相关论文: OPT: Omni-Perception Pre-Trainer for Cross-Modal U…

In this work, we pursue a unified paradigm for multimodal pretraining to break the scaffolds of complex task/modality-specific customization. We propose OFA, a Task-Agnostic and Modality-Agnostic framework that supports Task…

We propose UniT, a Unified Transformer model to simultaneously learn the most prominent tasks across different domains, ranging from object detection to natural language understanding and multimodal reasoning. Based on the transformer…

Recent cross-lingual cross-modal works attempt to extend Vision-Language Pre-training (VLP) models to non-English inputs and achieve impressive performance. However, these models focus only on understanding tasks utilizing encoder-only…

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…

Large Language Models (LLMs) have made significant strides in text generation and comprehension, with recent advancements extending into multimodal LLMs that integrate visual and audio inputs. However, these models continue to struggle with…

We present Emu, a Transformer-based multimodal foundation model, which can seamlessly generate images and texts in multimodal context. This omnivore model can take in any single-modality or multimodal data input indiscriminately (e.g.,…

Recently, vision-language joint representation learning has proven to be highly effective in various scenarios. In this paper, we specifically adapt vision-language joint learning for scene text detection, a task that intrinsically involves…

Contrastive Language-Image Pre-training (CLIP) has shown impressive performance in aligning visual and textual representations. Recent studies have extended this paradigm to 3D vision to improve scene understanding for autonomous driving. A…

Cross-modal alignment Learning integrates information from different modalities like text, image, audio and video to create unified models. This approach develops shared representations and learns correlations between modalities, enabling…

Vision-and-language reasoning requires an understanding of visual concepts, language semantics, and, most importantly, the alignment and relationships between these two modalities. We thus propose the LXMERT (Learning Cross-Modality Encoder…

Transformer is a popularly used neural network architecture, especially for language understanding. We introduce an extended and unified architecture that can be used for tasks involving a variety of modalities like image, text, videos,…

We propose to build omni-modal intelligence, which is capable of understanding any modality and learning universal representations. In specific, we propose a scalable pretraining paradigm, named Multimodal Context (MiCo), which can scale up…

Recent advances in Large Multimodal Models (LMMs) have unveiled great potential as visual assistants. However, most existing works focus on responding to individual instructions or using previous dialogues for contextual understanding.…

Side information of items, e.g., images and text description, has shown to be effective in contributing to accurate recommendations. Inspired by the recent success of pre-training models on natural language and images, we propose a…

While many BERT-based cross-modal pre-trained models produce excellent results on downstream understanding tasks like image-text retrieval and VQA, they cannot be applied to generation tasks directly. In this paper, we propose XGPT, a new…

Transfer learning between different language pairs has shown its effectiveness for Neural Machine Translation (NMT) in low-resource scenario. However, existing transfer methods involving a common target language are far from success in the…

Vision Transformers (ViTs) have demonstrated remarkable capabilities in learning representations, but their performance is compromised when applied to unseen domains. Previous methods either engage in prompt learning during the training…

Vision-language models (VLMs) such as CLIP demonstrate strong performance but struggle when adapted to downstream tasks. Prompt learning has emerged as an efficient and effective strategy to adapt VLMs while preserving their pre-trained…

Pre-trained models learn general representations from large datsets which can be fine-turned for specific tasks to significantly reduce training time. Pre-trained models like generative pretrained transformers (GPT), bidirectional encoder…

We present a new pre-training strategy called M$^{3}$3D ($\underline{M}$ulti-$\underline{M}$odal $\underline{M}$asked $\underline{3D}$) built based on Multi-modal masked autoencoders that can leverage 3D priors and learned cross-modal…