AI Paper Atlas

Research map / Video / Video-language understanding

Visual Text Correction

Amir Mazaheri, Mubarak Shah

ECCV 2018 · Video › Video-language understanding · approach: Encoder-decoder video captioning · 11 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 word position gating to convolutional n-grams (ablation)Conv N-Grams · LSMDC-based VTC detectiondetection accuracy (%): 66.8 -> 69.0Improved
add bidirectional (BiLSTM) instead of one-way LSTM (ablation)long-term dependencies · LSMDC-based VTC detectiondetection accuracy (%): 58.0 -> 67.2Improved
combine conv n-grams with long-term dependencies (ablation)text-only detector · LSMDC-based VTC detectiondetection accuracy (%): 69.0 -> 72.5Improved
add visual gated bias (ablation)text-only detector · LSMDC-based VTC detectiondetection accuracy (%): 72.5 -> 74.5Improved
use visual gated bias instead of feature concatenation (ablation)detector with video · LSMDC-based VTC detectiondetection accuracy (%): 72.8 -> 74.5Improved
replace vanilla LSTM with proposed text modeldetector · LSMDC-based VTC detectiondetection accuracy (%): 28.0 -> 72.5Improved
add C3D video features (ablation)text-only corrector · LSMDC-based VTC correctioncorrection accuracy (%): 35.2 -> 38.6Improved
add VGG19 features instead of C3D (ablation)corrector with video · LSMDC-based VTC correctioncorrection accuracy (%): 38.6 -> 38.8Improved
add both VGG19 and C3D (ablation)corrector with video · LSMDC-based VTC correctioncorrection accuracy (%): 38.8 -> 38.9No clear effect
train end-to-end instead of detector plus pre-trained FIB (ablation)corrector · LSMDC-based VTC correctioncorrection accuracy (%): 36.0 -> 38.9Improved
add video to text-only model with multiple inaccuracies (ablation)detector · Multiple inaccuracies, all k (detection)sentence-based accuracy (%): 59 -> 63Improved
add video to text-only model with multiple inaccuracies (ablation)corrector · Multiple inaccuracies, all k (correction)word-based accuracy (%): 3 -> 18Improved

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