collaborators

5 papers

cs.CV2026

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…

cs.CV2025

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…

cs.AI2025

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…

cs.CV2025

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…

cs.CV2025

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…