activity
20232026
most citedLabel-efficient Segmentation via Affinity Propagation

3 citations · 8 across the 15 of their papers we have counts for

collaborators
Showing 2024 · cs.CVShow all

7 papers · 2 filters

cs.CV2024

ReliOcc: Towards Reliable Semantic Occupancy Prediction via Uncertainty Learning

Song Wang, Zhongdao Wang, Jiawei Yu +4

Vision-centric semantic occupancy prediction plays a crucial role in autonomous driving, which requires accurate and reliable predictions from low-cost sensors. Although having not…

cs.CV2024

TokenPacker: Efficient Visual Projector for Multimodal LLM

Wentong Li, Yuqian Yuan, Jian Liu +5

The visual projector serves as an essential bridge between the visual encoder and the Large Language Model (LLM) in a Multimodal LLM (MLLM). Typically, MLLMs adopt a simple MLP to…

cs.CV2024

Label-efficient Semantic Scene Completion with Scribble Annotations

Song Wang, Jiawei Yu, Wentong Li +4

Semantic scene completion aims to infer the 3D geometric structures with semantic classes from camera or LiDAR, which provide essential occupancy information in autonomous driving.…

cs.CV2024

DTCLMapper: Dual Temporal Consistent Learning for Vectorized HD Map Construction

Siyu Li, Jiacheng Lin, Hao Shi +5

Temporal information plays a pivotal role in Bird's-Eye-View (BEV) driving scene understanding, which can alleviate the visual information sparsity. However, the indiscriminate tem…

cs.CV2024★ 2 cited

Not All Voxels Are Equal: Hardness-Aware Semantic Scene Completion with Self-Distillation

Song Wang, Jiawei Yu, Wentong Li +4

Semantic scene completion, also known as semantic occupancy prediction, can provide dense geometric and semantic information for autonomous vehicles, which attracts the increasing…

cs.CV2024★ 1 cited

MGMap: Mask-Guided Learning for Online Vectorized HD Map Construction

Xiaolu Liu, Song Wang, Wentong Li +3

Currently, high-definition (HD) map construction leans towards a lightweight online generation tendency, which aims to preserve timely and reliable road scene information. However,…