AI Paper Atlas

Research map / Video / Video-language understanding

Reconstruct and Represent Video Contents for Captioning via Reinforcement Learning

Wei Zhang, Bairui Wang, Lin Ma, Wei Liu

TPAMI 2019 · Video › Video-language understanding · approach: Encoder-decoder video captioning · 85 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 global reconstructor to SA-LSTM (ablation)SA-LSTM (Inception-V4) · MSR-VTT (test)CIDEr: 39.9 -> 41.7Improved
add local reconstructor to SA-LSTM (ablation)SA-LSTM (Inception-V4) · MSR-VTT (test)CIDEr: 39.9 -> 42.7Improved
add local reconstructor to SA-LSTM trained with RL (ablation)SA-LSTM (RL) · MSR-VTT (test)CIDEr: 46.1 -> 48.7Improved
add global reconstructor to SA-LSTM (ablation)SA-LSTM (Inception-V4) · MSVDCIDEr: 76.2 -> 79.7Improved
add local reconstructor to SA-LSTM (ablation)SA-LSTM (Inception-V4) · MSVDCIDEr: 76.2 -> 80.3Improved
add local reconstructor to S2VT (ablation)S2VT (Inception-V4) · MSVDCIDEr: 66.7 -> 69.8Improved
add local reconstructor to SA-LSTM (ablation)SA-LSTM · ActivityNet (val)CIDEr: 28.50 -> 35.52Improved
add self-critical RL fine-tuning to SA-LSTM (ablation)SA-LSTM · MSR-VTT (test)CIDEr: 39.9 -> 46.1Improved
combine global and local reconstructors (g+l) in RL setting (ablation)RecNet(RL) · MSVDCIDEr: 83.6 -> 85.9Improved
combine global and local reconstructors (g+l) in RL setting (ablation)RecNet(RL) · MSR-VTT (test)CIDEr: 48.7 -> 49.5Improved
replace learned reconstructor attention with transposed decoder attention matrix (ablation)RecNet_local · MSR-VTT (test)CIDEr: 42.7 -> 40.4Hurt
reduce MSVD training data to 50% with reconstructor (ablation)RecNet_local · MSVD (50% training data)CIDEr gain over SA-LSTM: +9.3% vs +5.4% on full dataImproved

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