{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/relaxed-spatio-temporal-deep-feature","title":"Relaxed Spatio-Temporal Deep Feature Aggregation for Real-Fake Expression Prediction","arxiv_id":"1708.07335","date":"2017-08-24","proceeding":null,"authors":["Savas Ozkan","Gozde Bozdagi Akar"],"abstract":"Frame-level visual features are generally aggregated in time with the\ntechniques such as LSTM, Fisher Vectors, NetVLAD etc. to produce a robust\nvideo-level representation. We here introduce a learnable aggregation technique\nwhose primary objective is to retain short-time temporal structure between\nframe-level features and their spatial interdependencies in the representation.\nAlso, it can be easily adapted to the cases where there have very scarce\ntraining samples. We evaluate the method on a real-fake expression prediction\ndataset to demonstrate its superiority. Our method obtains 65% score on the\ntest dataset in the official MAP evaluation and there is only one misclassified\ndecision with the best reported result in the Chalearn Challenge (i.e. 66:7%) .\nLastly, we believe that this method can be extended to different problems such\nas action/event recognition in future.","url_abs":"http://arxiv.org/abs/1708.07335v1","url_pdf":"http://arxiv.org/pdf/1708.07335v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"relaxed-spatio-temporal-deep-feature","repo_url":"https://github.com/savasozkan/real-fake-emotions","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"relaxed-spatio-temporal-deep-feature","repo_url":"https://github.com/anshu123priya/Real-v-s-Fake-Emotion-Challenge","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"relaxed-spatio-temporal-deep-feature","repo_url":"https://github.com/anshu123priya/Real-vs-Fake-Emotion-Challenge","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[],"methods":[{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}