AI Paper Atlas

Research map / Video / Video-language understanding

Multi-modal Transformer for Video Retrieval

Valentin Gabeur, Chen Sun, Karteek Alahari, Cordelia Schmid

ECCV 2020 · Video › Video-language understanding · approach: Text-video retrieval · 631 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
replace max-pooled expert features with MMT over all extracted features (ablation)video encoder · MSRVTT 1k-AR@5: 50.9 -> 54.0Improved
replace collaborative gating with MMT (ablation)video encoder · MSRVTT 1k-AR@5: 51.3 -> 52.5Improved
give MMT all extracted features instead of only aggregated ones (ablation)MMT · MSRVTT 1k-AR@5: 52.5 -> 54.0Improved
keep temporal order of features rather than shuffling (ablation)MMT · MSRVTT 1k-AR@5: 53.3 -> 54.0Improved
initialise F_agg with max pooling instead of zeros (ablation)MMT · MSRVTT 1k-AR@5: 50.2 -> 54.0Improved
initialise F_agg with max pool instead of mean pool (ablation)MMT · MSRVTT 1k-AR@5: 54.2 -> 54.0No clear effect
use 4 layers 4 heads instead of 2 layers 2 heads (ablation)MMT · MSRVTT 1k-AR@5: 53.2 -> 54.0Improved
use 8 layers 8 heads instead of 4 layers 4 heads (ablation)MMT · MSRVTT 1k-AR@5: 54.0 -> 53.9No clear effect
finetune BERT instead of freezing it (ablation)caption encoder · MSRVTT (from scratch)R@5: 17.1 -> 54.0Improved
remove stop words from captions (zero-shot) (ablation)pretrained model · MSRVTT zero-shotR@5: 6.9 -> 14.4Improved
remove stop words from captions (training from scratch) (ablation)MMT · MSRVTTR@5: 54.0 -> 50.0Hurt
remove stop words from captions (pretrain then finetune) (ablation)MMT · MSRVTTR@5: 57.1 -> 55.0Hurt

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