AI Paper Atlas

Research map / Video / Action recognition

VideoBERT: A Joint Model for Video and Language Representation Learning

Chen Sun, Austin Myers, Carl Vondrick, Kevin Murphy, Cordelia Schmid

ICCV 2019 · Video › Action recognition · approach: Contrastive video representation learning · 1,265 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
add video inputs (cross modal) to language prior (ablation)VideoBERT · YouCook II action classificationverb top-5 (%): 6.9 -> 43.3Improved
add video inputs (cross modal) to language prior (ablation)VideoBERT · YouCook II action classificationobject top-5 (%): 15.3 -> 33.7Improved
fine-tune BERT on cooking videos language (ablation)BERT language prior · YouCook II action classificationobject top-1 (%): 0.0 -> 7.7Improved
increase pretraining videos from 10K to 300K (ablation)VideoBERT · YouCook II action classification (pretraining data size)verb top-5 (%): 15.5 -> 43.3Improved
increase pretraining videos from 10K to 300K (ablation)VideoBERT · YouCook II action classification (pretraining data size)object top-5 (%): 17.8 -> 33.7Improved
increase pretraining videos from 10K to 300K (ablation)VideoBERT · YouCook II action classification (pretraining data size)object top-1 (%): 2.9 -> 13.1Improved
add text via cross-modal pretraining instead of video-only (ablation)VideoBERT feature extractor · YouCook II video captioning (val)CIDEr: 0.47 -> 0.49Improved
add text via cross-modal pretraining instead of video-only (ablation)VideoBERT feature extractor · YouCook II video captioning (val)BLEU-4: 3.81 -> 4.04Improved
use VideoBERT features instead of S3D featurescaptioning transformer · YouCook II video captioning (val)CIDEr: 0.31 -> 0.49Improved
concatenate S3D features with VideoBERT features (ablation)captioning transformer · YouCook II video captioning (val)CIDEr: 0.49 -> 0.55Improved
use VideoBERT cross modal instead of supervised S3D classifierzero-shot classification · YouCook II action classificationverb top-1 (%): 16.1 -> 3.2Hurt
use VideoBERT cross modal instead of supervised S3D classifierzero-shot classification · YouCook II action classificationverb top-5 (%): 46.9 -> 43.3No clear effect

Later papers that compared with this method

3 later accepted papers report VideoBERT as a baseline in their results tables; 2 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