5 papers
SGFormer++: Semantic Graph Transformer for Incremental 3D Scene Graph Generation
Mengshi Qi, Changsheng Lv, Zijian Fu +2
In this paper, we propose SGFormer++, a novel Semantic Graph Transformer for 3D scene graph generation (SGG), which aims to parse point cloud scenes into semantic structural graphs…
Robo-SGG: Exploiting Layout-Oriented Normalization and Restitution Can Improve Robust Scene Graph Generation
Changsheng Lv, Zijian Fu, Mengshi Qi
In this paper, we propose Robo-SGG, a plug-and-play module for robust scene graph generation (SGG). Unlike standard SGG, the robust scene graph generation aims to perform inference…
Multi-Modal Scene Graph with Kolmogorov-Arnold Experts for Audio-Visual Question Answering
Zijian Fu, Changsheng Lv, Mengshi Qi +2
In this paper, we propose a novel Multi-Modal Scene Graph with Kolmogorov-Arnold Expert Network for Audio-Visual Question Answering (SHRIKE). The task aims to mimic human reasoning…
T2SG: Traffic Topology Scene Graph for Topology Reasoning in Autonomous Driving
Changsheng Lv, Mengshi Qi, Liang Liu +1
Understanding the traffic scenes and then generating high-definition (HD) maps present significant challenges in autonomous driving. In this paper, we defined a novel Traffic Topol…
Robust Disentangled Counterfactual Learning for Physical Audiovisual Commonsense Reasoning
Mengshi Qi, Changsheng Lv, Huadong Ma
In this paper, we propose a new Robust Disentangled Counterfactual Learning (RDCL) approach for physical audiovisual commonsense reasoning. The task aims to infer objects' physics…