Most visual recognition studies rely heavily on crowd-labelled data in deep neural networks
(DNNs) training, and they usually train a DNN for each single visual recognition task …

Video moment retrieval pursues an efficient and generalized solution to identify the specific
temporal segments within an untrimmed video that correspond to a given language …

While existing backdoor attacks have successfully infected multimodal contrastive learning
models such as CLIP they can be easily countered by specialized backdoor defenses for …

We study the zero-shot Composed Image Retrieval (ZS-CIR) task which is to retrieve the
target image given a reference image and a description without training on the triplet …

Abstract Multi-modal (vision-language) models, such as CLIP, are replacing traditional
supervised pre-training models (eg, ImageNet-based pre-training) as the new generation of …

Abstract The advancement of Zero-Shot Learning in the medical domain has been driven
forward by using pre-trained models on large-scale image-text pairs focusing on image-text …

Contrastive image-text models such as CLIP form the building blocks of many state-of-the-art
systems. While they excel at recognizing common generic concepts, they still struggle on …

The success of contrastive language-image pretraining (CLIP) relies on the supervision from
the pairing between images and captions which tends to be noisy in web-crawled data. We …

In the era of big data and Artificial Intelligence, an emerging paradigm is to utilize contrastive
self-supervised learning to model large-scale heterogeneous data. Many existing foundation …

We aim at finetuning a vision-language model without hurting its out-of-distribution (OOD)
generalization. We address two types of OOD generalization ie i) domain shift such as …