Gangyan Zeng

Venues

Frequent coauthors

Papers

1. CLIP is Almost All You Need: Towards Parameter-Efficient Scene Text Retrieval without OCR
   CVPR 2025 ·

   Xugong Qin

   DBLP profile ↗ORCID search ↗
2. Gather and Trace: Rethinking Video TextVQA from an Instance-oriented Perspective
   ACM MM 2025 ·

   Yan Zhang

   DBLP profile ↗ORCID search ↗
3. PerturbCTC: Improving Alignment in Scene Text Recognition with Feature Perturbation Based CTC
   ICDAR 2025 ·

   Zeng Li

   DBLP profile ↗ORCID search ↗
4. Towards Natural Language-Based Document Image Retrieval: New Dataset and Benchmark
   CVPR 2025 ·

   Hao Guo

   DBLP profile ↗ORCID search ↗
5. Track the Answer: Extending TextVQA from Image to Video with Spatio-Temporal Clues
   AAAI 2025 ·

   Yan Zhang

   DBLP profile ↗ORCID search ↗
6. When Semantics Mislead Vision: Mitigating Large Multimodal Models Hallucinations in Scene Text Spotting and Understanding
   NeurIPS 2025 ·

   Yan Shu

   DBLP profile ↗ORCID search ↗
7. Focus, Distinguish, and Prompt: Unleashing CLIP for Efficient and Flexible Scene Text Retrieval
   ACM MM 2024 · Gangyan Zeng