paper-with-me

Papers

Scene Graph Generation with Geometric Context

2021-11-25 · Vishal Kumar, Albert Mundu, Satish Kumar Singh

Scene Graph Generation has gained much attention in computer vision research with the growing demand in image understanding projects like visual question answering, image captioning, self-driving cars, crowd behavior analysis, activity recognition, and more. Scene graph, a visually grounded graphical structure of an image, immensely helps to simplify the image understanding tasks. In this work, we introduced a post-processing algorithm called Geometric Context to understand the visual scenes better geometrically. We use this post-processing algorithm to add and refine the geometric relationships between object pairs to a prior model. We exploit this context by calculating the direction and distance between object pairs. We use Knowledge Embedded Routing Network (KERN) as our baseline model, extend the work with our algorithm, and show comparable results on the recent state-of-the-art algorithms.

📄 PDF Abstract BibTeX arXiv:2111.13131

Code (0)

등록된 구현이 없습니다.

Tasks

Activity RecognitionGraph GenerationImage CaptioningQuestion AnsweringScene Graph GenerationSelf-Driving CarsVisual Question AnsweringVisual Question Answering (VQA)

Similar Papers 제목 키워드 기반

Fixed External Cameras as Common Prior Maps for Active 3D Scene Graph Generation

2026-05-18 · Giorgia Modi, Davide Buoso, Giuseppe Averta, Daniele De Martini arxiv

Commonly available prior information, such as BIM models, floor plans, and remote sensing images, can provide valuable geometric and semantic context for autonomous robotic systems. In this paper, we treat observations f…

Scene Graph Generation3D Reconstruction

KeySG: Hierarchical Keyframe-Based 3D Scene Graphs

2025-10-01 · Abdelrhman Werby, Dennis Rotondi, Fabio Scaparro, Kai O. Arras arxiv

In recent years, 3D scene graphs have emerged as a powerful world representation, offering both geometric accuracy and semantic richness. Combining 3D scene graphs with large language models enables robots to reason, pla…

Semantic Segmentation

Heuristics for Image Generation from Scene Graphs

2019-03-20 · ICLR Workshop LLD 2019 · Subarna Tripathi, Anahita Bhiwandiwalla, Alexei Bastidas, Hanlin Tang

Generating realistic images from scene graphs requires neural networks to be able to reason about object relationships and compositionality. Learning a sufficiently rich representation to facilitate this reasoning is cha…

Image GenerationImage Generation from Scene GraphsRelation

LinkNet: Relational Embedding for Scene Graph

2018-11-15 · NeurIPS 2018 12 · Sanghyun Woo, Dahun Kim, Donghyeon Cho, In So Kweon

Objects and their relationships are critical contents for image understanding. A scene graph provides a structured description that captures these properties of an image. However, reasoning about the relationships betwee…

Graph GenerationScene Graph Generation

Residual Attention Graph Convolutional Network for Geometric 3D Scene Classification

2019-09-30 · Albert Mosella-Montoro, Javier Ruiz-Hidalgo

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 possibl…

ClassificationGeneral ClassificationScene Classification