Related papers: RTIC: Residual Learning for Text and Image Composi…

Numerous important problems can be framed as learning from graph data. We propose a framework for learning convolutional neural networks for arbitrary graphs. These graphs may be undirected, directed, and with both discrete and continuous…

We consider the problem of composed image retrieval that takes an input query consisting of an image and a modification text indicating the desired changes to be made on the image and retrieves images that match these changes. Current…

We present a model for capturing musical features and creating novel sequences of music, called the Convolutional Variational Recurrent Neural Network. To generate sequential data, the model uses an encoder-decoder architecture with latent…

Conditional image modeling based on textual descriptions is a relatively new domain in unsupervised learning. Previous approaches use a latent variable model and generative adversarial networks. While the formers are approximated by using…

Geometric 3D scene classification is a very challenging task. Current methodologies extract the geometric information using only a depth channel provided by an RGB-D sensor. These kinds of methodologies introduce possible errors due to…

Text-to-image synthesis aims to generate natural images conditioned on text descriptions. The main difficulty of this task lies in effectively fusing text information into the image synthesis process. Existing methods usually adaptively…

Temporal grounding is the task of locating a specific segment from an untrimmed video according to a query sentence. This task has achieved significant momentum in the computer vision community as it enables activity grounding beyond…

Text classification is a quintessential and practical problem in natural language processing with applications in diverse domains such as sentiment analysis, fake news detection, medical diagnosis, and document classification. A sizable…

Recently using convolutional neural networks (CNNs) has gained popularity in visual tracking, due to its robust feature representation of images. Recent methods perform online tracking by fine-tuning a pre-trained CNN model to the specific…

Text-to-image generative models have enabled high-resolution image synthesis across different domains, but require users to specify the content they wish to generate. In this paper, we consider the inverse problem -- given a collection of…

This article aims to provide the information retrieval community with some reflections on recent advances in retrieval learning by analyzing the reproducibility of image-text retrieval models. Due to the increase of multimodal data over the…

Image harmonization task aims at harmonizing different composite foreground regions according to specific background image. Previous methods would rather focus on improving the reconstruction ability of the generator by some internal…

Scene parsing is a technique that consist on giving a label to all pixels in an image according to the class they belong to. To ensure a good visual coherence and a high class accuracy, it is essential for a scene parser to capture image…

The task of text-video retrieval aims to understand the correspondence between language and vision, has gained increasing attention in recent years. Previous studies either adopt off-the-shelf 2D/3D-CNN and then use average/max pooling to…

Conditional computation and modular networks have been recently proposed for multitask learning and other problems as a way to decompose problem solving into multiple reusable computational blocks. We propose a new approach for learning…

We propose an approach to learn spatio-temporal features in videos from intermediate visual representations we call "percepts" using Gated-Recurrent-Unit Recurrent Networks (GRUs).Our method relies on percepts that are extracted from all…

We develop a learning framework for building deformable templates, which play a fundamental role in many image analysis and computational anatomy tasks. Conventional methods for template creation and image alignment to the template have…

Scene graphs are a powerful structured representation of the underlying content of images, and embeddings derived from them have been shown to be useful in multiple downstream tasks. In this work, we employ a graph convolutional network to…

Content-Based Image Retrieval (CIR) aims to search for a target image by concurrently comprehending the composition of an example image and a complementary text, which potentially impacts a wide variety of real-world applications, such as…

This paper investigates a novel task of generating texture images from perceptual descriptions. Previous work on texture generation focused on either synthesis from examples or generation from procedural models. Generating textures from…