conftrace_

pretrained vision-language model

5 papers

Explore in graph

Co-occurring keywords · papers mentioning both

multimodal representation (2) zero-shot method (1) spatio-temporal grounding (1) compositional vulnerability (1) attribute prompt (1) non-incremental learner (1) attribute bank (1) zero-shot (1) multimodal modulation (1) prototype-based textual modulation (1)

Papers

Can LLMs Deceive CLIP? Benchmarking Adversarial Compositionality of Pre-trained Multimodal Representation via Text Updates ACL 2025 Enhanced OoD Detection through Cross-Modal Alignment of Multi-Modal Representations CVPR 2025 FakeRadar: Probing Forgery Outliers to Detect Unknown Deepfake Videos ICCV 2025 E3M: Zero-Shot Spatio-Temporal Video Grounding with Expectation-Maximization Multimodal Modulation ECCV 2024 AttriCLIP: A Non-Incremental Learner for Incremental Knowledge Learning CVPR 2023