MaskBooster: End-to-End Self-Training for Sparsely Supervised Instance Segmentation

von Zheng, Shida
Veröffentlicht in AAAI Conference on Artificial Intelligence (37. : 2023 : Washington, DC; Online) 37th AAAI Conference on Artificial Intelligence (AAAI-23) ; Volume 3, part 2 of 2 (2023)

Adapting on Long-Tail Domains by High Quality Self-training for Object Detection

von Li, Duo
Veröffentlicht in IFTC (18. : 2021 : Schanghai) Digital TV and wireless multimedia communications (2022)

SAViT: Structure-Aware Vision Transformer Pruning via Collaborative Optimization

von Zheng, Chuanyang
Veröffentlicht in NeurIPS (36. : 2022 : New Orleans, La.; Online) 36th Conference on Neural Information Processing Systems (NeurIPS 2022 ; Volume 12 of 50 (2023)

Reciprocal Feature Learning via Explicit and Implicit Tasks in Scene Text Recognition

von Jiang, Hui
Veröffentlicht in ICDAR (16. : 2021 : Lausanne) Document Analysis and Recognition - ICDAR 2021 ; Part 1 (2021)

LGPMA: Complicated Table Structure Recognition with Local and Global Pyramid Mask Alignment

von Qiao, Liang
Veröffentlicht in ICDAR (16. : 2021 : Lausanne) Document Analysis and Recognition - ICDAR 2021 ; Part 1 (2021)