SASSM: Semantic Awareness and Self-Support Matching for Semi-Supervised Video Object Segmentation.

SASSM：面向半监督视频目标分割的语义感知与自支持匹配方法

2023

Relevance and Irrelevance Considered Subspace Mapping Neural Networks for Remote Sensing Text-Image Retrieval.

考虑相关性与无关性的子空间映射神经网络用于遥感文本-图像检索。

2023

EmAGAN: Embedded Blocks Search and Mask Attention GAN for Makeup Transfer.

EmAGAN：嵌入块搜索与掩码注意力生成对抗网络用于妆容迁移。

2023

Efficient Hand Gesture Recognition using Multi-Task Multi-Modal Learning and Self-Distillation.

高效手势识别使用多任务多模态学习和自蒸馏方法。

2023

Enhancing Visually-Rich Document Understanding via Layout Structure Modeling.

通过布局结构建模增强视觉丰富文档理解。

2023

Cross-modal Image-Recipe Retrieval via Multimodal Fusion.

通过多模态融合实现跨模态图像-食谱检索。

2023

DiffuseGAE: Controllable and High-fidelity Image Manipulation from Disentangled Representation.

DiffuseGAE：从解耦表示中实现可控和高保真图像操作。

2023

PhasePerturbation: Speech Data Augmentation via Phase Perturbation for Automatic Speech Recognition.

PhasePerturbation：通过相位扰动进行语音数据增强以用于自动语音识别。

2023

Basketball Flow: Learning to Synthesize Realistic and Diverse Basketball GamePlays based on Strategy Sketches.

篮球流：基于策略草图合成逼真且多样化的篮球比赛场景。

2023

Moving Inside the Box: Interacting with Interpretation of Historical Artefacts Through Tangible Augmented Reality.

盒中漫游：通过实物增强现实与历史文物的诠释互动。

2023