584 citations · 637 across the 15 of their papers we have counts for
15 papers · 1 filter
Distilling Object Detectors With Global Knowledge
Sanli Tang, Zhongyu Zhang, Zhanzhan Cheng +4
Knowledge distillation learns a lightweight student model that mimics a cumbersome teacher. Existing methods regard the knowledge as the feature of each instance or their relations…
E2-AEN: End-to-End Incremental Learning with Adaptively Expandable Network
Guimei Cao, Zhanzhan Cheng, Yunlu Xu +4
Expandable networks have demonstrated their advantages in dealing with catastrophic forgetting problem in incremental learning. Considering that different tasks may need different…
TRIE++: Towards End-to-End Information Extraction from Visually Rich Documents
Zhanzhan Cheng, Peng Zhang, Can Li +6
Recently, automatically extracting information from visually rich documents (e.g., tickets and resumes) has become a hot and vital research topic due to its widespread commercial v…
DavarOCR: A Toolbox for OCR and Multi-Modal Document Understanding
Liang Qiao, Hui Jiang, Ying Chen +9
This paper presents DavarOCR, an open-source toolbox for OCR and document understanding tasks. DavarOCR currently implements 19 advanced algorithms, covering 9 different task forms…
Technical Report for ICCV 2021 Challenge SSLAD-Track3B: Transformers Are Better Continual Learners
Duo Li, Guimei Cao, Yunlu Xu +2
In the SSLAD-Track 3B challenge on continual learning, we propose the method of COntinual Learning with Transformer (COLT). We find that transformers suffer less from catastrophic…
A Strong Baseline for Semi-Supervised Incremental Few-Shot Learning
Linglan Zhao, Dashan Guo, Yunlu Xu +5
Few-shot learning (FSL) aims to learn models that generalize to novel classes with limited training samples. Recent works advance FSL towards a scenario where unlabeled examples ar…
Reciprocal Feature Learning via Explicit and Implicit Tasks in Scene Text Recognition
Hui Jiang, Yunlu Xu, Zhanzhan Cheng +5
Text recognition is a popular topic for its broad applications. In this work, we excavate the implicit task, character counting within the traditional text recognition, without add…
MANGO: A Mask Attention Guided One-Stage Scene Text Spotter
Liang Qiao, Ying Chen, Zhanzhan Cheng +4
Recently end-to-end scene text spotting has become a popular research topic due to its advantages of global optimization and high maintainability in real applications. Most methods…
TRIE: End-to-End Text Reading and Information Extraction for Document Understanding
Peng Zhang, Yunlu Xu, Zhanzhan Cheng +5
Since real-world ubiquitous documents (e.g., invoices, tickets, resumes and leaflets) contain rich information, automatic document image understanding has become a hot topic. Most…
SPIN: Structure-Preserving Inner Offset Network for Scene Text Recognition
Chengwei Zhang, Yunlu Xu, Zhanzhan Cheng +4
Arbitrary text appearance poses a great challenge in scene text recognition tasks. Existing works mostly handle with the problem in consideration of the shape distortion, including…
Refined Gate: A Simple and Effective Gating Mechanism for Recurrent Units
Zhanzhan Cheng, Yunlu Xu, Mingjian Cheng +4
Recurrent neural network (RNN) has been widely studied in sequence learning tasks, while the mainstream models (e.g., LSTM and GRU) rely on the gating mechanism (in control of how…
Text Perceptron: Towards End-to-End Arbitrary-Shaped Text Spotting
Liang Qiao, Sanli Tang, Zhanzhan Cheng +4
Many approaches have recently been proposed to detect irregular scene text and achieved promising results. However, their localization results may not well satisfy the following te…
Adversarial Seeded Sequence Growing for Weakly-Supervised Temporal Action Localization
Chengwei Zhang, Yunlu Xu, Zhanzhan Cheng +4
Temporal action localization is an important yet challenging research topic due to its various applications. Since the frame-level or segment-level annotations of untrimmed videos…
Segregated Temporal Assembly Recurrent Networks for Weakly Supervised Multiple Action Detection
Yunlu Xu, Chengwei Zhang, Zhanzhan Cheng +4
This paper proposes a segregated temporal assembly recurrent (STAR) network for weakly-supervised multiple action detection. The model learns from untrimmed videos with only superv…
Focusing Attention: Towards Accurate Text Recognition in Natural Images
Zhanzhan Cheng, Fan Bai, Yunlu Xu +3
Scene text recognition has been a hot research topic in computer vision due to its various applications. The state of the art is the attention-based encoder-decoder framework that…