ResearchTasksVisual Attention PredictionVisual Attention PredictionFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedObjectVisA 120 (test)SUM0.472CC16Feb 26, 2026Aria Everyday Activities (AEA) unseen (test)language-guided scene context-aware learning framework53.7F1 Score9Feb 26, 2026
Aria Everyday Activities (AEA) unseen (test)language-guided scene context-aware learning framework53.7F1 Score9Feb 26, 2026