Dimensions overall score 7.0

GitHub Code Pulse

No public code linked for this paper yet.

• Existing visual grounding benchmarks primarily evaluate alignment between image regions and literal referring expressions, where models can often succeed by matching a prominent named category.limitation 95%
• Scenario-based visual grounding is more challenging than standard referring expression grounding because targets must be inferred from roles, intentions, and relational context rather than explicit naming.technical 90%
• The Referring Scenario Comprehension (RSC) benchmark contains approximately 31k training examples, 4k in-domain test examples, and a 3k out-of-distribution split with unseen object categories.method 95%
• The ScenGround method combines supervised warm-starting with difficulty-aware reinforcement learning for scenario-based visual grounding.method 90%
• Scenario-based queries expose systematic failures in current models that standard benchmarks do not reveal.result 90%
• Curriculum training improves performance on challenging slices and transfers to standard benchmarks.result 85%
• RSC benchmark queries are paragraph-length texts that describe object roles, user goals, and contextual cues, including deliberate references to distractor objects.method 90%
• Each RSC instance is annotated with interpretable difficulty tags for uniqueness, clutter, size, overlap, and position which expose distinct failure modes.method 90%

Competitive landscape

Competitor map is still being generated for this paper. Enable generation or check back soon.

Startup potential card