Related papers: Normalized and Geometry-Aware Self-Attention Netwo…
We consider the problem of referring image segmentation. Given an input image and a natural language expression, the goal is to segment the object referred by the language expression in the image. Existing works in this area treat the…
Current state-of-the-art neural machine translation (NMT) uses a deep multi-head self-attention network with no explicit phrase information. However, prior work on statistical machine translation has shown that extending the basic…
Image captioning, like many tasks involving vision and language, currently relies on Transformer-based architectures for extracting the semantics in an image and translating it into linguistically coherent descriptions. Although successful,…
Generating natural sentences from images is a fundamental learning task for visual-semantic understanding in multimedia. In this paper, we propose to apply dual attention on pyramid image feature maps to fully explore the visual-semantic…
Skeleton-based action recognition aims to recognize human actions given human joint coordinates with skeletal interconnections. By defining a graph with joints as vertices and their natural connections as edges, previous works successfully…
State-of-the-art approaches for image captioning require supervised training data consisting of captions with paired image data. These methods are typically unable to use unsupervised data such as textual data with no corresponding images,…
We introduce a novel self-attention mechanism, which we call CSA (Chromatic Self-Attention), which extends the notion of attention scores to attention _filters_, independently modulating the feature channels. We showcase CSA in a…
Forensic analysis of manipulated pixels requires the identification of various hidden and subtle features from images. Conventional image recognition models generally fail at this task because they are biased and more attentive toward the…
In recent years, assessing action quality from videos has attracted growing attention in computer vision community and human computer interaction. Most existing approaches usually tackle this problem by directly migrating the model from…
The ability to generate natural language explanations conditioned on the visual perception is a crucial step towards autonomous agents which can explain themselves and communicate with humans. While the research efforts in image and video…
Image captioning is the generation of natural language descriptions of images which have increased immense popularity in the recent past. With this different deep-learning techniques are devised for the development of factual and stylized…
Convolutional neural networks (CNNs) have been shown to be state-of-the-art models for visual cortical neurons. Cortical neurons in the primary visual cortex are sensitive to contextual information mediated by extensive horizontal and…
We introduce a manifold analysis technique for neural network representations. Normalized Space Alignment (NSA) compares pairwise distances between two point clouds derived from the same source and having the same size, while potentially…
The internal workings of modern deep learning models stay often unclear to an external observer, although spatial attention mechanisms are involved. The idea of this work is to translate these spatial attentions into natural language to…
Self-attention has been successfully applied to video representation learning due to the effectiveness of modeling long range dependencies. Existing approaches build the dependencies merely by computing the pairwise correlations along…
Recent advancements in unified image generation models, such as OmniGen, have enabled the handling of diverse image generation and editing tasks within a single framework, accepting multimodal, interleaved texts and images in free form.…
The use of attention models for automated image captioning has enabled many systems to produce accurate and meaningful descriptions for images. Over the years, many novel approaches have been proposed to enhance the attention process using…
Recent Vision Transformer~(ViT) models have demonstrated encouraging results across various computer vision tasks, thanks to their competence in modeling long-range dependencies of image patches or tokens via self-attention. These models,…
In this paper, we propose Dynamic Self-Attention (DSA), a new self-attention mechanism for sentence embedding. We design DSA by modifying dynamic routing in capsule network (Sabouretal.,2017) for natural language processing. DSA attends to…
Image captioning is a challenging task at the intersection of computer vision and natural language processing, requiring models to generate meaningful textual descriptions of images. Traditional approaches rely on recurrent neural networks…