Despite substantial advances, single-image super-resolution (SISR) is al...
Reconstructing hand-held objects from a single RGB image is an important...
In this paper, we present a novel shape reconstruction method leveraging...
In this paper, we propose U-RED, an Unsupervised shape REtrieval and
Def...
Time series remains one of the most challenging modalities in machine
le...
The top-down and bottom-up methods are two mainstreams of referring
segm...
Large amounts of incremental learning algorithms have been proposed to
a...
Contrastive learning-based video-language representation learning approa...
Interactive segmentation enables users to segment as needed by providing...
Recent years have seen the ever-increasing importance of pre-trained mod...
Existing text-video retrieval solutions are, in essence, discriminant mo...
Unified visual grounding pursues a simple and generic technical route to...
Guided depth map super-resolution (GDSR), which aims to reconstruct a
hi...
Masked image modeling (MIM) has shown great promise for self-supervised
...
Body Mass Index (BMI), age, height and weight are important indicators o...
Adapting object detectors learned with sufficient supervision to novel
c...
Real-time monocular 3D reconstruction is a challenging problem that rema...
Unsupervised foreground-background segmentation aims at extracting salie...
Weakly supervised semantic segmentation is typically inspired by class
a...
The success of state-of-the-art deep neural networks heavily relies on t...
In recent years, generative adversarial networks (GANs) have been an act...
Multiview self-supervised representation learning roots in exploring sem...
Contrastive self-supervised learning (CSL) based on instance discriminat...
In this paper,
we study the episodic reinforcement learning (RL) probl...
Depth map estimation from images is an important task in robotic systems...
Lossless and near-lossless image compression is of paramount importance ...
Vision-based robotic assembly is a crucial yet challenging task as the
i...
Category-level pose estimation is a challenging problem due to intra-cla...
Category-level object pose estimation aims to predict the 6D pose as wel...
While category-level 9DoF object pose estimation has emerged recently,
p...
The success of deep neural networks greatly relies on the availability o...
One of the main challenges for feature representation in deep learning-b...
Modern object detectors have taken the advantages of pre-trained vision
...
Vision-language pre-training (VLP) relying on large-scale pre-training
d...
Compressed Sensing MRI (CS-MRI) aims at reconstructing de-aliased images...
Point clouds upsampling is a challenging issue to generate dense and uni...
This paper gives the first polynomial-time algorithm for tabular Markov
...
6D object pose estimation is a fundamental yet challenging problem in
co...
While 6D object pose estimation has recently made a huge leap forward, m...
Estimating the risk level of adversarial examples is essential for safel...
The semantically disentangled latent subspace in GAN provides rich
inter...
We propose an end-to-end image compression and analysis model with
Trans...
Guided filter is a fundamental tool in computer vision and computer grap...
We study the optimal batch-regret tradeoff for batch linear contextual
b...
Unsupervised reinforcement learning aims to train agents to learn a hand...
Depth estimation from a single image is an active research topic in comp...
Directly regressing all 6 degrees-of-freedom (6DoF) for the object pose ...
Learning with noisy labels is an important and challenging task for trai...
Robust loss functions are essential for training deep neural networks wi...
Multiple instance learning (MIL) is a powerful tool to solve the weakly
...