In this work, we construct a large-scale dataset for Ground-to-Aerial Pe...
Recently, learning-based algorithms have achieved promising performance ...
Self-supervised sound source localization is usually challenged by the
m...
Camouflaged object detection (COD), aiming to segment camouflaged object...
Egocentric action anticipation is a challenging task that aims to make
a...
Diffusion models have gained significant popularity in the field of
imag...
Semi-supervised video anomaly detection (VAD) is a critical task in the
...
As a fundamental problem in computer vision, 3D point cloud registration...
Multi-frame depth estimation generally achieves high accuracy relying on...
Non-exemplar class-incremental learning refers to classifying new and ol...
Mapping Low Dynamic Range (LDR) images with different exposures to High
...
Generating a high-quality High Dynamic Range (HDR) image from dynamic sc...
3D single object tracking (SOT) is an indispensable part of automated
dr...
Temporal action localization (TAL) is a prevailing task due to its great...
As the gold standard for phase retrieval, phase-shifting algorithm (PS) ...
Recently, many works have designed wider and deeper networks to achieve
...
To imitate the ability of keeping learning of human, continual learning ...
Recovering clear structures from severely blurry inputs is a challenging...
Multispectral pedestrian detection is an important task for many
around-...
Weakly supervised video anomaly detection (WSVAD) is a challenging task ...
In the current person Re-identification (ReID) methods, most domain
gene...
Convolutional neural networks (CNNs) have obtained remarkable performanc...
Deep convolutional neural networks (CNNs) are used for image denoising v...
Video anomaly detection aims to find the events in a video that do not
c...
With the emergence of large pre-trained vison-language model like CLIP,
...
The fusion of multispectral and panchromatic images is always dubbed
pan...
Accurate semantic segmentation models typically require significant
comp...
Computer vision models for image quality assessment (IQA) predict the
su...
This paper reviews the challenge on constrained high dynamic range (HDR)...
Single image super-resolution (SISR) has played an important role in the...
DeepFake based digital facial forgery is threatening the public media
se...
Multi-modal based speech separation has exhibited a specific advantage o...
For the weakly supervised anomaly detection task, most existing work is
...
Deep learning-based person Re-IDentification (ReID) often requires a lar...
Video anomaly detection (VAD) mainly refers to identifying anomalous eve...
Finding target persons in full scene images with a query of text descrip...
The target representation learned by convolutional neural networks plays...
With the explosive growth of video data, video summarization, which atte...
The training loss function that enforces certain training sample distrib...
The deep-learning-based image restoration and fusion methods have achiev...
Contextual information plays an important role in action recognition. Lo...
Learning cross-view consistent feature representation is the key for acc...
Self-supervised depth estimation has made a great success in learning de...
Blind image deblurring is a fundamental and challenging computer vision
...
Self-supervised depth estimation has shown its great effectiveness in
pr...
Despite the great success of deep model on Hyperspectral imagery (HSI)
s...
Learning to generate a task-aware base learner proves a promising direct...
This paper focuses on developing efficient and robust evaluation metrics...
Fashion products typically feature in compositions of a variety of style...
Few-shot learning aims to recognize instances from novel classes with fe...