Emotion Recognition Comparison Hub

Reference Surfaces

Top Papers

• XEmoGPT: An Explainable Multimodal Emotion Recognition Framework with Cue-Level Perception and Reasoning(8.0)

  XEmoGPT revolutionizes emotion recognition in multimedia by perceiving and reasoning fine-grained emotional cues with advanced datasets and benchmarks.

• Emotion Transcription in Conversation: A Benchmark for Capturing Subtle and Complex Emotional States through Natural Language(7.0)

  Generate natural language descriptions of emotional states in conversations using a new Japanese dataset, enabling more nuanced human-machine interactions.

• Solution to the 10th ABAW Expression Recognition Challenge: A Robust Multimodal Framework with Safe Cross-Attention and Modality Dropout(7.0)

  A multimodal emotion recognition framework leveraging safe cross-attention and modality dropout to handle missing data and improve accuracy in real-world environments.

• Stage-Adaptive Reliability Modeling for Continuous Valence-Arousal Estimation(7.0)

  SAGE enhances continuous valence-arousal estimation by dynamically calibrating modality reliability during multimodal integration.

• Multimodal Emotion Recognition via Bi-directional Cross-Attention and Temporal Modeling(6.0)

  A multimodal framework for robust emotion recognition in video data using cross-attention and temporal modeling.

• EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models(4.0)

  Enhance MLLMs with Reflective Reinforcement Learning for superior emotional intelligence and interpretability.