AI Paper Atlas

Research map / Benchmarks / DFEW

DFEW leaderboard

10 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on DFEW. Best WAR: 78.29 (TiCAL, AAAI 2026).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

DFEW · WAR

10 papers, each with its best reported number for its own method; higher is better.

#WAR ↑MethodPaperTopic
178.29TiCALTiCAL:Typicality-Based Consistency-Aware Learning for Multimodal Emotion Recognition
AAAI 2026 · Table 2
Cross-modal learning
277.45AVF-MAE++ (H)AVF-MAE++: Scaling Affective Video Facial Masked Autoencoders via Efficient Audio-Visual Self-Supervised Learning
CVPR 2025 · Table 2(b)
Video segmentation and tracking
374.02OUS
CLIP ViT-L/14
OUS: Bridging Scene Context and Facial Features to Overcome the Rigid Cognitive Problem
AAAI 2025 · Table 2
Human and embodied modeling
473.82IFDD-3DViT
MViT-S
Lifting Scheme-Based Implicit Disentanglement of Emotion-Related Facial Dynamics in the Wild
AAAI 2025 · Table: Comparisons with the st
Video segmentation and tracking
573.1VidEmoVidEmo: Affective-Tree Reasoning for Emotion-Centric Video Foundation Models
NeurIPS 2025 · Downstream tasks table
Video-language understanding
669.25M3DFEL
R3D18
Rethinking the Learning Paradigm for Dynamic Facial Expression Recognition
CVPR 2023 · Table 1
Video segmentation and tracking
769.24GCA+IAL
ResNet18
Intensity-Aware Loss for Dynamic Facial Expression Recognition in the Wild
AAAI 2023 · Table 4
Video segmentation and tracking
869.2ViT_LSTM + D2SP
ViT_LSTM
D2SP: Dynamic Dual-Stage Purification Framework for Dual Noise Mitigation in Vision-based Affective Recognition.
CVPR 2025 · Table 1
Noisy labels
967.3Ours (ERV + Explanation Reward)
HumanOmni 0.5B
Emotion-Coherent Reasoning for Multimodal LLMs via Emotional Rationale Verifier
AAAI 2026 · Table 1
Multimodal LLMs
1065.89EMO-LLaMAEMO-LLaMA: Enhancing Facial Emotion Understanding with Instruction Tuning
IJCV 2026 · Table 1
Multimodal LLMs

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.