Related papers: Parallel Multiscale Autoregressive Density Estimat…

To address the sequential changes of images including poses, in this paper we propose a recurrent regression neural network(RRNN) framework to unify two classic tasks of cross-pose face recognition on still images and video-based face…

In this work we describe a Convolutional Neural Network (CNN) to accurately predict the scene illumination. Taking image patches as input, the CNN works in the spatial domain without using hand-crafted features that are employed by most…

This paper proposes to go beyond the state-of-the-art deep convolutional neural network (CNN) by incorporating the information from object detection, focusing on dealing with fine-grained image classification. Unfortunately, CNN suffers…

We propose a new model for unsupervised document embedding. Leading existing approaches either require complex inference or use recurrent neural networks (RNN) that are difficult to parallelize. We take a different route and develop a…

Semantic inpainting is the task of inferring missing pixels in an image given surrounding pixels and high level image semantics. Most semantic inpainting algorithms are deterministic: given an image with missing regions, a single inpainted…

Recurrent Neural Network (RNN) has been widely applied for sequence modeling. In RNN, the hidden states at current step are full connected to those at previous step, thus the influence from less related features at previous step may…

Similarity analysis using neural networks has emerged as a powerful technique for understanding and categorizing complex patterns in various domains. By leveraging the latent representations learned by neural networks, data objects such as…

Recent advances in diffusion-based text-to-image generation have demonstrated promising results through visual condition control. However, existing ControlNet-like methods struggle with compositional visual conditioning - simultaneously…

Pixel synthesis is a promising research paradigm for image generation, which can well exploit pixel-wise prior knowledge for generation. However, existing methods still suffer from excessive memory footprint and computation overhead. In…

Superpixels are a useful representation to reduce the complexity of image data. However, to combine superpixels with convolutional neural networks (CNNs) in an end-to-end fashion, one requires extra models to generate superpixels and…

With the continuous trend of data explosion, delivering packets from data servers to end users causes increased stress on both the fronthaul and backhaul traffic of mobile networks. To mitigate this problem, caching popular content closer…

Object classification is one of the many holy grails in computer vision and as such has resulted in a very large number of algorithms being proposed already. Specifically in recent years there has been considerable progress in this area…

Thanks to the ability of providing an immersive and interactive experience, the uptake of 360 degree image content has been rapidly growing in consumer and industrial applications. Compared to planar 2D images, saliency prediction for 360…

Scaling CNN training is necessary to keep up with growing datasets and reduce training time. We also see an emerging need to handle datasets with very large samples, where memory requirements for training are large. Existing training…

Photonic computing shows great potential for signal processing and artificial intelligence (AI) acceleration due to its ultra-high speed, low energy consumption, and inherent parallelism. Existing photonic computing research has mainly…

Human observers can learn to recognize new categories of images from a handful of examples, yet doing so with artificial ones remains an open challenge. We hypothesize that data-efficient recognition is enabled by representations which make…

Compared with electrical neural networks, optical neural networks (ONNs) have the potentials to break the limit of the bandwidth and reduce the consumption of energy, and therefore draw much attention in recent years. By far, several types…

We propose a technique to train semantic part-based models of object classes from Google Images. Our models encompass the appearance of parts and their spatial arrangement on the object, specific to each viewpoint. We learn these rich…

Neural Image Classifiers are effective but inherently hard to interpret and susceptible to adversarial attacks. Solutions to both problems exist, among others, in the form of counterfactual examples generation to enhance explainability or…

Annotating images with pixel-wise labels is a time-consuming and costly process. Recently, DatasetGAN showcased a promising alternative - to synthesize a large labeled dataset via a generative adversarial network (GAN) by exploiting a small…