相关论文: MILES: Visual BERT Pre-training with Injected Lang…

The self-supervised Masked Image Modeling (MIM) schema, following "mask-and-reconstruct" pipeline of recovering contents from masked image, has recently captured the increasing interest in the multimedia community, owing to the excellent…

Image BERT pre-training with masked image modeling (MIM) becomes a popular practice to cope with self-supervised representation learning. A seminal work, BEiT, casts MIM as a classification task with a visual vocabulary, tokenizing the…

Joint image-text embedding is the bedrock for most Vision-and-Language (V+L) tasks, where multimodality inputs are simultaneously processed for joint visual and textual understanding. In this paper, we introduce UNITER, a UNiversal…

Video-Text pre-training aims at learning transferable representations from large-scale video-text pairs via aligning the semantics between visual and textual information. State-of-the-art approaches extract visual features from raw pixels…

Passage retrieval aims to retrieve relevant passages from large collections of the open-domain corpus. Contextual Masked Auto-Encoding has been proven effective in representation bottleneck pre-training of a monolithic dual-encoder for…

Referring image segmentation (RIS) aims to find a segmentation mask given a referring expression grounded to a region of the input image. Collecting labelled datasets for this task, however, is notoriously costly and labor-intensive. To…

In this paper, we introduce ActBERT for self-supervised learning of joint video-text representations from unlabeled data. First, we leverage global action information to catalyze the mutual interactions between linguistic texts and local…

Few-shot learning (FSL) is the task of learning to recognize previously unseen categories of images from a small number of training examples. This is a challenging task, as the available examples may not be enough to unambiguously determine…

How to learn discriminative video representation from unlabeled videos is challenging but crucial for video analysis. The latest attempts seek to learn a representation model by predicting the appearance contents in the masked regions.…

Recent works show that learning contextualized embeddings for words is beneficial for downstream tasks. BERT is one successful example of this approach. It learns embeddings by solving two tasks, which are masked language model (masked LM)…

Existing contrastive language-image pre-training aims to learn a joint representation by matching abundant image-text pairs. However, the number of image-text pairs in medical datasets is usually orders of magnitude smaller than that in…

Image-based visual-language (I-VL) pre-training has shown great success for learning joint visual-textual representations from large-scale web data, revealing remarkable ability for zero-shot generalisation. This paper presents a simple but…

Cross-modal retrieval is an important functionality in modern search engines, as it increases the user experience by allowing queries and retrieved objects to pertain to different modalities. In this paper, we focus on the image-sentence…

In this paper, we present StrucTexTv2, an effective document image pre-training framework, by performing masked visual-textual prediction. It consists of two self-supervised pre-training tasks: masked image modeling and masked language…

Large pre-trained vision-language models have shown great prominence in transferring pre-acquired knowledge to various domains and downstream tasks with appropriate prompting or tuning. Existing prevalent tuning methods can be generally…

Effective cross-modal retrieval is essential for applications like information retrieval and recommendation systems, particularly in specialized domains such as manufacturing, where product information often consists of visual samples…

Masked Autoencoder (MAE) has recently been shown to be effective in pre-training Vision Transformers (ViT) for natural image analysis. By reconstructing full images from partially masked inputs, a ViT encoder aggregates contextual…

We present a simplified, task-agnostic multi-modal pre-training approach that can accept either video or text input, or both for a variety of end tasks. Existing pre-training are task-specific by adopting either a single cross-modal encoder…

We introduce Perception Encoder (PE), a state-of-the-art vision encoder for image and video understanding trained via simple vision-language learning. Traditionally, vision encoders have relied on a variety of pretraining objectives, each…

Medical vision-and-language pre-training provides a feasible solution to extract effective vision-and-language representations from medical images and texts. However, few studies have been dedicated to this field to facilitate medical…