HyperAIHyperAI

Command Palette

Search for a command to run...

5 months ago

What Makes Training Multi-Modal Classification Networks Hard?

Weiyao Wang Du Tran Matt Feiszli

What Makes Training Multi-Modal Classification Networks Hard?

Abstract

Code Repositories

facebookresearch/R2Plus1D
caffe2
Mentioned in GitHub
facebookresearch/VMZ
caffe2
Mentioned in GitHub

Benchmarks

BenchmarkMethodologyMetrics
action-classification-on-kinetics-400G-Blend (Sports-1M pretrain)
Acc@1: 78.9
action-classification-on-kinetics-400G-Blend
Acc@1: 77.7
action-recognition-in-videos-on-minisports-1G-Blend
Clip Hit@1: 49.7
Video hit@1: 62.8
Video hit@5: 85.5
action-recognition-in-videos-on-sports-1m-1G-Blend
Video hit@1: 74.8
Video hit@5: 92.4

Build AI with AI

From idea to launch — accelerate your AI development with free AI co-coding, out-of-the-box environment and best price of GPUs.

AI Co-coding
Ready-to-use GPUs
Best Pricing
Get Started

Hyper Newsletters

Subscribe to our latest updates
We will deliver the latest updates of the week to your inbox at nine o'clock every Monday morning
Powered by MailChimp
What Makes Training Multi-Modal Classification Networks Hard? | Papers | HyperAI