Large-scale vision-language models (VLMs) like CLIP successfully find correspondences
between images and text. Through the standard deterministic map** process, an image or …

Image-Text Matching (ITM) task, a fundamental vision-language (VL) task, suffers from the
inherent ambiguity arising from multiplicity and imperfect annotations. Deterministic …

Cross-modal alignment is essential for vision-language pre-training (VLP) models to learn
the correct corresponding information across different modalities. For this purpose, inspired …

Are vision-language models (VLMs) for open-vocabulary perception inherently open-set
models because they are trained on internet-scale datasets? We answer this question with a …

Current Visual-Language Pre-training (VLP) models are vulnerable to adversarial examples.
These adversarial examples present substantial security risks to VLP models, as they can …

Composed image retrieval (CoIR) involves a multi-modal query of the reference image and
modification text describing the desired changes, allowing users to express image retrieval …

Abstract Self-supervised Multi-modal Contrastive Learning (SMCL) remarkably advances
modern Vision-Language Pre-training (VLP) models by aligning visual and linguistic …

As a fundamental problem in multimodal learning multimodal fusion aims to compensate for
the inherent limitations of a single modality. One challenge of multimodal fusion is that the …

Vision-language models (VLMs) embed aligned image-text pairs into a joint space but often
rely on deterministic embeddings, assuming a one-to-one correspondence between images …

Event cameras have recently been shown beneficial for practical vision tasks such as action
recognition thanks to their high temporal resolution power efficiency and reduced privacy …