no code implementations • 29 Dec 2023 • Qishen Chen, Xinyu Lyu, Haonan Zhang, Pengpeng Zeng, Lianli Gao, Jingkuan Song
Thus, we introduce a plug-and-play method named CITrans, which iteratively trains SGG models with progressively enhanced data.
no code implementations • 10 Aug 2023 • Lianli Gao, Xinyu Lyu, Yuyu Guo, Yuxuan Hu, Yuan-Fang Li, Lu Xu, Heng Tao Shen, Jingkuan Song
It integrates two components: Semantic Debiasing (SD) and Balanced Predicate Learning (BPL), for these imbalances.
no code implementations • 10 Aug 2023 • Xinyu Lyu, Jingwei Liu, Yuyu Guo, Lianli Gao
Long-temporal human actions supervise the model to generate multiple scene graphs that conform to the global constraints and avoid the model being unable to learn the tail predicates.
no code implementations • 9 Aug 2023 • Xinyu Lyu, Lianli Gao, Junlin Xie, Pengpeng Zeng, Yulu Tian, Jie Shao, Heng Tao Shen
To the end, we propose the Multi-Concept Learning (MCL) framework, which ensures a balanced learning process across rare/ uncommon/ common concepts.
1 code implementation • CVPR 2023 • Chaofan Zheng, Xinyu Lyu, Lianli Gao, Bo Dai, Jingkuan Song
Current Scene Graph Generation (SGG) methods explore contextual information to predict relationships among entity pairs.
1 code implementation • 16 Jul 2022 • Chaofan Zheng, Lianli Gao, Xinyu Lyu, Pengpeng Zeng, Abdulmotaleb El Saddik, Heng Tao Shen
Experiments show that our approach achieves a new state-of-the-art performance on VG and GQA datasets and makes a trade-off between the performance of tail predicates and head ones.
no code implementations • 11 Jul 2022 • Xinyu Lyu, Lianli Gao, Pengpeng Zeng, Heng Tao Shen, Jingkuan Song
The performance of current Scene Graph Generation (SGG) models is severely hampered by hard-to-distinguish predicates, e. g., woman-on/standing on/walking on-beach.
no code implementations • 23 Jun 2022 • Chaofan Zheng, Xinyu Lyu, Yuyu Guo, Pengpeng Zeng, Jingkuan Song, Lianli Gao
SCM is proposed to relieve semantic deviation by ensuring the semantic consistency between the generated scene graph and the ground truth in global and local representations.
1 code implementation • CVPR 2022 • Xinyu Lyu, Lianli Gao, Yuyu Guo, Zhou Zhao, Hao Huang, Heng Tao Shen, Jingkuan Song
The performance of current Scene Graph Generation models is severely hampered by some hard-to-distinguish predicates, e. g., "woman-on/standing on/walking on-beach" or "woman-near/looking at/in front of-child".