Search Results for author:
Found 9 papers, 4 papers with code
DGST : Discriminator Guided Scene Text detector
Scene text detection task has attracted considerable attention in computer vision because of its wide application.
Adversarial Soft-detection-based Aggregation Network for Image Retrieval
Our weakly supervised ASDA method achieves state-of-the-art performance on most datasets.
Selective Feature Connection Mechanism: Concatenating Multi-layer CNN Features with a Feature Selector
Different layers of deep convolutional neural networks(CNNs) can encode different-level information.
Excavate Condition-invariant Space by Intrinsic Encoder
Our method excavates the space of intrinsic structure and semantic information by proposed self-supervised encoder loss.
Unsupervised Semantic-based Aggregation of Deep Convolutional Features
In this paper, we propose a simple but effective semantic-based aggregation (SBA) method.
Iterative Manifold Embedding Layer Learned by Incomplete Data for Large-scale Image Retrieval
Without post-processing, Our IME layer achieves a boost in performance of state-of-the-art image retrieval methods with post-processing on most datasets, and needs less computational cost.
Ranked #1 on
Image Retrieval
on Paris6k
Unsupervised Part-based Weighting Aggregation of Deep Convolutional Features for Image Retrieval
In this paper, we propose a simple but effective semantic part-based weighting aggregation (PWA) for image retrieval.
Scene Text Recognition Using Part-Based Tree-Structured Character Detection
Scene text recognition has inspired great interests from the computer vision community in recent years.
Cross-View Action Recognition via a Continuous Virtual Path
In this paper, we propose a novel method for cross-view action recognition via a continuous virtual path which connects the source view and the target view.
