AI Paper Atlas

Research map / Video / Video-language understanding

Jointly Localizing and Describing Events for Dense Video Captioning

Yehao Li, Ting Yao, Yingwei Pan, Hongyang Chao, Tao Mei

CVPR 2018 · Video › Video-language understanding · approach: Dense video captioning · 180 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
Jointly train event localization and caption generation with descriptiveness regressionDVC · ActivityNet Captions validation, learnt proposalsMETEOR: 5.69 -> 6.93Improved
Jointly train event localization and caption generation with descriptiveness regressionDVC · ActivityNet Captions validation, GT proposalsMETEOR: 8.88 -> 10.33Improved
Use descriptiveness-driven temporal attention instead of mean pooling (ablation)LSTM captioner · ActivityNet Captions validation, learnt proposalsMETEOR: 5.53 -> 5.79Improved
Add high-level semantic attributes (ablation)DVC-D · ActivityNet Captions validation, learnt proposalsMETEOR: 5.79 -> 6.14Improved
Replace cross-entropy sentence loss with METEOR-reward reinforcement learning (ablation)DVC-D-A · ActivityNet Captions validation, learnt proposalsMETEOR: 6.14 -> 6.93Improved
Use P3D ResNet pool5 features instead of C3D features (ablation)DVC · ActivityNet Captions official testMETEOR: 10.36 -> 12.96Improved
Add conv9 anchor layer to conv3–conv8 (ablation)DVC temporal event proposal · ActivityNet Captions validationAUC: 55.73 -> 57.38Improved
Add conv10 anchor layer to conv3–conv9 (ablation)DVC temporal event proposal · ActivityNet Captions validationAUC: 57.38 -> 58.75Improved
Add conv11 anchor layer to conv3–conv10 (ablation)DVC temporal event proposal · ActivityNet Captions validationAUC: 58.75 -> 59.91Improved
Add conv12 anchor layer to conv3–conv11 (ablation)DVC temporal event proposal · ActivityNet Captions validationAUC: 59.91 -> 60.07Improved
Add descriptiveness regression to event proposal generationDVC temporal event proposal · ActivityNet Captions validationAUCImproved
Use ground-truth proposals rather than learned proposals (ablation)DVC · ActivityNet Captions validationMETEOR: 6.93 -> 10.33Improved

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