AI Paper Atlas

Research map / Video / Video segmentation and tracking

Improving Spatiotemporal Self-Supervision by Deep Reinforcement Learning

Uta Buchler, Biagio Brattoli, Bjorn Ommer

ECCV 2018 · Video › Video segmentation and tracking · approach: Self-supervised video representation learning · 116 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 RL-selected permutation policy to the spatial task (ablation)Spatial permutation task · Pascal VOC07 classificationmAP: 67.6 -> 71.3Improved
add RL-selected permutation policy to the temporal task (ablation)Temporal permutation task · Pascal VOC07 classificationmAP: 64.1 -> 65.9Improved
add RL policy to the combined spatiotemporal model (ablation)S+T · Pascal VOC07 classificationmAP: 72.0 -> 74.2Improved
add RL policy to the spatial task (ablation)Spatial permutation task · UCF-101 action recognitionaccuracy: 51.5 -> 54.6Improved
add RL policy to the temporal task (ablation)Temporal permutation task · UCF-101 action recognitionaccuracy: 52.8 -> 55.7Improved
add RL policy to the combined spatiotemporal model (ablation)S+T · UCF-101 action recognitionaccuracy: 57.3 -> 58.6Improved
train spatial and temporal tasks jointly instead of the spatial task alone (ablation)Spatial task · Pascal VOC07 classificationmAP: 67.6 -> 72.0Improved
train spatial and temporal tasks jointly instead of the temporal task alone (ablation)Temporal task · Pascal VOC07 classificationmAP: 64.1 -> 72.0Improved
train tasks in parallel instead of serially (spatial then temporal) (ablation)S&T vs S+T · Pascal VOC07 classificationmAP: 69.8 -> 72.0Improved
train tasks in parallel instead of serially (ablation)S&T vs S+T · UCF-101 action recognitionaccuracy: 54.2 -> 57.3Improved
use trained RL policy instead of random permutation selection (ablation)Self-supervised network · Validation accuracy after one epochrelative accuracy to random policy: (125\pm14)\%Improved
use inverse policy (discarded permutations) instead of random selection (ablation)Self-supervised network · Validation accuracy after one epochrelative accuracy to random policy: (78\pm16)\%Hurt

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