Referring video object segmentation (R-VOS) is a fundamental vision-language task which aims to segment the target referred by language expression in all video frames. Existing query-based R-VOS methods have conducted in-depth exploration of the interaction and alignment between visual and linguistic features but fail to transfer the information of the two modalities to the query vector with balanced intensities. Furthermore, most of the traditional approaches suffer from severe information loss in the process of multi-scale feature fusion, resulting in inaccurate segmentation. In this paper, we propose DCT, an end-to-end decoupled cross-modal transformer for referring video object segmentation, to better utilize multi-modal and multi-scale information. Specifically, we first design a Language-Guided Visual Enhancement Module (LGVE) to transmit discriminative linguistic information to visual features of all levels, performing an initial filtering of irrelevant background regions. Then, we propose a decoupled transformer decoder, using a set of object queries to gather entity-related information from both visual and linguistic features independently, mitigating the attention bias caused by feature size differences. Finally, the Cross-layer Feature Pyramid Network (CFPN) is introduced to preserve more visual details by establishing direct cross-layer communication. Extensive experiments have been carried out on A2D-Sentences, JHMDB-Sentences and Ref-Youtube-VOS. The results show that DCT achieves competitive segmentation accuracy compared with the state-of-the-art methods.

Person re-identification is a technology used to identify individuals across different cameras. Existing methods involve extracting features from an input image and using a single feature for matching. However, these features often provide a biased description of the person. To address this limitation, this paper introduces a new method called the Dual Descriptor Feature Enhancement (DDFE) network, which aims to emulate the multi-perspective observation abilities of humans. The DDFE network uses two independent sub-networks to extract descriptors from the same person image. These descriptors are subsequently combined to create a comprehensive multi-view representation, resulting in a significant improvement in recognition performance. To further enhance the discriminative capability of the DDFE network, a carefully designed training strategy is employed. Firstly, the CurricularFace loss is introduced to enhance the recognition accuracy of each sub-network. Secondly, the DropPath operation is incorporated to introduce randomness during sub-network training, promoting difference between the descriptors. Additionally, an Integration Training Module (ITM) is devised to enhance the discriminability of the integrated features. Extensive experiments are conducted on the Market1501 and MSMT17 datasets. On the Market1501 dataset, the DDFE network achieves an mAP of 91.6% and a Rank1 of 96.1%; on the MSMT17 dataset, the network achieves an mAP of 69.9% and a Rank1 of 87.5%. These outcomes outperform most SOTA methods, highlighting the significant advancement and effectiveness of the DDFE network.

Visible-infrared person re-identification aims to solve the matching problem between cross-camera and cross-modal person images. Existing methods strive to perform better cross-modal alignment, but often neglect the critical importance of feature enhancement for achieving better performance. Therefore, we proposed an effective method that combines both modal alignment and feature enhancement. Specifically, we introduced Visible-Infrared Modal Data Augmentation (VIMDA) for visible images to improve modal alignment. Margin MMD-ID Loss was also used to further enhance modal alignment and optimize model convergence. Then, we proposed Multi-Grain Feature Extraction (MGFE) Structure for feature enhancement to further improve recognition performance. Extensive experiments have been carried out on SYSY-MM01 and RegDB. The result indicates that our method outperforms the current state-of-the-art method for visible-infrared person re-identification. Ablation experiments verified the effectiveness of the proposed method.