Related papers: A Lightweight Neural Network for Monocular View Ge…
Many real-world applications involve data from multiple modalities and thus exhibit the view heterogeneity. For example, user modeling on social media might leverage both the topology of the underlying social network and the content of the…
In this work, we propose a novel meta-learning approach for few-shot classification, which learns transferable prior knowledge across tasks and directly produces network parameters for similar unseen tasks with training samples. Our…
Gaze redirection is the task of changing the gaze to a desired direction for a given monocular eye patch image. Many applications such as videoconferencing, films, games, and generation of training data for gaze estimation require…
Estimating 3D poses from a monocular video is still a challenging task, despite the significant progress that has been made in recent years. Generally, the performance of existing methods drops when the target person is too small/large, or…
Applying convolutional neural networks to large images is computationally expensive because the amount of computation scales linearly with the number of image pixels. We present a novel recurrent neural network model that is capable of…
Training GANs in low-data regimes remains a challenge, as overfitting often leads to memorization or training divergence. In this work, we introduce One-Shot GAN that can learn to generate samples from a training set as little as one image…
For human pose estimation in monocular images, joint occlusions and overlapping upon human bodies often result in deviated pose predictions. Under these circumstances, biologically implausible pose predictions may be produced. In contrast,…
Analyzing complex scenes with Deep Neural Networks is a challenging task, particularly when images contain multiple objects that partially occlude each other. Existing approaches to image analysis mostly process objects independently and do…
Humans excel at building generalizations of new concepts from just one single example. Contrary to this, current computer vision models typically require large amount of training samples to achieve a comparable accuracy. In this work we…
We present an image preprocessing technique capable of improving the performance of few-shot classifiers on abstract visual reasoning tasks. Many visual reasoning tasks with abstract features are easy for humans to learn with few examples…
Monocular depth estimation is an extensively studied computer vision problem with a vast variety of applications. Deep learning-based methods have demonstrated promise for both supervised and unsupervised depth estimation from monocular…
The task of synthesizing novel views from a single image is highly ill-posed due to multiple explanations for unobserved areas. Most current methods tend to generate unseen regions from ambiguity priors and interpolation near input views,…
It is arguable that whether the single camera captured (monocular) image datasets are sufficient enough to train and test convolutional neural networks (CNNs) for imitating the biological neural network structures of the human brain. As…
Recently, many Convolution Neural Networks (CNN) have been successfully employed in bitemporal SAR image change detection. However, most of the existing networks are too heavy and occupy a large volume of memory for storage and calculation.…
Presenting context images to a viewer's peripheral vision is one of the most effective techniques to enhance immersive visual experiences. However, most images only present a narrow view, since the field-of-view (FoV) of standard cameras is…
We formulate truncated singular value decompositions of entire convolutional neural networks. We demonstrate the computed left and right singular vectors are useful in identifying which images the convolutional neural network is likely to…
Novel view synthesis (NVS) seeks to render photorealistic, 3D-consistent images of a scene from unseen camera poses given only a sparse set of posed views. Existing deterministic networks render observed regions quickly but blur unobserved…
Recently, convolutional neural networks (CNNs) have shown great success on the task of monocular depth estimation. A fundamental yet unanswered question is: how CNNs can infer depth from a single image. Toward answering this question, we…
This paper presents a novel joint neural networks approach to address the challenging one-shot object recognition and detection tasks. Inspired by Siamese neural networks and state-of-art multi-box detection approaches, the joint neural…
We present a method that synthesizes novel views of complex scenes by interpolating a sparse set of nearby views. The core of our method is a network architecture that includes a multilayer perceptron and a ray transformer that estimates…