Qingyu Song

5 papers · 2020–2024 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (11) ❓ The Questioner

Venues

CVPR (2) ICCV (2) AAAI (1)

Top co-authors

Yabiao Wang (3) Changan Wang (3) Ying Tai (3) Chengjie Wang (3) Jilin Li (3) Jian Wu (2) Jiayi Ma (2) Yang Wu (2) Boshen Zhang (1) Haochao Ying (1)

Research topics

Machine Learning (4) Computer Vision (3) Deep Learning (3) Analysis (3) Core Methods (3) Learning Types (2) Mathematics & Optimization (1) Architectures (1) Optimization (1) Optimization & Theory (1)

Keywords

crowd counting (3) robust optimization (1) gradient-based optimization (1) convergence analysis (1) point cloud (1) neural network optimization (1) out-of-distribution generalization (1) 3d object detection (1) semantic information (1) convolutional neural network (1) graph convolution (1) multi-scale feature (1) bounding box (1) count estimation (1) quantization error (1) density map estimation (1) discretization error (1) learning to optimize (1) scale variation (1) hierarchical graph (1)

Papers

Towards Robust Learning to Optimize with Theoretical Guarantees CVPR 2024 Rethinking Counting and Localization in Crowds: A Purely Point-Based Framework ICCV 2021 To Choose or to Fuse? Scale Selection for Crowd Counting AAAI 2021 Uniformity in Heterogeneity: Diving Deep Into Count Interval Partition for Crowd Counting ICCV 2021 A Hierarchical Graph Network for 3D Object Detection on Point Clouds CVPR 2020