AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Trial-Oriented Visual Rearrangement

Yuyi Liu, Xinhang Song, Tianliang Qi, Shuqiang Jiang

ICCV 2025 · Detection and segmentation › Open-set and few-shot detection · approach: Hand-object and articulated interaction · 1 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 dynamic trial mechanism (ablation)TOR (static scoring only) · AI2THOR RoomR (test)Success rate (%): 11.3 -> 18.5Improved
add static scoring (ablation)TOR (dynamic trial only) · AI2THOR RoomR (test)Success rate (%): 17.1 -> 18.5Improved
add dynamic trial mechanism (ablation)TOR (static scoring only) · AI2THOR RoomR (test)Fixed Strict (%): 31.5 -> 40.6Improved
add static scoring (ablation)TOR (dynamic trial only) · AI2THOR RoomR (test)Fixed Strict (%): 40.0 -> 40.6Improved
add static scoring to reduce trial attempts (ablation)TOR (dynamic trial only) · AI2THOR RoomR (test)Average trial times: 2.16 -> 1.33Improved
add dynamic trial and static scoring to CAVR-like baseline (ablation)CAVR · AI2THOR RoomR (test)Success rate (%): 8.9 -> 18.5Improved
add dynamic trial and static scoring (ablation)CAVR · AI2THOR RoomR (test)Energy Remaining: 0.800 -> 0.639Improved
TOR vs CAVR on harder VIR datasetCAVR · VIR dataset (test)Success rate (%): 4.5 -> 11.3Improved
TOR vs CAVR on RoomR testCAVR · AI2THOR RoomR (test)Success rate (%): 8.9 -> 18.5Improved
TOR vs CAVR on RoomR testCAVR · AI2THOR RoomR (test)Misplaced: 0.797 -> 0.633Improved
set diff-cloud granularity 0.01m and reduction threshold 50 (ablation)TOR · RoomR validationaverage metrics: granularity 0.01m, threshold 50Improved

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