Showing cs.CVShow all
2 papers · 1 filter
cs.CV2026
TIPSv2: Advancing Vision-Language Pretraining with Enhanced Patch-Text Alignment
Bingyi Cao, Koert Chen, Kevis-Kokitsi Maninis +16
Recent progress in vision-language pretraining has enabled significant improvements to many downstream computer vision applications, such as classification, retrieval, segmentation…
cs.CV2024
Scene-Graph ViT: End-to-End Open-Vocabulary Visual Relationship Detection
Tim Salzmann, Markus Ryll, Alex Bewley +1
Visual relationship detection aims to identify objects and their relationships in images. Prior methods approach this task by adding separate relationship modules or decoders to ex…