CV方向多模态融合有哪些好的paper？
2023-06-25 阅读 27
以下是一些多模态融合方面的优秀论文：
1. "Learning Cross-Modal Deep Representations for Robust Pedestrian Detection" by Shanshan Zhang, Rodrigo Benenson, and Bernt Schiele. This paper proposes a novel cross-modal deep learning approach for pedestrian detection that fuses visual and thermal data.
2. "Multimodal Deep Learning for Robust RGB-D Object Recognition" by Shuran Song, Samuel Schulman, and Jianxiong Xiao. This paper presents a deep learning approach that fuses RGB and depth data for object recognition, achieving state-of-the-art results on benchmark datasets.
3. "Multimodal Deep Learning for Gesture Recognition: A Review" by Hui Zhang, Jianfeng Xu, and Guangming Zhu. This paper provides a comprehensive review of multimodal deep learning approaches for gesture recognition, including fusion methods and network architectures.
4. "Multimodal Deep Learning for Audio-Visual Speech Recognition" by Triantafyllos Afouras, Joon Son Chung, and Andrew Zisserman. This paper proposes a deep learning approach that fuses audio and visual data for speech recognition, achieving state-of-the-art results on benchmark datasets.
5. "Multimodal Deep Learning for Activity Recognition in Smart Homes" by Mohammad M. Masud, Iftekhar Naim, and Huan Liu. This paper presents a deep learning approach that fuses data from multiple sensors in smart homes for activity recognition, achieving high accuracy on benchmark datasets.
这些论文都是在多模态融合方面具有代表性和影响力的论文，可以作为参考。
更新于 2023年06月27日
