AI Paper Atlas

Research map / Video / Action recognition

Moments in Time Dataset: One Million Videos for Event Understanding

Mathew Monfort, Carl Vondrick, Aude Oliva, Alex Andonian, Bolei Zhou, Kandan Ramakrishnan, Sarah Adel Bargal, Tom Yan, Lisa Brown, Quanfu Fan, Dan Gutfreund

TPAMI 2019 · Video › Action recognition · approach: Disentangled action recognition · 572 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
initialize ResNet50 from ImageNet instead of scratchResNet50 spatial · Moments in Time (val)top-1 accuracy: 23.65 -> 27.16Improved
initialize ResNet50 from Places instead of scratchResNet50 spatial · Moments in Time (val)top-1 accuracy: 23.65 -> 26.44Improved
ImageNet init instead of Places initResNet50 spatial · Moments in Time (val)top-1 accuracy: 26.44 -> 27.16Improved
add optical flow stream to TSN spatial stream (two-stream)TSN · Moments in Time (val)top-1 accuracy: 24.11 -> 25.32Improved
flow modality alone vs spatial for TSNTSN-Flow · Moments in Time (val)top-1 accuracy: 24.11 -> 15.71Hurt
use TSN over plain BNInception on flow inputBNInception-Flow · Moments in Time (val)top-1 accuracy: 11.60 -> 15.71Improved
inflate 3D ResNet50 from best 2D ResNet50 (I3D) rather than 2D spatial modelResNet50 · Moments in Time (val)top-1 accuracy: 27.16 -> 29.51Improved
ensemble spatial, spatiotemporal and auditory features with linear SVMI3D · Moments in Time (val)top-1 accuracy: 29.51 -> 31.16Improved
pretrain on Moments in Time instead of KineticsResNet50 I3D · HMDB51top-1 accuracy: 62.0 -> 65.9Improved
pretrain on Moments in Time instead of KineticsResNet50 I3D · Something-Somethingtop-1 accuracy: 48.6 -> 50.0Improved
pretrain on Moments in Time instead of KineticsResNet50 I3D · UCF101top-1 accuracy: 92.6 -> 91.9Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy