Mengshi Qi

12

Papers

60

Total Citations

Papers (12)

SGFormer: Semantic Graph Transformer for Point Cloud-Based 3D Scene Graph Generation

Weakly-Supervised Temporal Action Localization by Inferring Salient Snippet-Feature

Global-Local Tree Search in VLMs for 3D Indoor Scene Generation

VIoTGPT: Learning to Schedule Vision Tools Towards Intelligent Video Internet of Things

KE-GAN: Knowledge Embedded Generative Adversarial Networks for Semi-Supervised Scene Parsing

Imitative Non-Autoregressive Modeling for Trajectory Forecasting and Imputation

RGB-Depth Fusion GAN for Indoor Depth Completion

Unsupervised Self-Driving Attention Prediction via Uncertainty Mining and Knowledge Embedding

Attentive Relational Networks for Mapping Images to Scene Graphs

T2SG: Traffic Topology Scene Graph for Topology Reasoning in Autonomous Driving

Towards Efficient Object Re-Identification with a Novel Cloud-Edge Collaborative Framework

Disentangled Counterfactual Learning for Physical Audiovisual Commonsense Reasoning