We present InstructDiffusion, a unifying and generic framework for align...
The past decade has witnessed the rapid development of ML and DL
methodo...
The dynamic request patterns of machine learning (ML) inference workload...
The past decade has witnessed many great successes of machine learning (...
In this work, we investigate the problem of creating high-fidelity 3D co...
This work focuses on sign language retrieval-a recently proposed task fo...
While generative modeling has been ubiquitous in natural language proces...
Denoising diffusion models have been a mainstream approach for image
gen...
Automated apple harvesting has attracted significant research interest i...
In this paper, we point out that the essential differences between CNN-b...
Recent years have witnessed significant growth of face alignment. Though...
Recent studies have shown that CLIP has achieved remarkable success in
p...
Copy-Paste is a simple and effective data augmentation strategy for inst...
Language-guided image editing has achieved great success recently. In th...
We present SinDiffusion, leveraging denoising diffusion models to captur...
Diverse image completion, a problem of generating various ways of fillin...
Weed management plays an important role in many modern agricultural
appl...
State-of-the-art face recognition models show impressive accuracy, achie...
In contrast to the traditional avatar creation pipeline which is a costl...
This paper presents a simple yet effective framework MaskCLIP, which
inc...
Event-triggered model predictive control (eMPC) is a popular optimal con...
We propose bootstrapped masked autoencoders (BootMAE), a new approach fo...
Denoising Diffusion Probabilistic Models (DDPMs) have achieved remarkabl...
In this paper, we present the Intra- and Inter-Human Relation Networks
(...
Recent years have seen a surge of interest in meta-learning techniques f...
Vector quantized diffusion (VQ-Diffusion) is a powerful generative model...
Masked image modeling (MIM) learns representations with remarkably good
...
Hybrid precoding is a cost-efficient technique for millimeter wave (mmWa...
In agricultural image analysis, optimal model performance is keenly purs...
This paper aims to address the problem of pre-training for person
re-ide...
Recent image-to-image translation works have been transferred from super...
In this work we propose Identity Consistency Transformer, a novel face
f...
Camera-IMU (Inertial Measurement Unit) sensor fusion has been extensivel...
Despite the tantalizing success in a broad of vision tasks, transformers...
How to learn a universal facial representation that boosts all face anal...
We present the vector quantized diffusion (VQ-Diffusion) model for
text-...
This paper explores a better codebook for BERT pre-training of vision
tr...
Autonomous driving has attracted significant research interests in the p...
Reinforcement learning (RL) is a powerful data-driven control method tha...
Precision weed management offers a promising solution for sustainable
cr...
Cocaine addiction accounts for a large portion of substance use disorder...
Although current face manipulation techniques achieve impressive perform...
Domain adaptation for semantic segmentation enables to alleviate the nee...
Contrastive learning shows great potential in unpaired image-to-image
tr...
Modern building control systems adopt demand control heating, ventilatio...
For autonomous vehicles integrating onto roadways with human traffic
par...
We present CSWin Transformer, an efficient and effective Transformer-bas...
Recent semi-supervised learning (SSL) methods are commonly based on pseu...
Cycle consistency is widely used for face editing. However, we observe t...
Numerous improvements for feedback mechanisms have contributed to the gr...