Area of research
Computer Vision and Pattern Recognition · Artificial Intelligence
Research interest
Research focused on Artificial intelligence and Segmentation, with related work in Benchmark (surveying), Underwater, Object (grammar). Notable publications include 'TopFormer: Token Pyramid Transformer for Mobile Semantic Segmentation', 'An Experimental-Based Review of Image Enhancement and Image Restoration Methods for Underwater Imaging', and 'Go Closer to See Better: Camouflaged Object Detection via Object Area Amplification and Figure-Ground Conversion'.
A survey on RGB, 3D, and multimodal approaches for unsupervised industrial image anomaly detection
OneTracker: Unifying Visual Object Tracking with Foundation Models and Efficient Tuning
Boosting the transferability of adversarial attacks with global momentum initialization
Go Closer to See Better: Camouflaged Object Detection via Object Area Amplification and Figure-Ground Conversion
ADPL: Adaptive Dual Path Learning for Domain Adaptation of Semantic Segmentation
LVOS: A Benchmark for Long-term Video Object Segmentation
A fine-grained modal label-based multi-stage network for multimodal sentiment analysis
CiCo: Domain-Aware Sign Language Retrieval via Cross-Lingual Contrastive Learning
MSC-AD: A Multiscene Unsupervised Anomaly Detection Dataset for Small Defect Detection of Casting Surface
TopFormer: Token Pyramid Transformer for Mobile Semantic Segmentation
Attribute Surrogates Learning and Spectral Tokens Pooling in Transformers for Few-shot Learning
Weakly-Supervised Salient Object Detection Using Point Supervision
Shape Matters: Deformable Patch Attack
Efficient Universal Shuffle Attack for Visual Object Tracking
Weakly Supervised Video Salient Object Detection via Point Supervision
On the Evaluation of Commit Message Generation Models: An Experimental Study
Rpattack: Refined Patch Attack on General Object Detectors
Improving Zero-Shot Cross-lingual Transfer for Multilingual Question Answering over Knowledge Graph
An Experimental-Based Review of Image Enhancement and Image Restoration Methods for Underwater Imaging
Matching User Photos to Online Products with Robust Deep Features