AI Paper Atlas

Research map / Video / Video segmentation and tracking

Deep Multimodal Representation Learning From Temporal Data

Xitong Yang, Palghat Ramesh, Radha Chitta, Sriganesh Madhvanath, Edgar A. Bernal, Jiebo Luo

CVPR 2017 · Video › Video segmentation and tracking · approach: Self-supervised video representation learning · 104 citations (OpenAlex)

Check 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
Use CorrRNN's temporal joint representation instead of CRBM featuresaudio-visual speech classification · AVLettersaccuracy: $67.10$ -> $\mathbf{83.40}$Improved
Use CorrRNN's temporal joint representation instead of CRBM featuresaudio-visual speech classification · CUAVEaccuracy: $69.10$ -> $\mathbf{95.9}$Improved
Learn features with both video and audio, then train and test using videoCorrRNN · AVLetters cross-modality learningaccuracy: 38.08 -> 81.85Improved
Learn features with both video and audio, then train and test using videoCorrRNN · CUAVE cross-modality learningaccuracy: 42.05 -> 96.22Improved
Learn features with both video and audio, then train and test using audioCorrRNN · AVLetters cross-modality learningaccuracy: 57.31 -> 85.33Improved
Learn features with both video and audio, then train and test using audioCorrRNN · CUAVE cross-modality learningaccuracy: 88.32 -> 96.11Improved
Learn a shared representation from both modalities and transfer across modalitiesCorrRNN · CUAVE shared representation learningaccuracy: 24.30 -> 96.77; 30.70 -> 96.33Improved
Use CorrRNN instead of MDAE + Audio RBM under 0dB SNR audio noiseCUAVE audio-visual speech classification · CUAVE noisy audio (0dB SNR)accuracy: 82.2 -> 90.88Improved
Add cross-reconstruction loss (ablation)CorrRNN · ISI activity classificationaccuracyImproved
Add self-reconstruction loss (ablation)CorrRNN · ISI activity classificationaccuracyImproved
Add correlation loss (ablation)CorrRNN · ISI activity classificationaccuracyImproved
Add dynamic modality weights (ablation)CorrRNN · ISI activity classificationaccuracyImproved

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