As the most critical components in a sentence, subject, predicate and ob...
Domain adaptive detection aims to improve the generality of a detector,
...
Multi-object tracking (MOT) is a fundamental problem in computer vision ...
In the digital age, data is a valuable commodity, and data marketplaces ...
Recent video inpainting methods have made remarkable progress by utilizi...
The vanilla image completion approaches are sensitive to the large missi...
Lexicographic Ranking SuperMartingale (LexRSM) is a generalization of Ra...
Current arbitrary style transfer models are limited to either image or v...
Video captioning aims to describe the content of videos using natural
la...
Planar object tracking is a critical computer vision problem and has dra...
In this paper, we develop a new method, termed SDF-3DGAN, for 3D object
...
Correlated Equilibrium (CE) is a well-established solution concept that
...
Domain adaptive detection aims to improve the generalization of detector...
Automatic security inspection relying on computer vision technology is a...
Image inpainting seeks a semantically consistent way to recover the corr...
Image inpainting is an ill-posed problem to recover missing or damaged i...
Video transition effects are widely used in video editing to connect sho...
This paper describes our champion solution for the CVPR2022 Generic Even...
Generic Event Boundary Detection (GEBD) aims to detect moments where hum...
Multi-animal tracking (MAT), a multi-object tracking (MOT) problem, is
c...
Domain adaptive object detection is challenging due to distinctive data
...
Generic event boundary detection aims to localize the generic, taxonomy-...
The recent mean field game (MFG) formalism has enabled the application o...
Prohibited items detection in X-ray images often plays an important role...
Automatic security inspection using computer vision technology is a
chal...
This report presents the approach used in the submission of Generic Even...
Object detection has taken advantage of the advances in deep convolution...
Unsupervised domain adaptation is critical in various computer vision ta...
The convention standard for object detection uses a bounding box to repr...
The lack of interpretability of existing CNN-based hand detection method...
The majority of existing human parsing methods formulate the task as sem...
In this paper, we present a novel siamese motion-aware network (SiamMan)...
Fine-grained visual categorization (FGVC) is an important but challengin...
Object detection and counting are related but challenging problems,
espe...
We address the problem of combining sequence models of symbolic music wi...
Existing hand detection methods usually follow the pipeline of multiple
...
Automatic Check-Out (ACO) receives increased interests in recent years. ...