Qi Chu

18

Papers

64

Total Citations

Papers (18)

TCI-Former: Thermal Conduction-Inspired Transformer for Infrared Small Target Detection

Unifying Multi-Modal Uncertainty Modeling and Semantic Alignment for Text-to-Image Person Re-identification

UNICL-SAM: Uncertainty-Driven In-Context Segmentation with Part Prototype Discovery

Rethinking Masked Data Reconstruction Pretraining for Strong 3D Action Representation Learning

Cross-Modality Person Re-Identification With Shared-Specific Feature Transfer

Density-Aware Graph for Deep Semi-Supervised Visual Recognition

Diverse Semantic Image Synthesis via Probability Distribution Modeling

Reduce Information Loss in Transformers for Pluralistic Image Inpainting

Online Multi-Object Tracking Using CNN-Based Single Object Tracker With Spatial-Temporal Attention Mechanism

Geometry Uncertainty Projection Network for Monocular 3D Object Detection

Mining Contextual Information Beyond Image for Semantic Segmentation

Improve Unsupervised Pretraining for Few-Label Transfer

ISNet: Integrate Image-Level and Semantic-Level Context for Semantic Segmentation

UIA-ViT: Unsupervised Inconsistency-Aware Method Based on Vision Transformer for Face Forgery Detection

Counterfactual Intervention Feature Transfer for Visible-Infrared Person Re-identification

FE-CLIP: Frequency Enhanced CLIP Model for Zero-Shot Anomaly Detection and Segmentation

Training-free Open-Vocabulary Semantic Segmentation via Diverse Prototype Construction and Sub-region Matching

Towards More Unified In-context Visual Understanding