Sight and hearing are two senses that play a vital role in human communication and scene
understanding. To mimic human perception ability, audio-visual learning, aimed at …

Multimodal fusion focuses on integrating information from multiple modalities with the goal of
more accurate prediction, which has achieved remarkable progress in a wide range of …

Dynamic neural network is an emerging research topic in deep learning. Compared to static
models which have fixed computational graphs and parameters at the inference stage …

Integration of heterogeneous and high-dimensional data (eg, multiomics) is becoming
increasingly important. Existing multimodal classification algorithms mainly focus on …

Despite the remarkable success of deep multi-modal learning in practice, it has not been
well-explained in theory. Recently, it has been observed that the best uni-modal network …

We abstract the features (ie learned representations) of multi-modal data into 1) uni-modal
features, which can be learned from uni-modal training, and 2) paired features, which can …

Deep multimodal learning has achieved great progress in recent years. However, current
fusion approaches are static in nature, ie, they process and fuse multimodal inputs with …

Human action recognition has been applied in many fields, such as video surveillance and
human computer interaction, where it helps to improve performance. Numerous reviews of …

In recent years, deep learning-based approaches for visual-inertial odometry (VIO) have
shown remarkable performance outperforming traditional geometric methods. Yet, all …

Temporal Sentence Grounding aims to retrieve a video moment given a natural language
query. Most existing literature merely focuses on visual information in videos without …