Related papers: SCENIR: Visual Semantic Clarity through Unsupervis…
Graph Edit Distance (GED) is a fundamental graph similarity metric widely used in various applications. However, computing GED is an NP-hard problem. Recent state-of-the-art hybrid GED solver has shown promising performance by formulating…
We propose a graph neural network(GNN) based method to incorporate scene context for the semantic segmentation of 3D LiDAR data. The problem is defined as building a graph to represent the topology of a center segment with its…
Comprehensive semantic segmentation is one of the key components for robust scene understanding and a requirement to enable autonomous driving. Driven by large scale datasets, convolutional neural networks show impressive results on this…
Graph-based convolutional model such as non-local block has shown to be effective for strengthening the context modeling ability in convolutional neural networks (CNNs). However, its pixel-wise computational overhead is prohibitive which…
Over the past few years, a significant progress has been made in deep convolutional neural networks (CNNs)-based image recognition. This is mainly due to the strong ability of such networks in mining discriminative object pose and parts…
Recently, Zero-shot Sketch-based Image Retrieval (ZS-SBIR) has attracted the attention of the computer vision community due to it's real-world applications, and the more realistic and challenging setting than found in SBIR. ZS-SBIR inherits…
Self-supervised representation learning on text-attributed graphs, which aims to create expressive and generalizable representations for various downstream tasks, has received increasing research attention lately. However, existing methods…
Existing Scene Text Recognition (STR) methods typically use a language model to optimize the joint probability of the 1D character sequence predicted by a visual recognition (VR) model, which ignore the 2D spatial context of visual…
Scene graph is structured semantic representation that can be modeled as a form of graph from images and texts. Image-based scene graph generation research has been actively conducted until recently, whereas text-based scene graph…
Object detection, scene graph generation and region captioning, which are three scene understanding tasks at different semantic levels, are tied together: scene graphs are generated on top of objects detected in an image with their pairwise…
Semantic similarity based retrieval is playing an increasingly important role in many IR systems such as modern web search, question-answering, similar document retrieval etc. Improvements in retrieval of semantically similar content are…
Learning from image-text data has demonstrated recent success for many recognition tasks, yet is currently limited to visual features or individual visual concepts such as objects. In this paper, we propose one of the first methods that…
The mainstream image captioning models rely on Convolutional Neural Network (CNN) image features to generate captions via recurrent models. Recently, image scene graphs have been used to augment captioning models so as to leverage their…
Most of current image captioning models heavily rely on paired image-caption datasets. However, getting large scale image-caption paired data is labor-intensive and time-consuming. In this paper, we present a scene graph-based approach for…
Recently image inpainting has witnessed rapid progress due to generative adversarial networks (GAN) that are able to synthesize realistic contents. However, most existing GAN-based methods for semantic inpainting apply an auto-encoder…
State-of-the-art text-to-image models excel at photorealistic rendering but often struggle to capture the layout and object relationships implied by complex prompts. Scene graphs provide a natural structural prior, yet previous graph-guided…
Unsupervised image segmentation is an important task in many real-world scenarios where labelled data is of scarce availability. In this paper we propose a novel approach that harnesses recent advances in unsupervised learning using a…
Scene graph generation has received growing attention with the advancements in image understanding tasks such as object detection, attributes and relationship prediction,~\etc. However, existing datasets are biased in terms of object and…
Research in scene graph generation has quickly gained traction in the past few years because of its potential to help in downstream tasks like visual question answering, image captioning, etc. Many interesting approaches have been proposed…
Image synthesis driven by computer graphics achieved recently a remarkable realism, yet synthetic image data generated this way reveals a significant domain gap with respect to real-world data. This is especially true in autonomous driving…