Now showing items 1-5 of 5

    • Is a “happy dog” more “happy” than “dog”? - Adjective and Noun Contributions for Adjective-Noun Pair prediction 

      Fernàndez, Dèlia; Campos Camúñez, Victor; Jou, Brendan; Giró Nieto, Xavier; Chang, Shih-Fu (2016)
      Conference lecture
      Open Access
    • More cat than cute?: interpretable prediction of adjective-noun pairs 

      Fernàndez, Dèlia; Woodward, Alejandro; Campos Camunez, Victor; Giró Nieto, Xavier; Jou, Brendan; Chang, Shih-Fu (2017)
      Conference report
      Restricted access - publisher's policy
      The increasing availability of affect-rich multimedia resources has bolstered interest in understanding sentiment and emotions in and from visual content. Adjective-noun pairs (ANP) are a popular midlevel semantic ...
    • Online detection of action start in untrimmed, streaming videos 

      Shou, Zheng; Pan, Junting; Chan, Jonathan; Miyazawa, Kazuyuki; Mansour, Hassan; Vetro, Anthony; Giró Nieto, Xavier; Chang, Shih-Fu (Springer, 2018)
      Conference lecture
      Open Access
      We aim to tackle a novel task in action detection - Online Detection of Action Start (ODAS) in untrimmed, streaming videos. The goal of ODAS is to detect the start of an action instance, with high categorization accuracy ...
    • Skip RNN: learning to skip state updates in recurrent neural networks 

      Campos, Víctor; Jou, Brendan; Giró Nieto, Xavier; Torres Viñals, Jordi; Chang, Shih-Fu (Barcelona Supercomputing Center, 2018-04-24)
      Conference report
      Open Access
      Recurrent Neural Networks (RNNs) continue to show outstanding performance in sequence modeling tasks. However, training RNNs on long sequences often face challenges like slow inference, vanishing gradients and difficulty ...
    • Skip RNN: learning to skip state updates in recurrent neural networks 

      Campos Camunez, Victor; Jou, Brendan; Giró Nieto, Xavier; Torres Viñals, Jordi; Chang, Shih-Fu (2018)
      Conference lecture
      Open Access
      Recurrent Neural Networks (RNNs) continue to show outstanding performance in sequence modeling tasks. However, training RNNs on long sequences often face challenges like slow inference, vanishing gradients and difficulty ...