24 citations · 179 across the 31 of their papers we have counts for
31 papers
DANCE: Dual-View Distribution Alignment for Dataset Condensation
Hansong Zhang, Shikun Li, Fanzhao Lin +3
Dataset condensation addresses the problem of data burden by learning a small synthetic training set that preserves essential knowledge from the larger real training set. To date,…
Towards Robust Real-Time Scene Text Detection: From Semantic to Instance Representation Learning
Xugong Qin, Pengyuan Lyu, Chengquan Zhang +5
Due to the flexible representation of arbitrary-shaped scene text and simple pipeline, bottom-up segmentation-based methods begin to be mainstream in real-time scene text detection…
Masked and Permuted Implicit Context Learning for Scene Text Recognition
Xiaomeng Yang, Zhi Qiao, Jin Wei +2
Scene Text Recognition (STR) is difficult because of the variations in text styles, shapes, and backgrounds. Though the integration of linguistic information enhances models' perfo…
UATVR: Uncertainty-Adaptive Text-Video Retrieval
Bo Fang, Wenhao Wu, Chang Liu +6
With the explosive growth of web videos and emerging large-scale vision-language pre-training models, e.g., CLIP, retrieving videos of interest with text instructions has attracted…
Beyond Instance Discrimination: Relation-aware Contrastive Self-supervised Learning
Yifei Zhang, Chang Liu, Yu Zhou +3
Contrastive self-supervised learning (CSL) based on instance discrimination typically attracts positive samples while repelling negatives to learn representations with pre-defined…
Handling Label Uncertainty for Camera Incremental Person Re-Identification
Zexian Yang, Dayan Wu, Wanqian Zhang +2
Incremental learning for person re-identification (ReID) aims to develop models that can be trained with a continuous data stream, which is a more practical setting for real-world…
UNITS: Unsupervised Intermediate Training Stage for Scene Text Detection
Youhui Guo, Yu Zhou, Xugong Qin +2
Recent scene text detection methods are almost based on deep learning and data-driven. Synthetic data is commonly adopted for pre-training due to expensive annotation cost. However…
Towards Escaping from Language Bias and OCR Error: Semantics-Centered Text Visual Question Answering
Chengyang Fang, Gangyan Zeng, Yu Zhou +4
Texts in scene images convey critical information for scene understanding and reasoning. The abilities of reading and reasoning matter for the model in the text-based visual questi…
Imagine by Reasoning: A Reasoning-Based Implicit Semantic Data Augmentation for Long-Tailed Classification
Xiaohua Chen, Yucan Zhou, Dayan Wu +4
Real-world data often follows a long-tailed distribution, which makes the performance of existing classification algorithms degrade heavily. A key issue is that samples in tail cat…
Dense Semantic Contrast for Self-Supervised Visual Representation Learning
Xiaoni Li, Yu Zhou, Yifei Zhang +5
Self-supervised representation learning for visual pre-training has achieved remarkable success with sample (instance or pixel) discrimination and semantics discovery of instance,…
PIMNet: A Parallel, Iterative and Mimicking Network for Scene Text Recognition
Zhi Qiao, Yu Zhou, Jin Wei +5
Nowadays, scene text recognition has attracted more and more attention due to its various applications. Most state-of-the-art methods adopt an encoder-decoder framework with attent…
Which and Where to Focus: A Simple yet Accurate Framework for Arbitrary-Shaped Nearby Text Detection in Scene Images
Youhui Guo, Yu Zhou, Xugong Qin +1
Scene text detection has drawn the close attention of researchers. Though many methods have been proposed for horizontal and oriented texts, previous methods may not perform well w…
Mask is All You Need: Rethinking Mask R-CNN for Dense and Arbitrary-Shaped Scene Text Detection
Xugong Qin, Yu Zhou, Youhui Guo +5
Due to the large success in object detection and instance segmentation, Mask R-CNN attracts great attention and is widely adopted as a strong baseline for arbitrary-shaped scene te…
Video 3D Sampling for Self-supervised Representation Learning
Wei Li, Dezhao Luo, Bo Fang +2
Most of the existing video self-supervised methods mainly leverage temporal signals of videos, ignoring that the semantics of moving objects and environmental information are all c…
Multi-View Correlation Distillation for Incremental Object Detection
Dongbao Yang, Yu Zhou, Weiping Wang
In real applications, new object classes often emerge after the detection model has been trained on a prepared dataset with fixed classes. Due to the storage burden and the privacy…
MMF: Multi-Task Multi-Structure Fusion for Hierarchical Image Classification
Xiaoni Li, Yucan Zhou, Yu Zhou +1
Hierarchical classification is significant for complex tasks by providing multi-granular predictions and encouraging better mistakes. As the label structure decides its performance…
Exploring Instance Relations for Unsupervised Feature Embedding
Yifei Zhang, Yu Zhou, Weiping Wang
Despite the great progress achieved in unsupervised feature embedding, existing contrastive learning methods typically pursue view-invariant representations through attracting posi…
Rescuing Deep Hashing from Dead Bits Problem
Shu Zhao, Dayan Wu, Yucan Zhou +2
Deep hashing methods have shown great retrieval accuracy and efficiency in large-scale image retrieval. How to optimize discrete hash bits is always the focus in deep hashing metho…
Deep Learning for Instance Retrieval: A Survey
Wei Chen, Yu Liu, Weiping Wang +5
In recent years a vast amount of visual content has been generated and shared from many fields, such as social media platforms, medical imaging, and robotics. This abundance of con…
Gaussian Constrained Attention Network for Scene Text Recognition
Zhi Qiao, Xugong Qin, Yu Zhou +2
Scene text recognition has been a hot topic in computer vision. Recent methods adopt the attention mechanism for sequence prediction which achieve convincing results. However, we a…
New Ideas and Trends in Deep Multimodal Content Understanding: A Review
Wei Chen, Weiping Wang, Li Liu +1
The focus of this survey is on the analysis of two modalities of multimodal deep learning: image and text. Unlike classic reviews of deep learning where monomodal image classifiers…
On the Exploration of Incremental Learning for Fine-grained Image Retrieval
Wei Chen, Yu Liu, Weiping Wang +3
In this paper, we consider the problem of fine-grained image retrieval in an incremental setting, when new categories are added over time. On the one hand, repeatedly training the…
Exploring Relations in Untrimmed Videos for Self-Supervised Learning
Dezhao Luo, Bo Fang, Yu Zhou +3
Existing video self-supervised learning methods mainly rely on trimmed videos for model training. However, trimmed datasets are manually annotated from untrimmed videos. In this se…
Two-Level Residual Distillation based Triple Network for Incremental Object Detection
Dongbao Yang, Yu Zhou, Dayan Wu +3
Modern object detection methods based on convolutional neural network suffer from severe catastrophic forgetting in learning new classes without original data. Due to time consumpt…