TAMFormer: Multi-Modal Transformer with Learned Attention Mask for Early Intent Prediction

1 code implementation • 26 Oct 2022 • Nada Osman, Guglielmo Camporese, Lamberto Ballan

Human intention prediction is a growing area of research where an activity in a video has to be anticipated by a vision-based system.

SlowFast Rolling-Unrolling LSTMs for Action Anticipation in Egocentric Videos

no code implementations • 2 Sep 2021 • Nada Osman, Guglielmo Camporese, Pasquale Coscia, Lamberto Ballan

Action anticipation in egocentric videos is a difficult task due to the inherently multi-modal nature of human actions.

Action Anticipation Optical Flow Estimation +1