Recent studies have drawn attention to the untapped potential of the" star
operation"(element-wise multiplication) in network design. While intuitive explanations …

Action recognition is intended to classify a video into a certain category by aggregating and
summarizing its temporal and spatial information. Existing methods have achieved …

In this paper, we address the challenges posed by the substantial training time and memory
consumption associated with video transformers, focusing on the ViViT (Video Vision …

The Contrastive Language-Image Pre-training (CLIP) model achieves strong generalization
by using a large number of text-image pairs for contrastive learning. However, when it is …

High frame-rate~(HFR) videos of action recognition improve fine-grained expression while
reducing the spatio-temporal relation and motion information density. Thus, large amounts of …

State-space models (SSMs), exemplified by S4, have introduced a novel context modeling
method by integrating state-space techniques into deep learning. However, they struggle …

With the surge in network traffic, the homogenization of short video content is becoming
increasingly prominent, resulting in low-quality entertainment due to proliferation and …

The increasing success of deep neural networks has raised concerns about their inherent
black-box nature, posing challenges related to interpretability and trust. While there has …

The proliferation of videos captured by sensor-based cameras has driven the application of
human action recognition (HAR) task. As the fundamental video application in human …

Satellite-derived agricultural drought indices can provide a complementary perspective of
terrestrial vegetation trends. In addition, their integration for drought assessments under …