Computer vision using deep neural networks (DNNs) has brought about semi...
Hand action recognition is essential. Communication, human-robot
interac...
Following their success in visual recognition tasks, Vision
Transformers...
Emerging large-scale text-to-image generative models, e.g., Stable Diffu...
Zero-cost proxies are nowadays frequently studied and used to search for...
The generalization with respect to domain shifts, as they frequently app...
Deep learning models have proven to be successful in a wide range of mac...
In recent years, optimization in the learned latent space of deep genera...
The success of deep learning is frequently described as the ability to t...
Implicit generative models have been widely employed to model 3D data an...
While neural networks allow highly accurate predictions in many tasks, t...
The generalization with respect to domain shifts, as they frequently app...
Recently, transformers have shown great potential in image classificatio...
The minimum cost multicut problem is the NP-hard/APX-hard combinatorial
...
The efficient, automated search for well-performing neural architectures...
The Minimum Cost Multicut Problem (MP) is a popular way for obtaining a ...
Differentiable architecture search (DARTS) is a widely researched tool f...
The rapid advances in deep generative models over the past years have le...
The minimum cost lifted multicut approach has proven practically good
pe...
Image generation has rapidly evolved in recent years. Modern architectur...
Despite the success of convolutional neural networks (CNNs) in many comp...
Recent advances in deep generative models for photo-realistic images hav...
In computer vision research, the process of automating architecture
engi...
In this paper, we propose an approach to neural architecture search (NAS...
Neural Architecture Search (NAS) is a logical next step in the automatic...
Observable motion in videos can give rise to the definition of objects m...
In this work, we evaluate two different image clustering objectives, k-m...
Generative convolutional deep neural networks, e.g. popular GAN
architec...
Multiple Object Tracking (MOT) is a long-standing task in computer visio...
In computer vision research, the process of automating architecture
engi...
Deep generative models have recently achieved impressive results for man...
We propose a light-weight variational framework for online tracking of o...
We tackle the problem of graph partitioning for image segmentation using...
Occlusions play an important role in disparity and optical flow estimati...
Contextual information is crucial for semantic segmentation. However, fi...
Most state-of-the-art motion segmentation algorithms draw their potentia...
The FlowNet demonstrated that optical flow estimation can be cast as a
l...
In this paper, we tackle the problem of temporally consistent boundary
d...
We propose a novel superpixel-based multi-view convolutional neural netw...
Formulations of the Image Decomposition Problem as a Multicut Problem (M...