Description
TDN, or Temporaral Difference Network, is an action recognition model that aims to capture multi-scale temporal information. To fully capture temporal information over the entire video, the TDN is established with a two-level difference modeling paradigm. Specifically, for local motion modeling, temporal difference over consecutive frames is used to supply 2D CNNs with finer motion pattern, while for global motion modeling, temporal difference across segments is incorporated to capture long-range structure for motion feature excitation.
Papers Using This Method
TopoDiffusionNet: A Topology-aware Diffusion Model2024-10-22Generation of Uncorrelated Residual Variables for Chemical Process Fault Diagnosis via Transfer Learning-based Input-Output Decoupled Network2024-04-29Terrain Diffusion Network: Climatic-Aware Terrain Generation with Geological Sketch Guidance2023-08-31Bi-Calibration Networks for Weakly-Supervised Video Representation Learning2022-06-21Making Person Search Enjoy the Merits of Person Re-identification2021-08-24Weakly-Supervised Temporal Action Localization Through Local-Global Background Modeling2021-06-20Temporal Difference Networks for Action Recognition2021-01-01TDN: Temporal Difference Networks for Efficient Action Recognition2020-12-18