Chengyin Li

7 papers · 2022–2026 · 5 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 · Silver 🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (17) 🔥 Unstoppable · Bronze

Venues

IJCAI (2) WACV (2) CVPR (1) ECCV (1) NeurIPS (1)

Top co-authors

Dongxiao Zhu (7) Yao Qiang (5) Prashant Khanduri (4) Rafi Ibn Sultan (3) Deng Pan (2) Xin Li (2) Marco Brocanelli (2) Chetty Indrin (2) Hui Zhu (2) Hassan Bagher Ebadian (1)

Research topics

Artificial Intelligence (6) Core AI (6) Computer Vision (3) Machine Learning (3) Domain-Specific (2) Processing (2) Deep Learning (1) Healthcare & Medicine (1) Analysis (1) Application Areas (1) Architectures (1) Clinical (1) Core Methods (1) Learning Types (1) Techniques (1)

Keywords

medical image segmentation (2) computed tomography (2) attention mechanism (1) data augmentation (1) depth estimation (1) visual grounding (1) feature importance (1) neural network interpretability (1) feature attribution (1) deep neural network (1) bias mitigation (1) foundation model (1) 3d segmentation (1) vision-language model (1) counterfactual reasoning (1) pedestrian navigation (1) text embedding (1) skip connection (1) parameter-efficient adaptation (1) attention weight (1)

Papers

WalkGPT: Grounded Vision-Language Conversation with Depth-Aware Segmentation for Pedestrian Navigation CVPR 2026 AutoProSAM: Automated Prompting SAM for 3D Multi-Organ Segmentation WACV 2025 MulModSeg: Enhancing Unpaired Multi-Modal Medical Image Segmentation with Modality-Conditioned Text Embedding and Alternating Training WACV 2025 Fairness-aware Vision Transformer via Debiased Self-Attention ECCV 2024 Negative Flux Aggregation to Estimate Feature Attributions IJCAI 2023 AttCAT: Explaining Transformers via Attentive Class Activation Tokens NeurIPS 2022 Counterfactual Interpolation Augmentation (CIA): A Unified Approach to Enhance Fairness and Explainability of DNN IJCAI 2022