AI Paper Atlas

Research map / Video / Action recognition

Actor and Action Video Segmentation From a Sentence

Kirill Gavrilyuk, Amir Ghodrati, Zhenyang Li, Cees G. M. Snoek

CVPR 2018 · Video › Action recognition · approach: Temporal action segmentation · 9 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 Flow to the RGB stream (ablation)Sentence-guided video segmentation model · A2D Sentences testOverall IoU: 53.6% -> 55.1%Improved
Use a larger temporal context, increasing input frames from 1 to 16 (ablation)RGB video encoder · A2D Sentences testOverall IoU: 48.2% -> 53.6%Improved
Replace the LSTM sentence encoder with a 1D convolutional encoder (ablation)Sentence-guided video segmentation model · A2D Sentences testOverall IoU: 51.8% -> 53.6%Improved
Replace the bidirectional LSTM sentence encoder with a 1D convolutional encoder (ablation)Sentence-guided video segmentation model · A2D Sentences testOverall IoU: 52.1% -> 53.6%Improved
Add supervision at multiple resolutions rather than only the highest resolution (ablation)Sentence-guided video segmentation model · A2D Sentences testOverall IoU: 49.4% -> 53.6%Improved
Use Flow input instead of RGB input (ablation)Video encoder · A2D Sentences testOverall IoU: 53.6% -> 49.5%Hurt
Use RGB + Flow fusion instead of RGB only (ablation)Sentence-guided video segmentation model · A2D Sentences testmAP: 19.8 -> 21.5Improved
Use the proposed sentence-guided model rather than the strongest fine-tuned image baselineA2D Sentences segmentation · A2D Sentences testMean IoU: 35.4 -> 42.6Improved
Use the proposed model rather than Hu et al.J-HMDB Sentences segmentation · J-HMDB Sentences testmAP: 17.8 -> 23.3Improved
Use the proposed model rather than Hu et al.J-HMDB Sentences segmentation · J-HMDB Sentences testOverall IoU: 54.6 -> 54.1Hurt
Use the proposed model rather than Kalogeiton et al.A2D actor segmentation · A2DClass-Average accuracy: 73.7 -> 71.4Hurt
Use the proposed model rather than Kalogeiton et al.A2D actor and action segmentation · A2DMean IoU: 29.7 -> 34.8Improved

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