Showing cs.CVShow all
2 papers · 1 filter
cs.CV2026
Prompt Sensitivity in Vision-Language Grounding: How Small Changes in Wording Affect Object Detection
Dawar Jyoti Deka, Amit Sethi, Syed Mohammad Ali
Vision-language models enable open-vocabulary object grounding through natural language queries, under the implicit assumption that semantically equivalent descriptions yield consi…
cs.CV2026
Inference-Time Temporal Probability Smoothing for Stable Video Segmentation with SAM2 under Weak Prompts
Dawar Jyoti Deka
Interactive video segmentation models such as SAM2 have demonstrated strong generalization across diverse visual domains. However, under weak user supervision, for example, when sp…