229 citations · 669 across the 26 of their papers we have counts for
26 papers
PNT-Edge: Towards Robust Edge Detection with Noisy Labels by Learning Pixel-level Noise Transitions
Wenjie Xuan, Shanshan Zhao, Yu Yao +5
Relying on large-scale training data with pixel-level labels, previous edge detection methods have achieved high performance. However, it is hard to manually label edges accurately…
Multi-Granularity Hand Action Detection
Ting Zhe, Jing Zhang, Yongqian Li +3
Detecting hand actions in videos is crucial for understanding video content and has diverse real-world applications. Existing approaches often focus on whole-body actions or coarse…
Revisit Weakly-Supervised Audio-Visual Video Parsing from the Language Perspective
Yingying Fan, Yu Wu, Bo Du +1
We focus on the weakly-supervised audio-visual video parsing task (AVVP), which aims to identify and locate all the events in audio/visual modalities. Previous works only concentra…
Self-Evolution Learning for Discriminative Language Model Pretraining
Qihuang Zhong, Liang Ding, Juhua Liu +2
Masked language modeling, widely used in discriminative language model (e.g., BERT) pretraining, commonly adopts a random masking strategy. However, random masking does not conside…
Revisiting Token Dropping Strategy in Efficient BERT Pretraining
Qihuang Zhong, Liang Ding, Juhua Liu +4
Token dropping is a recently-proposed strategy to speed up the pretraining of masked language models, such as BERT, by skipping the computation of a subset of the input tokens at s…
Scalable Mask Annotation for Video Text Spotting
Haibin He, Jing Zhang, Mengyang Xu +3
Video text spotting refers to localizing, recognizing, and tracking textual elements such as captions, logos, license plates, signs, and other forms of text within consecutive vide…
Can ChatGPT Understand Too? A Comparative Study on ChatGPT and Fine-tuned BERT
Qihuang Zhong, Liang Ding, Juhua Liu +2
Recently, ChatGPT has attracted great attention, as it can generate fluent and high-quality responses to human inquiries. Several prior studies have shown that ChatGPT attains rema…
Diff-Font: Diffusion Model for Robust One-Shot Font Generation
Haibin He, Xinyuan Chen, Chaoyue Wang +4
Font generation is a difficult and time-consuming task, especially in those languages using ideograms that have complicated structures with a large number of characters, such as Ch…
DeepSolo: Let Transformer Decoder with Explicit Points Solo for Text Spotting
Maoyuan Ye, Jing Zhang, Shanshan Zhao +4
End-to-end text spotting aims to integrate scene text detection and recognition into a unified framework. Dealing with the relationship between the two sub-tasks plays a pivotal ro…
Unsupervised Multimodal Change Detection Based on Structural Relationship Graph Representation Learning
Hongruixuan Chen, Naoto Yokoya, Chen Wu +1
Unsupervised multimodal change detection is a practical and challenging topic that can play an important role in time-sensitive emergency applications. To address the challenge tha…
PANDA: Prompt Transfer Meets Knowledge Distillation for Efficient Model Adaptation
Qihuang Zhong, Liang Ding, Juhua Liu +2
Prompt Transfer (PoT) is a recently-proposed approach to improve prompt-tuning, by initializing the target prompt with the existing prompt trained on similar source tasks. However,…
DPText-DETR: Towards Better Scene Text Detection with Dynamic Points in Transformer
Maoyuan Ye, Jing Zhang, Shanshan Zhao +3
Recently, Transformer-based methods, which predict polygon points or Bezier curve control points for localizing texts, are popular in scene text detection. However, these methods b…
E2S2: Encoding-Enhanced Sequence-to-Sequence Pretraining for Language Understanding and Generation
Qihuang Zhong, Liang Ding, Juhua Liu +2
Sequence-to-sequence (seq2seq) learning is a popular fashion for large-scale pretraining language models. However, the prior seq2seq pretraining models generally focus on reconstru…
An Empirical Study of Remote Sensing Pretraining
Di Wang, Jing Zhang, Bo Du +2
Deep learning has largely reshaped remote sensing (RS) research for aerial image understanding and made a great success. Nevertheless, most of the existing deep models are initiali…
An End-to-end Supervised Domain Adaptation Framework for Cross-Domain Change Detection
Jia Liu, Wenjie Xuan, Yuhang Gan +2
Existing deep learning-based change detection methods try to elaborately design complicated neural networks with powerful feature representations, but ignore the universal domain s…
Visual Semantics Allow for Textual Reasoning Better in Scene Text Recognition
Yue He, Chen Chen, Jing Zhang +4
Existing Scene Text Recognition (STR) methods typically use a language model to optimize the joint probability of the 1D character sequence predicted by a visual recognition (VR) m…
MixSiam: A Mixture-based Approach to Self-supervised Representation Learning
Xiaoyang Guo, Tianhao Zhao, Yutian Lin +1
Recently contrastive learning has shown significant progress in learning visual representations from unlabeled data. The core idea is training the backbone to be invariant to diffe…
SGEN: Single-cell Sequencing Graph Self-supervised Embedding Network
Ziyi Liu, Minghui Liao, Fulin luo +1
Single-cell sequencing has a significant role to explore biological processes such as embryonic development, cancer evolution, and cell differentiation. These biological properties…
Unified Instance and Knowledge Alignment Pretraining for Aspect-based Sentiment Analysis
Juhua Liu, Qihuang Zhong, Liang Ding +3
Aspect-based Sentiment Analysis (ABSA) aims to determine the sentiment polarity towards an aspect. Because of the expensive and limited labelled data, the pretraining strategy has…
Unsupervised Domain Adaptation for Semantic Segmentation via Low-level Edge Information Transfer
Hongruixuan Chen, Chen Wu, Yonghao Xu +1
Unsupervised domain adaptation for semantic segmentation aims to make models trained on synthetic data (source domain) adapt to real images (target domain). Previous feature-level…
Towards Deep and Efficient: A Deep Siamese Self-Attention Fully Efficient Convolutional Network for Change Detection in VHR Images
Hongruixuan Chen, Chen Wu, Bo Du
Recently, FCNs have attracted widespread attention in the CD field. In pursuit of better CD performance, it has become a tendency to design deeper and more complicated FCNs, which…
DeepFake MNIST+: A DeepFake Facial Animation Dataset
Jiajun Huang, Xueyu Wang, Bo Du +2
The DeepFakes, which are the facial manipulation techniques, is the emerging threat to digital society. Various DeepFake detection methods and datasets are proposed for detecting s…
Unsupervised Person Re-identification with Stochastic Training Strategy
Tianyang Liu, Yutian Lin, Bo Du
Unsupervised person re-identification (re-ID) has attracted increasing research interests because of its scalability and possibility for real-world applications. State-of-the-art u…
I3CL:Intra- and Inter-Instance Collaborative Learning for Arbitrary-shaped Scene Text Detection
Bo Du, Jian Ye, Jing Zhang +2
Existing methods for arbitrary-shaped text detection in natural scenes face two critical issues, i.e., 1) fracture detections at the gaps in a text instance; and 2) inaccurate dete…