Moments in Time Dataset: one million videos for event understanding

We present the Moments in Time Dataset, a large-scale human-annotated collection of one million short videos corresponding to dynamic events unfolding within three seconds. Modeling the spatial-audio-temporal dynamics even for actions occurring in 3 second videos poses many challenges: meaningful events do not include only people, but also objects, animals, and natural phenomena; visual and auditory events can be symmetrical in time ("opening" is "closing" in reverse), and either transient or sustained. We describe the annotation process of our dataset (each video is tagged with one action or activity label among 339 different classes), analyze its scale and diversity in comparison to other large-scale video datasets for action recognition, and report results of several baseline models addressing separately, and jointly, three modalities: spatial, temporal and auditory. The Moments in Time dataset, designed to have a large coverage and diversity of events in both visual and auditory modalities, can serve as a new challenge to develop models that scale to the level of complexity and abstract reasoning that a human processes on a daily basis.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
Multimodal Activity Recognition Moments in Time Dataset TRN-Multiscale Top-1 (%) 28.27 # 4
Top-5 (%) 53.87 # 4
Multimodal Activity Recognition Moments in Time Dataset I3D Top-1 (%) 29.51 # 3
Top-5 (%) 56.06 # 3
Multimodal Activity Recognition Moments in Time Dataset Ensemble (SVM) Top-1 (%) 31.16 # 2
Top-5 (%) 57.67 # 2
Multimodal Activity Recognition Moments in Time Dataset TSN-Flow Top-1 (%) 15.71 # 5
Top-5 (%) 34.65 # 5
Multimodal Activity Recognition Moments in Time Dataset SoundNet Top-1 (%) 7.60 # 6
Top-5 (%) 18.00 # 6
Action Recognition Something-Something V1 ResNet50 I3D (Moments pretrained) Top 1 Accuracy 50 # 50
Action Recognition Something-Something V1 ResNet50 I3D (Kinetics pretrained) Top 1 Accuracy 48.6 # 58

Methods