{"url":"/method/tdn","slug":"tdn","name":"TDN","full_name":"Temporaral Difference Network","full_name_withheld":false,"description_markdown":"**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.","description_state":"present","introduced_year":null,"introduced_by":{"title":"TDN: Temporal Difference Networks for Efficient Action Recognition","paper":"/paper/tdn-temporal-difference-networks-for","first_author":"LiMin Wang","n_authors":4,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/tdn-temporal-difference-networks-for"},"source":{"url":"https://arxiv.org/abs/2012.10071v2","title":"TDN: Temporal Difference Networks for Efficient Action Recognition","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Action Recognition Models","url":"/methods/category/action-recognition-models","pwc_aliases":[]}],"n_papers_tagged":8,"archive_num_papers":8,"papers_newest_first":[{"paper":"/paper/topodiffusionnet-a-topology-aware-diffusion","title":"TopoDiffusionNet: A Topology-aware Diffusion Model","date":"2024-10-22","arxiv_id":"2410.16646","n_code_links":1,"syntology":{"ran":3,"of":7,"unverified":4,"pointer_only":0}},{"paper":null,"title":"Generation of Uncorrelated Residual Variables for Chemical Process Fault Diagnosis via Transfer Learning-based Input-Output Decoupled Network","date":"2024-04-29","arxiv_id":"2404.18528","n_code_links":0,"syntology":null},{"paper":null,"title":"Terrain Diffusion Network: Climatic-Aware Terrain Generation with Geological Sketch Guidance","date":"2023-08-31","arxiv_id":"2308.16725","n_code_links":0,"syntology":null},{"paper":"/paper/bi-calibration-networks-for-weakly-supervised","title":"Bi-Calibration Networks for Weakly-Supervised Video Representation Learning","date":"2022-06-21","arxiv_id":"2206.10491","n_code_links":1,"syntology":null},{"paper":null,"title":"Making Person Search Enjoy the Merits of Person Re-identification","date":"2021-08-24","arxiv_id":"2108.10536","n_code_links":0,"syntology":null},{"paper":null,"title":"Weakly-Supervised Temporal Action Localization Through Local-Global Background Modeling","date":"2021-06-20","arxiv_id":"2106.11811","n_code_links":0,"syntology":null},{"paper":null,"title":"Temporal Difference Networks for Action Recognition","date":"2021-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/tdn-temporal-difference-networks-for","title":"TDN: Temporal Difference Networks for Efficient Action Recognition","date":"2020-12-18","arxiv_id":"2012.10071","n_code_links":1,"syntology":{"ran":2,"of":4,"unverified":2,"pointer_only":0}}],"papers_shown":8,"tasks":[{"task":"/task/action-recognition-in-videos","name":"Action Recognition","papers":2},{"task":"/task/action-recognition-in-videos-2","name":"Action Recognition In Videos","papers":2},{"task":"/task/denoising","name":"Denoising","papers":2},{"task":"/task/transfer-learning","name":"Transfer Learning","papers":2},{"task":"/task/action-classification","name":"Action Classification","papers":1},{"task":"/task/action-localization","name":"Action Localization","papers":1},{"task":"/task/chemical-process","name":"Chemical Process","papers":1},{"task":"/task/diagnostic","name":"Diagnostic","papers":1},{"task":"/task/fault-detection","name":"Fault Detection","papers":1},{"task":"/task/fault-diagnosis","name":"Fault Diagnosis","papers":1},{"task":"/task/fault-localization","name":"Fault localization","papers":1},{"task":"/task/human-detection","name":"Human Detection","papers":1},{"task":"/task/person-re-identification","name":"Person Re-Identification","papers":1},{"task":"/task/person-search","name":"Person Search","papers":1},{"task":"/task/representation-learning","name":"Representation Learning","papers":1},{"task":"/task/retrieval","name":"Retrieval","papers":1},{"task":"/task/action-recognition","name":"Temporal Action Localization","papers":1},{"task":"/task/topological-data-analysis","name":"Topological Data Analysis","papers":1},{"task":"/task/weakly-supervised-learning","name":"Weakly-supervised Learning","papers":1},{"task":"/task/weakly-supervised-temporal-action","name":"Weakly-supervised Temporal Action Localization","papers":1}],"tasks_shown":20,"n_tasks":21,"usage_by_year":[{"year":"2020","papers":1},{"year":"2021","papers":3},{"year":"2022","papers":1},{"year":"2023","papers":1},{"year":"2024","papers":2}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/tdn"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}