1 Hit in 1.1 sec

AdaMML: Adaptive Multi-Modal Learning for Efficient Video Recognition [article]

Rameswar Panda, Chun-Fu Chen, Quanfu Fan, Ximeng Sun, Kate Saenko, Aude Oliva, Rogerio Feris
2021 arXiv   pre-print
In this paper, we propose an adaptive multi-modal learning framework, called AdaMML, that selects on-the-fly the optimal modalities for each segment conditioned on the input for efficient video recognition  ...  Multi-modal learning, which focuses on utilizing various modalities to improve the performance of a model, is widely used in video recognition.  ...  for efficient multi-modal learning.  ... 
arXiv:2105.05165v2 fatcat:6dfmdzy3gbbozomvz3w5sqeaia