AI Paper Atlas

Research map / Video / Video-language understanding

Joint Syntax Representation Learning and Visual Cue Translation for Video Captioning

Jingyi Hou, Xinxiao Wu, Wentian Zhao, Jiebo Luo, Yunde Jia

ICCV 2019 · Video › Video-language understanding · approach: Encoder-decoder video captioning · 99 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 POS tagging and mixture model to the S2S baseline (ablation)ConvCap S2S baseline · MSVDCIDEr: 77.0 -> 87.8Improved
add mixture model for word generation instead of a softmax classifier (ablation)Ours · MSVDCIDEr: 82.1 -> 87.8Improved
add video POS tagging (ablation)Ours · MSVDCIDEr: 85.6 -> 87.8Improved
add constraint term Lc encouraging POS variety (ablation)Ours · MSVDCIDEr: 83.3 -> 87.8Improved
add constraint term Lc (ablation)Ours · MSVDB@4: 51.3 -> 52.8Improved
add video POS tagging (ablation)Ours · MSVDMETEOR: 35.1 -> 36.1Improved
add mixture model (ablation)Ours · MSVDMETEOR: 34.3 -> 34.3No clear effect
proposed method versus best prior on MSR-VTT B@4Ours · MSR-VTTB@4: 41.3 -> 42.3Improved
proposed method versus SDVC on ActivityNetOurs · ActivityNet Captions valMETEOR: 13.1 -> 11.3Hurt
proposed method versus GRU-EVE on MSR-VTTOurs · MSR-VTTCIDEr: 48.1 -> 49.1Improved

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