Hongjian Zhan

3

Papers

1

Total Citations

Papers (3)

Why 1 + 1 < 1 in Visual Token Pruning: Beyond Naive Integration via Multi-Objective Balanced Covering

MSA2: Multi-task Framework with Structure-aware and Style-adaptive Character Representation for Open-set Chinese Text Recognition

Spotting the Unseen: Reciprocal Consensus Network Guided by Visual Archetypes