FoCo learns composition for zero-shot CIR via text-anchored visual aggregation and context-conditioned semantic completion trained jointly with cross-instance contrastive loss, reporting SOTA on four benchmarks.
Tmcir: Token merge benefits composed image retrieval
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2representative citing papers
AdaTooler-V trains MLLMs to adaptively use vision tools via AT-GRPO reinforcement learning and new datasets, reaching 89.8% on V* and outperforming GPT-4o.
citing papers explorer
-
Learning to Compose: Revisiting Proxy Task Design for Zero-Shot Composed Image Retrieval
FoCo learns composition for zero-shot CIR via text-anchored visual aggregation and context-conditioned semantic completion trained jointly with cross-instance contrastive loss, reporting SOTA on four benchmarks.
-
AdaTooler-V: Adaptive Tool-Use for Images and Videos
AdaTooler-V trains MLLMs to adaptively use vision tools via AT-GRPO reinforcement learning and new datasets, reaching 89.8% on V* and outperforming GPT-4o.