AI Paper Atlas

Research map / Multi-agent systems and games / Human-AI and goal-conditioned

Look-Ahead Before You Leap: End-to-End Active Recognition by Forecasting the Effect of Motion

Dinesh Jayaraman, Kristen Grauman

ECCV 2016 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Vision-language navigation agents · 73 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 the look-ahead module to the active RNNActive RNN · SUN360 (T=5)accuracy (%): 65.32 -> 66.01Improved
add the look-ahead module to the active RNNActive RNN · SUN360 (T=3)accuracy (%): 57.52 -> 58.12Improved
add the look-ahead module to the active RNNActive RNN · SUN360 (T=2)accuracy (%): 50.76 -> 51.72Improved
add the look-ahead module to the active RNNActive RNN · GERMS (T=3)accuracy (%): 46.86 -> 47.99Improved
add the look-ahead module to the active RNNActive RNN · GERMS (T=2)accuracy (%): 47.30 -> 48.02Improved
learn motion policy with REINFORCE instead of random motions (ablation)Random views (recurrent) · SUN360 (T=5)accuracy (%): 55.64 -> 65.32Improved
learn motion policy with REINFORCE instead of random motions (ablation)Random views (recurrent) · GERMS (T=3)accuracy (%): 44.24 -> 46.86Improved
average per-timestep classifier outputs on top of the look-ahead RNNLook-ahead active RNN · SUN360 (T=5)accuracy (%): 66.01 -> 62.61Hurt
average per-timestep classifier outputs on top of the look-ahead RNNLook-ahead active RNN · GERMS (T=3)accuracy (%): 47.99 -> 48.31Improved
use recurrent aggregation instead of averaging over random views (ablation)Random views (average) · SUN360 (T=5)accuracy (%): 54.21 -> 55.64Improved
use recurrent aggregation instead of averaging over random views (ablation)Random views (average) · GERMS (T=3)accuracy (%): 46.97 -> 44.24Hurt
use multiple random views instead of a single view (ablation)Single view (neural net) · SUN360 (T=5)accuracy (%): 40.12 -> 54.21Improved

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