AI Paper Atlas

Research map / Video / Video segmentation and tracking

Movies2Scenes: Using Movie Metadata To Learn Scene Representation

Shixing Chen, Chun-Hao Liu, Xiang Hao, Xiaohan Nie, Maxim Arap, Raffay Hamid

CVPR 2023 · Video › Video segmentation and tracking · approach: Self-supervised video representation learning · 11 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
Use Movies2Scenes scene-contrast representations instead of SlowFast representationsLVU place retrieval · LVU place retrieval, all queriestop-1 precision: 38.59 -> 47.36Improved
Use Movies2Scenes scene-contrast representations instead of CLIP representationsLVU place retrieval · LVU place retrieval, all queriestop-5 precision: 29.64 -> 39.29Improved
Use Movies2Scenes scene-contrast representations instead of CLIP representationsLVU place retrieval · LVU place retrieval, all queriestop-10 precision: 28.85 -> 35.70Improved
Use Movies2Scenes pre-training instead of MerlotReserve pre-trainingMCD age-appropriate activity classification · MCDaverage: 66.2 -> 71.1Improved
Use Movies2Scenes pre-training instead of MerlotReserve pre-trainingMCD age-appropriate activity classification · MCDsex: 77.0 -> 81.5Improved
Use Movies2Scenes pre-training instead of MerlotReserve pre-trainingMCD age-appropriate activity classification · MCDviolence: 68.2 -> 70.2Improved
Use Movies2Scenes pre-training instead of BridgeFormer pre-trainingMCD age-appropriate activity classification · MCDdrug-use: 61.2 -> 61.8Improved

Later papers that compared with this method

1 later accepted paper reports Movies2Scenes as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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