AI Paper Atlas

Research map / Video / Video-language understanding

Hierarchical LSTMs with Adaptive Attention for Visual Captioning

Lianli Gao, Xiangpeng Li, Jingkuan Song, Heng Tao Shen

TPAMI 2019 · Video › Video-language understanding · approach: Encoder-decoder video captioning · 256 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 temporal attention to the basic LSTM (SA vs basic LSTM) (ablation)basic LSTM · MSVD (ResNet-152)CIDEr: 69.9 -> 72.0Improved
add adaptive attention to the basic LSTM (ablation)basic LSTM · MSVD (ResNet-152)CIDEr: 69.9 -> 71.5Improved
add adaptive attention to hLSTMt (ablation)hLSTMt · MSVD (ResNet-152)BLEU@4: 52.1 -> 53.0Improved
add adaptive attention to hLSTMt (ablation)hLSTMt · MSVD (ResNet-152)CIDEr: 73.5 -> 73.8Improved
use hierarchical (two-layer) LSTMs instead of a single LSTM with temporal attention (ablation)SA · MSVD (ResNet-152)CIDEr: 72.0 -> 73.5Improved
use ResNet-152 features instead of C3D features (ablation)hLSTMat · MSVD (encoder study)BLEU@4: 47.5 -> 53.0Improved
use deeper ResNet encoder (ResNet-50 to ResNet-101 to ResNet-152) (ablation)hLSTMat · MSVD (encoder study)BLEU@4: 49.0 -> 50.8 -> 53.0Improved
use Two-stream fusion instead of concatenation fusion of C3D and ResNet-152 (ablation)hLSTMat · MSVD (C3D+ResNet-152 fusion)CIDEr: 65.1 -> 71.3Improved
use ParA parallel adaptive attention instead of concatenation fusion (ablation)hLSTMat · MSVD (C3D+ResNet-152 fusion)BLEU@4: 52.5 -> 53.6Improved
add C3D motion features to ResNet-152 appearance features (Two-stream) (ablation)hLSTMat · MSVD (C3D+ResNet-152 fusion)CIDEr: 73.8 -> 71.3Mixed
replace C3D with Inception-v3 in the two-stream model (ablation)Two-stream · MSVDBLEU@4: 54.0 -> 56.2Improved
use spatial region attention instead of temporal attention (ablation)hLSTMat · MSVD (spatial attention)CIDEr: 73.8 -> 72.3Mixed

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