This paper introduces the 7th Affective Behavior Analysis in-the-wild (ABAW) Competition, held alongside ECCV 2024. The competition focuses on two main challenges: Multi-Task Learning (MTL) and Compound Expression Recognition. The MTL challenge aims to estimate valence and arousal, recognize eight basic facial expressions, and detect 12 Action Units (AUs) simultaneously. The Compound Expression Recognition challenge targets identifying seven specific compound expressions. The datasets used are s-Aff-Wild2 for MTL and a subset of C-EXPR-DB for Compound Expression Recognition. Evaluation metrics include the Concordance Correlation Coefficient (CCC) for valence and arousal, macro F1 Score for expressions, and binary F1 Score for AUs. The paper details the datasets, protocols, and baseline systems, highlighting the importance of these challenges in advancing human-centered technologies.This paper introduces the 7th Affective Behavior Analysis in-the-wild (ABAW) Competition, held alongside ECCV 2024. The competition focuses on two main challenges: Multi-Task Learning (MTL) and Compound Expression Recognition. The MTL challenge aims to estimate valence and arousal, recognize eight basic facial expressions, and detect 12 Action Units (AUs) simultaneously. The Compound Expression Recognition challenge targets identifying seven specific compound expressions. The datasets used are s-Aff-Wild2 for MTL and a subset of C-EXPR-DB for Compound Expression Recognition. Evaluation metrics include the Concordance Correlation Coefficient (CCC) for valence and arousal, macro F1 Score for expressions, and binary F1 Score for AUs. The paper details the datasets, protocols, and baseline systems, highlighting the importance of these challenges in advancing human-centered technologies.