Challenges in Representation Learning: A report on three machine\n learning contests

2013/07/01 by Ian Goodfellow, Dumitru Erhan, Goodfellow, Ian J. +55 · 28 citations
Computer Science · #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Multimodal Machine Learning Applications #Natural Language Processing Techniques #Topic Modeling

paper · pdf · doi:10.48550/arxiv.1307.0414

openalex publication_date 2013/07/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

The ICML 2013 Workshop on Challenges in Representation Learning focused on\nthree challenges: the black box learning challenge, the facial expression\nrecognition challenge, and the multimodal learning challenge. We describe the\ndatasets created for these challenges and summarize the results of the\ncompetitions. We provide suggestions for organizers of future challenges and\nsome comments on what kind of knowledge can be gained from machine learning\ncompetitions.\n

Citations

• Representation Learning: A Review and New Perspectives

Cited by

• Rethinking Expert Training for Model Merging with Prompt Learning
• Controlling Embedding Spaces with Text-Conditioned Transformations
• Model Merging via Multi-Teacher Knowledge Distillation
• SuperCLIP: CLIP with Simple Classification Supervision
• A Perception CNN for Facial Expression Recognition
• VAD-Net: Multidimensional Facial Expression Recognition in Intelligent Education System
• From Coefficients to Directions: Rethinking Model Merging with Directional Alignment
• CHIPS: Efficient CLIP Adaptation via Curvature-aware Hybrid Influence-based Data Selection
• Facial Expression Recognition with YOLOv11 and YOLOv12: A Comparative Study
• Global Multiple Extraction Network for Low-Resolution Facial Expression Recognition
• Facial Expression Recognition System Using DNN Accelerator with Multi-threading on FPGA
• Facial-Expression-Aware Prompting for Empathetic LLM Tutoring
• WELD: A Large-Scale Longitudinal Dataset of Emotional Dynamics for Ubiquitous Affective Computing
• ExpressNet-MoE: A Hybrid Deep Neural Network for Emotion Recognition
• Error correction in multiclass image classification of facial emotion on unbalanced samples
• Edu-EmotionNet: Cross-Modality Attention Alignment with Temporal Feedback Loops
• Null-Space Filtering for Data-Free Continual Model Merging: Preserving Transparency, Promoting Fidelity
• A Scenario-Driven Cognitive Approach to Next-Generation AI Memory
• Robust Audio-Visual Target Speaker Extraction with Emotion-Aware Multiple Enrollment Fusion
• Towards Open World Detection: A Survey
• MVRS: The Multimodal Virtual Reality Stimuli-based Emotion Recognition Dataset
• Disentanglement for Discriminative Visual Recognition
• Holo-Artisan: A Personalized Multi-User Holographic Experience for Virtual Museums on the Edge Intelligence
• Evaluating Open-Source Vision Language Models for Facial Emotion Recognition against Traditional Deep Learning Models
• Feature-level and Model-level Audiovisual Fusion for Emotion Recognition in the Wild
• RegMean++: Enhancing Effectiveness and Generalization of Regression Mean for Model Merging
• Evading Data Provenance in Deep Neural Networks
• Principled Non-Linear Feature Selection

Related

• Deep representation learning: Fundamentals, Perspectives, Applications, and Open Challenges
• Multimodal Representation Learning and Fusion
• Empirical Evaluation and Theoretical Analysis for Representation Learning: A Survey
• Survey on Self-Supervised Multimodal Representation Learning and Foundation Models
• MultiBench: Multiscale Benchmarks for Multimodal Representation Learning