Prototype-based embedding network for scene graph generation

C Zheng, X Lyu, L Gao, B Dai… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Abstract Current Scene Graph Generation (SGG) methods explore contextual information to
predict relationships among entity pairs. However, due to the diverse visual appearance of …

Sgtr: End-to-end scene graph generation with transformer

R Li, S Zhang, X He - … of the IEEE/CVF conference on …, 2022 - openaccess.thecvf.com
Abstract Scene Graph Generation (SGG) remains a challenging visual understanding task
due to its compositional property. Most previous works adopt a bottom-up two-stage or a …

Compositional feature augmentation for unbiased scene graph generation

L Li, G Chen, J **ao, Y Yang… - Proceedings of the …, 2023 - openaccess.thecvf.com
Abstract Scene Graph Generation (SGG) aims to detect all the visual relation triplets< sub,
pred, obj> in a given image. With the emergence of various advanced techniques for better …

Visually-prompted language model for fine-grained scene graph generation in an open world

Q Yu, J Li, Y Wu, S Tang, W Ji… - Proceedings of the …, 2023 - openaccess.thecvf.com
Abstract Scene Graph Generation (SGG) aims to extract< subject, predicate, object>
relationships in images for vision understanding. Although recent works have made steady …

Vision relation transformer for unbiased scene graph generation

G Sudhakaran, DS Dhami… - Proceedings of the …, 2023 - openaccess.thecvf.com
Recent years have seen a growing interest in Scene Graph Generation (SGG), a
comprehensive visual scene understanding task that aims to predict entity relationships …

Unbiased scene graph generation via two-stage causal modeling

S Sun, S Zhi, Q Liao, J Heikkilä… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Despite the impressive performance of recent unbiased Scene Graph Generation (SGG)
methods, the current debiasing literature mainly focuses on the long-tailed distribution …

Zero-shot visual relation detection via composite visual cues from large language models

L Li, J **ao, G Chen, J Shao… - Advances in Neural …, 2024 - proceedings.neurips.cc
Pretrained vision-language models, such as CLIP, have demonstrated strong generalization
capabilities, making them promising tools in the realm of zero-shot visual recognition. Visual …

Scene graph refinement network for visual question answering

T Qian, J Chen, S Chen, B Wu… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Visual Question Answering aims to answer the free-form natural language question based
on the visual clues in a given image. It is a difficult problem as it requires understanding the …

Hilo: Exploiting high low frequency relations for unbiased panoptic scene graph generation

Z Zhou, M Shi, H Caesar - Proceedings of the IEEE/CVF …, 2023 - openaccess.thecvf.com
Abstract Panoptic Scene Graph generation (PSG) is a recently proposed task in image
scene understanding that aims to segment the image and extract triplets of subjects, objects …

Unbiased heterogeneous scene graph generation with relation-aware message passing neural network

K Yoon, K Kim, J Moon, C Park - … of the AAAI Conference on Artificial …, 2023 - ojs.aaai.org
Recent scene graph generation (SGG) frameworks have focused on learning complex
relationships among multiple objects in an image. Thanks to the nature of the message …