In this paper, we present frame reconstruction model: FrameRS. It consis...
Text-to-3D generation from a single-view image is a popular but challeng...
Knowledge distillation (KD) has shown potential for learning compact mod...
Animal visual perception is an important technique for automatically
mon...
Diffusion-based methods can generate realistic images and videos, but th...
Recently, integrating video foundation models and large language models ...
Deep learning has the potential to revolutionize sports performance, wit...
Estimating 3D human poses only from a 2D human pose sequence is thorough...
Although the impressive performance in visual grounding, the prevailing
...
As an important and challenging problem in computer vision, PAnoramic
Se...
When applying a pre-trained 2D-to-3D human pose lifting model to a targe...
Reducing the radiation dose in computed tomography (CT) is important to
...
Medical images often contain artificial markers added by doctors, which ...
With the development of computer-assisted techniques, research communiti...
Cross-view multi-object tracking aims to link objects between frames and...
Image-based fashion design with AI techniques has attracted increasing
a...
Spiking Neural Networks (SNNs), as one of the algorithmic models in
neur...
Multimodal sentiment analysis (MSA) is an important way of observing men...
Anomaly detection aims at identifying deviant samples from the normal da...
Multi-object tracking (MOT) aims to associate target objects across vide...
Video-based action recognition is one of the most popular topics in comp...
Recently, much progress has been made for self-supervised action recogni...
Spiking Neural Network (SNN) is considered more biologically realistic a...
Large-scale datasets are important for the development of deep learning
...
Semi-supervised learning (SSL) is an efficient framework that can train
...
Vehicle tracking is an essential task in the multi-object tracking (MOT)...
Radar has long been a common sensor on autonomous vehicles for obstacle
...
Multi-object tracking (MOT) is an essential task in the computer vision
...
Different from static images, videos contain additional temporal and spa...
To achieve good performance in face recognition, a large scale training
...
3D human pose estimation (HPE) is crucial in many fields, such as human
...
Drones, or general UAVs, equipped with a single camera have been widely
...
Multi-object tracking (MOT) is an important and practical task related t...
Tracking of multiple objects is an important application in AI City gear...