Early Action Recognition with Action Prototypes

Distilling Knowledge for Short-to-Long Term Trajectory Prediction

Empowering Convolutional Neural Nets with MetaSin Activation

Prediction of Activities and Visual Concepts Under Complex and Changing Conditions

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

Where are my Neighbors? Exploiting Patches Relations in Self-Supervised Vision Transformer

Early Pedestrian Intent Prediction Via Features Estimation

Conditional Variational Capsule Network for Open Set Recognition

Improved Robustness to Disfluencies in Rnn-Transducer Based Speech Recognition

SlowFast Rolling-Unrolling LSTMs for Action Anticipation in Egocentric Videos

Knowledge Distillation for Action Anticipation via Label Smoothing