代表性成果

In this review, we summarize the latest research findings and analyze the developmental trends of driver fatigue detection. We present the work on integration of RGB-D camera and deep learning, where Generative Adversarial Networks and multi-channel schemes are utilized to enhance the performance.

We present a comprehensive survey on Single Sample Per Person (SSPP) Face Recognition.

In this paper, we show a representation grouping effect during this process: the InfoNCE objective indirectly groups semantically similar representations together via randomly emerged within-modal anchors. We introduce Prototypical Contrastive Language Image Pretraining (ProtoCLIP) to enhance such grouping by boosting its efficiency and increasing its robustness against modality gap.

This technical report presents a Flood Domain Adaptation Network (FloodDAN), the first baseline of unsupervised flood forecasting problem.

In this paper, we concentrate on analyzing the loss functions during the training process of crack segmentation tasks and propose an Asymmetric Exponential Loss Function (AELF) that addresses two key challenges in semantic segmentation: sample biases and dataset biases.

This paper proposed the First deep-learning based music-driven conducting motion generation method, and presented a large-scale music motion dataset ConductorMotion100 with unprecedented 100 hours length.

In this paper, we construct a large-scale Multi-modal E-commerce Products classification dataset MEP-3M, which consists of over 3 million products and 599 fine-grained product categories. This paper won Best Dataset Paper award.

In this demo, we present the VirtualConductor, a system that can generate conducting video from a given piece of music and a single user’s image. This demo won the ICME 2021 Best Demo award.

In this paper, we focus on enabling the deep learning model to learn both short-term and long-term spatial-temporal dependencies for Significant Wave Height (SWH) prediction. A Wavelet Graph Neural Network (WGNN) approach is proposed. This paper won the BDAI 2021 Best Presentation award.

A convolutional neural network (CNN) is one of the most significant networks in the deep learning field. Since CNN made impressive …

Due to the semantic gap between the insufficient facial features and facial identifying information, the single sample per person …