Temporal Information
Temporal information processing focuses on effectively integrating time-dependent data into various computational tasks, aiming to improve accuracy and understanding of dynamic systems. Current research emphasizes the development of models that efficiently capture temporal dependencies, with a focus on transformer architectures, recurrent neural networks (like LSTMs), and graph-based methods for handling complex spatiotemporal relationships in diverse data types, including videos, sensor networks, and time series. This research is significant for advancing fields like video summarization, action recognition, traffic prediction, and medical image analysis, where accurate modeling of temporal dynamics is crucial for improved performance and interpretability.
Papers
Temporal Convolution-based Hybrid Model Approach with Representation Learning for Real-Time Acoustic Anomaly Detection
Sahan Dissanayaka, Manjusri Wickramasinghe, Pasindu Marasinghe
GeoLLaVA: Efficient Fine-Tuned Vision-Language Models for Temporal Change Detection in Remote Sensing
Hosam Elgendy, Ahmed Sharshar, Ahmed Aboeitta, Yasser Ashraf, Mohsen Guizani