YWYinan Wu

Yinan Wu

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Yinan Wu has a total of 6 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • TrTr-CMR: Cross-Modal Reasoning Dual Transformer for Remote Sensing Image Captioning

    by Yinan Wu, Lingling Li, Licheng Jiao, Fang Liu, Xu Liu, Shuyuan Yang

    Remote sensing image captioning is an interesting but challenging cross-modal reasoning task for computer vision and natural language processing. Most of the recent popular approaches for remote sensing image captioning utilize encoder-decoder architectures which focus on visual features captured by CNN-based encoder and semantic information by RNN-based or LSTM-based decoder, but encounter difficulties with multi-scale, multi-categories, and direction ambiguity challenges. To make the most of semantic understanding ability of Transformers, in this paper, we propose a new attention-based visual-linguistic reasoning framework with dual Transformer for remote sensing image captioning. Specifically, Swin Transformer encoder with shifted window partitioning scheme is introduced for multi-scale visual feature extraction to discover the intrinsic relationship in the objects, and then a Transformer language model with self-attention and cross-attention is designed as the decoder to generate a well-formed sentence for the image. Extensive experiments are conducted on the public remote sensing image captioning benchmark datasets, including UCM-Captions, Sydney-Captions, and RSICD. The impressive performance verifies the effectiveness and superiority of the proposed method. Additionally, the source code and models of this work are publicly available at https://github.com/LianYi233/TrTr-CMR.


  • Domain Adaptation-Aware Transformer for Hyperspectral Object Tracking

    by Yinan Wu, Licheng Jiao, Xu Liu, Fang Liu, Shuyuan Yang, Lingling Li

    Visual object tracking in natural scenes is a popular but challenging task, owing to the difficulties of feature representation from various changes of the targets, such as size change, deformation, illumination change, rotations, motion blur, background clutter, etc. High-speed hyperspectral imaging systems capture hyperspectral videos (HSVs) in wide spectral ranges and provide abundant spectral and spatial information to tell targets apart from backgrounds, alleviating the model drift in appearance-based tracking methods. However, different hyperspectral imagers, such as near-infrared (NIR), red-to-near-infrared (RedNIR), and visible (VIS), obtain heterogeneous types of data that could not be handled by common object trackers. In this paper, a domain adaptive Transformer framework is proposed for hyperspectral object tracking. Considering the HSVs are from different types of sensors, their heterogeneous features are learned in an adversarial way by domain label reverse learning with a gradient reversed layer. To fully utilize the spectral information in HSV frames, a band-wise spatial attention module (BSAM) is designed to emphasize the salient area near the target of interest. We adopt a Siamese-like Transformer tracker as the main structure for tracking. Our tracker outperforms top-ranking methods on a hyperspectral object tracking benchmark dataset containing three types, 87 hyperspectral videos in total. The comparison experiments validate the effectiveness of the proposed method. The source code and trained models of this work will be publicly available soon at https://github.com/LianYi233/Trans-DAT.


  • CSLT: Contourlet-Based Siamese Learning Tracker for Dim and Small Targets in Satellite Videos

    by Yinan Wu, Licheng Jiao, Fang Liu, Zhaoliang Pi, Xu Liu, Lingling Li, Shuyuan Yang

    Most popular visual trackers for natural scenarios always adopt handcraft features or deep features to track the target in a video. However, they face with difficulties in discriminative feature representation and usually suffer from severe model drift for satellite videos, especially when encountering challenges of dim and small targets, low contrast or similar target interference. To overcome these difficulties, we propose a Contourlet-based Siamese Learning Tracker (CSLT), which mainly aims at tracking dim and small objects in satellite videos. In contrast to conventional methods, the contourlet transform enriches directional multi-resolution information which is crucial to discriminative feature representation for dim and small targets in satellite video frames that lack distinguishable appearance features. We jointly use multi-resolution features with deep features by spatial-attention fusion strategy and then track the targets by a Siamese structure network. To further improve the accuracy and robustness, a model drift alarm and calibration module, including translation drifting penalty and rotation drifting penalty, is employed during tracking. We conduct extensive comparisons with 16 popular state-of-the-art trackers on three satellite video datasets. The experimental results validate the effectiveness of the proposed tracker.