AI Paper Atlas

Research map / Video / Video segmentation and tracking

The Sound of Water: Inferring Physical Properties From Pouring Liquids

Piyush Bagad, Makarand Tapaswi, Cees G. M. Snoek, Andrew Zisserman

TPAMI 2026 · Video › Video segmentation and tracking · approach: Layered video decomposition and dynamics · 5 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 visual co-supervision (ablation)audio pitch network · Test set I air column lengthMAE (cm): 0.78 -> 0.60Improved
add visual co-supervision (ablation)audio pitch network · Test set II air column lengthMAE (cm): 0.82 -> 0.71Improved
add visual co-supervision (ablation)audio pitch network · Test set I radiusMAE (cm): 1.62 -> 1.39Improved
add visual co-supervision (ablation)audio pitch network · Test set II radiusMAE (cm): 2.24 -> 1.88Improved
add visual co-supervision (ablation)audio pitch network · Test set I container heightMAE (cm): 2.23 -> 2.27No clear effect
add visual co-supervision (ablation)audio pitch network · Test set II container heightMAE (cm): 2.77 -> 2.85No clear effect
add visual co-supervision (ablation)audio pitch network · Test set I flow rateMAE (ml/s): 25.20 -> 22.50Improved
add visual co-supervision (ablation)audio pitch network · Test set II flow rateMAE (ml/s): 45.70 -> 40.41Improved
add visual co-supervision (ablation)audio pitch network · Test set I time to fillMAE (s): 25%: 3.96 -> 4.16; 50%: 1.62 -> 1.49; 75%: 1.53 -> 1.07Mixed
add visual co-supervision (ablation)audio pitch network · Test set II time to fillMAE (s): 25%: 4.39 -> 4.10; 50%: 3.44 -> 2.99; 75%: 2.66 -> 2.21Improved
add visual co-supervision (ablation)audio features · Shape classification (Test set III)per-sample accuracy (%): 88.63 -> 90.91Improved
add visual co-supervision (ablation)audio features · Shape classification (Test set III)mean class accuracy (%): 89.44 -> 92.47Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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