AI Paper Atlas

Research map / Video / Video generation

Identity-Aware Multi-Sentence Video Description

Jae Sung Park, Trevor Darrell, Anna Rohrbach

ECCV 2020 · Video › Video generation · approach: Compositional text-to-video diffusion · 19 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 Transformer with BERT gender-pretrained text encoding instead of BERT Character LM (ablation)Fill-in the Identity · LSMDC Validation (Fill-in the Identity)Class-Acc: 57.9 -> 62.6Improved
Add training data augmentation with overlapping clip sets (ablation)Transformer + BERT Gen. LM · LSMDC Validation (Fill-in the Identity)Class-Acc: 62.6 -> 64.4Improved
Add training data augmentation with overlapping clip sets (ablation)Transformer + BERT Gen. LM · LSMDC Validation (Fill-in the Identity)Gender accuracy: 80.3 -> 81.8Improved
Add face cluster features (ablation)Transformer + BERT Gen. LM + Aug. · LSMDC Validation (Fill-in the Identity)Class-Acc: 64.4 -> 65.3Improved
Add face cluster features (ablation)Transformer + BERT Gen. LM + Aug. · LSMDC Validation (Fill-in the Identity)Inst-Acc: 69.6 -> 69.7No clear effect
Add I3D video features (ablation)Transformer + Aug. + Face · LSMDC Validation (Fill-in the Identity)Class-Acc: 65.3 -> 65.7Improved
Add I3D video features (ablation)Transformer + Aug. + Face · LSMDC Validation (Fill-in the Identity)Inst-Acc: 69.7 -> 69.6No clear effect
Add visual gender prediction loss (ablation)Transformer + Aug. + Face + Video · LSMDC Validation (Fill-in the Identity)Class-Acc: 65.7 -> 65.9Improved
Add visual gender prediction loss (ablation)Transformer + Aug. + Face + Video · LSMDC Validation (Fill-in the Identity)Gender accuracy: 81.8 -> 83.0Improved
Add visual input to the model (full vs text only) (ablation)Fill-in the Identity · LSMDC Test (Fill-in the Identity)Class-Acc: 62.7 -> 64.9Improved
Let humans see the videoHuman annotators · LSMDC Test, 200 random sets (Fill-in the Identity)Class-Acc: 65.7 -> 86.8Improved
Use joint Transformer prediction rather than pairwise binary matching (Yu et al., Brown et al.)Fill-in the Identity · LSMDC Test (Fill-in the Identity)Class-Acc: 40.6 -> 64.9; 47.5 -> 64.9Improved

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