscent o...
Human action recognition aims at classifying the category of human actio...
Extracting building footprints from remote sensing images has been attra...
Graph Neural Networks (GNNs) have shown remarkable success in graph
repr...
How to effectively leverage the plentiful existing datasets to train a r...
The current success of Graph Neural Networks (GNNs) usually relies on lo...
Recently, few-shot object detection (FSOD) has received much attention f...
Tracking multiple athletes in sports videos is a very challenging
Multi-...
Heterogeneous graph learning has drawn significant attentions in recent
...
Video Anomaly Detection (VAD) is an important topic in computer vision.
...
Transformers have been successfully applied to the visual tracking task ...
Pan-sharpening aims at producing a high-resolution (HR) multi-spectral (...
Human gait is considered a unique biometric identifier which can be acqu...
Occlusions are very common in face images in the wild, leading to the
de...
Dance challenges are going viral in video communities like TikTok nowada...
Though image-level weakly supervised semantic segmentation (WSSS) has
ac...
Deep learning based pan-sharpening has received significant research int...
Differentiable ARchiTecture Search (DARTS) uses a continuous relaxation ...
The transferability and robustness of adversarial examples are two pract...
Fine-grained action recognition is attracting increasing attention due t...
Gait recognition under multiple views is an important computer vision an...
Although much progress has been made recently in 3D face reconstruction,...
The existing auto-encoder based face pose editing methods primarily focu...
In this paper, we propose a transformer based approach for visual ground...
In this paper, an effective pipeline to automatic 4D Facial Expression
R...
Most of the adversarial attack methods suffer from large perceptual
dist...
Boosting performance of the offline trained siamese trackers is getting
...
Objects in aerial images usually have arbitrary orientations and are den...
Hyperspectral image classification (HIC) is an important but challenging...
LiDAR-based 3D object detection is an important task for autonomous driv...
Pan-sharpening aims at fusing a low-resolution (LR) multi-spectral (MS) ...
Crowd counting, which towards to accurately count the number of the obje...
Graph Neural Networks (GNNs) have achieved tremendous success in graph
r...
Coarsely-labeled semantic segmentation annotations are easy to obtain, b...
Object counting, whose aim is to estimate the number of objects from a g...
Co-saliency detection aims to detect common salient objects from a group...
Few-shot object detection (FSOD) helps detectors adapt to unseen classes...
Accurately estimating the number of objects in a single image is a
chall...
Recent years have witnessed great progress in deep learning based object...
Traditional change detection methods usually follow the image differenci...
With the development of deep neural networks, digital fake paintings can...
Estimating accurate number of interested objects from a given image is a...
Recently, Human Attribute Recognition (HAR) has become a hot topic due t...
Pyramidal feature representation is the common practice to address the
c...