activity
20242026
collaborators
Showing cs.CVShow all

8 papers · 1 filter

cs.CV2026

SoLA-Vision: Fine-grained Layer-wise Linear Softmax Hybrid Attention

Ruibang Li, Guan Luo, Yiwei Zhang +3

Standard softmax self-attention excels in vision tasks but incurs quadratic complexity O(N^2), limiting high-resolution deployment. Linear attention reduces the cost to O(N), yet i…

cs.CV2026

Integrating Diverse Assignment Strategies into DETRs

Yiwei Zhang, Jin Gao, Hanshi Wang +4

Label assignment is a critical component in object detectors, particularly within DETR-style frameworks where the one-to-one matching strategy, despite its end-to-end elegance, suf…

cs.CV2025

Online Segment Any 3D Thing as Instance Tracking

Hanshi Wang, Zijian Cai, Jin Gao +4

Online, real-time, and fine-grained 3D segmentation constitutes a fundamental capability for embodied intelligent agents to perceive and comprehend their operational environments.…

cs.CV2025

AutoPrune: Each Complexity Deserves a Pruning Policy

Hanshi Wang, Yuhao Xu, Zekun Xu +5

The established redundancy in visual tokens within large vision-language models allows pruning to effectively reduce their substantial computational demands. Previous methods typic…

cs.CV2025

MambaFusion: Height-Fidelity Dense Global Fusion for Multi-modal 3D Object Detection

Hanshi Wang, Jin Gao, Weiming Hu +1

We present the first work demonstrating that a pure Mamba block can achieve efficient Dense Global Fusion, meanwhile guaranteeing top performance for camera-LiDAR multi-modal 3D ob…

cs.CV2025

PFSD: A Multi-Modal Pedestrian-Focus Scene Dataset for Rich Tasks in Semi-Structured Environments

Yueting Liu, Hanshi Wang, Zhengjun Zha +2

Recent advancements in autonomous driving perception have revealed exceptional capabilities within structured environments dominated by vehicular traffic. However, current percepti…