… Mutual Learning module, we propose a novel decoder framework with two parallel decoder
branches in opposite decoding directions (L2R and R2L) and use mutual … mutual learning, …

… of expressions. This paper proposes a harmonious mutual learning framework for emotion
recognition, … focus on mutual learning in the field of facial expression recognition. Some metric …

… To this end, we propose Joint Discriminative and Mutual Adaptation Networks (… on mutual
information and discriminative metric learning techniques. Specifically, we design a mutual …

… We introduce a novel tree-based mutual learning method to deeply integrate the string
decoder and the tree decoder in both the training and inference stages, which fully complement …

… To leverage knowledge acquisition in deep learning models, this paper adopts the strategy
of deep mutual learning to guide the interactive training of micro-expression sequences …

… expression representations that invariant to the identity-specific attributes is a long-lasting
problem for facial expression recognition … off-the-shelf and valuable expression-related muscle …

… an identity-invariant facial expression recognition framework. It aims to make a facial
expression recognition (FER) model independently understand facial expressions and identity (ID) …

… in the first column indicates whether multi-scale and bidirectional mutual learning is used, …
we found that mutual learning has a great impact on the model. Without mutual learning, multi-…

… By advancing crossmodal mutual learning strategies, our model is able to convert visual or
audio-based linguistic features into modalityagnostic representations. Such derived linguistic …

… learning ability, inspired by Deep Mutual Learning (DML) [9], we design a dynamic deep
mutual learning … as follows: (1) A lightweight face expression recognition network is designed, a …