182 results found (page 6 of 13)
https://www.academia.edu/118432156/Tell_me_what_you_see_A_zero_shot_action_recognition_met…

… as an object concept description. Additionally, they proposed a combination of Wikipedia and dictionary data to compose action class descriptions using human supervision in this task. Hence, they could identify objects in videos and provide a representation based on their concep…

https://www.academia.edu/74401277/Masked_Language_Modeling_and_the_Distributional_Hypothes…

… we use the original 16GB and target languages, LSTM language models lever- BookWiki corpus (the Toronto Books Corpus, Zhu age the latent hierarchical structure of the input to et al. 2015, plus English Wikipedia) from Liu et al. obtain better performance than a random, Zipfian (…