YouTube-8M: A Large-Scale Video Classification Benchmark

Many recent advancements in Computer Vision are attributed to large datasets. Open-source software packages for Machine Learning and inexpensive commodity hardware have reduced the barrier of entry for exploring novel approaches at scale... (read more)

PDF Abstract

Results from the Paper


 Ranked #1 on Action Recognition on ActivityNet (using extra training data)

     Get a GitHub badge
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK USES EXTRA
TRAINING DATA
RESULT BENCHMARK
Action Recognition ActivityNet LSTM + Pretrained on YT-8M mAP 75.6 # 1
Action Recognition Sports-1M LSTM +Pretrained on YT-8M Video [email protected] 65.7 # 7
Video [email protected] 86.2 # 7
Video Classification YouTube-8M Mixture-of-2-Experts [email protected] 70.1 # 2
PERR 29.1 # 1
[email protected] 84.8 # 1

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet