TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Papers/Conditional Generative Adversarial Nets

Conditional Generative Adversarial Nets

Mehdi Mirza, Simon Osindero

2014-11-06DescriptiveHuman action generation
PaperPDFCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCode

Abstract

Generative Adversarial Nets [8] were recently introduced as a novel way to train generative models. In this work we introduce the conditional version of generative adversarial nets, which can be constructed by simply feeding the data, y, we wish to condition on to both the generator and discriminator. We show that this model can generate MNIST digits conditioned on class labels. We also illustrate how this model could be used to learn a multi-modal model, and provide preliminary examples of an application to image tagging in which we demonstrate how this approach can generate descriptive tags which are not part of training labels.

Results

TaskDatasetMetricValueModel
Activity RecognitionNTU RGB+DFID (CS)27.48c-GAN
Activity RecognitionNTU RGB+DFID (CV)31.875c-GAN
Activity RecognitionNTU RGB+D 120FID (CS)54.403c-GAN
Activity RecognitionNTU RGB+D 120FID (CV)58.531c-GAN
Activity RecognitionNTU RGB+D 2DMMDa (CS)0.334c-GAN
Activity RecognitionNTU RGB+D 2DMMDa (CV)0.365c-GAN
Activity RecognitionNTU RGB+D 2DMMDs (CS)0.354c-GAN
Activity RecognitionNTU RGB+D 2DMMDs (CV)0.373c-GAN
Activity RecognitionHuman3.6MMMDa0.161c-GAN
Activity RecognitionHuman3.6MMMDs0.187c-GAN
Human action generationNTU RGB+DFID (CS)27.48c-GAN
Human action generationNTU RGB+DFID (CV)31.875c-GAN
Human action generationNTU RGB+D 120FID (CS)54.403c-GAN
Human action generationNTU RGB+D 120FID (CV)58.531c-GAN
Human action generationNTU RGB+D 2DMMDa (CS)0.334c-GAN
Human action generationNTU RGB+D 2DMMDa (CV)0.365c-GAN
Human action generationNTU RGB+D 2DMMDs (CS)0.354c-GAN
Human action generationNTU RGB+D 2DMMDs (CV)0.373c-GAN
Human action generationHuman3.6MMMDa0.161c-GAN
Human action generationHuman3.6MMMDs0.187c-GAN

Related Papers

DiffRhythm+: Controllable and Flexible Full-Length Song Generation with Preference Optimization2025-07-17Assay2Mol: large language model-based drug design using BioAssay context2025-07-16Describe Anything Model for Visual Question Answering on Text-rich Images2025-07-16FIFA: Unified Faithfulness Evaluation Framework for Text-to-Video and Video-to-Text Generation2025-07-09Beyond Accuracy: Metrics that Uncover What Makes a 'Good' Visual Descriptor2025-07-04Prompt Disentanglement via Language Guidance and Representation Alignment for Domain Generalization2025-07-03Dataset Distillation via Vision-Language Category Prototype2025-06-30Show, Tell and Summarize: Dense Video Captioning Using Visual Cue Aided Sentence Summarization2025-06-25