Related papers: TVLT: Textless Vision-Language Transformer

Vision-and-Language Pre-training (VLP) has improved performance on various joint vision-and-language downstream tasks. Current approaches to VLP heavily rely on image feature extraction processes, most of which involve region supervision…

We present a framework for learning multimodal representations from unlabeled data using convolution-free Transformer architectures. Specifically, our Video-Audio-Text Transformer (VATT) takes raw signals as inputs and extracts multimodal…

This paper presents SimVTP: a Simple Video-Text Pretraining framework via masked autoencoders. We randomly mask out the spatial-temporal tubes of input video and the word tokens of input text and then feed them into a unified autencoder to…

Scene text recognition (STR) enables computers to recognize and read the text in various real-world scenes. Recent STR models benefit from taking linguistic information in addition to visual cues into consideration. We propose a novel…

In this paper, we propose Mixture of Layer-Wise Tokens (MoLT), a parameter- and memory-efficient adaptation framework for audio-visual learning. The key idea of MoLT is to replace conventional, computationally heavy sequential adaptation at…

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 propose a Vision-Language Transformer (VLT) framework for referring segmentation to facilitate deep interactions among multi-modal information and enhance the holistic understanding to vision-language features. There are different ways…

Although speech is a simple and effective way for humans to communicate with the outside world, a more realistic speech interaction contains multimodal information, e.g., vision, text. How to design a unified framework to integrate…

Vision-Language Transformers can be learned without low-level human labels (e.g. class labels, bounding boxes, etc). Existing work, whether explicitly utilizing bounding boxes or patches, assumes that the visual backbone must first be…

This paper reveals that large language models (LLMs), despite being trained solely on textual data, are surprisingly strong encoders for purely visual tasks in the absence of language. Even more intriguingly, this can be achieved by a…

In this work, we introduce Vision-Language Generative Pre-trained Transformer (VL-GPT), a transformer model proficient at concurrently perceiving and generating visual and linguistic data. VL-GPT achieves a unified pre-training approach for…

A great challenge in video-language (VidL) modeling lies in the disconnection between fixed video representations extracted from image/video understanding models and downstream VidL data. Recent studies try to mitigate this disconnection…

Vision-language pre-training (VLP) methods are blossoming recently, and its crucial goal is to jointly learn visual and textual features via a transformer-based architecture, demonstrating promising improvements on a variety of…

Audio and video are two most common modalities in the mainstream media platforms, e.g., YouTube. To learn from multimodal videos effectively, in this work, we propose a novel audio-video recognition approach termed audio video Transformer,…

This paper presents Audio-Visual LLM, a Multimodal Large Language Model that takes both visual and auditory inputs for holistic video understanding. A key design is the modality-augmented training, which involves the integration of…

The rapid success of Vision Large Language Models (VLLMs) often depends on the high-resolution images with abundant visual tokens, which hinders training and deployment efficiency. Current training-free visual token compression methods…

Current methods for learning visually grounded language from videos often rely on text annotation, such as human generated captions or machine generated automatic speech recognition (ASR) transcripts. In this work, we introduce the…

Video-language pre-training is a typical and challenging problem that aims at learning visual and textual representations from large-scale data in a self-supervised way. Existing pre-training approaches either captured the correspondence of…

Vision-language pre-training (VLP) has recently proven highly effective for various uni- and multi-modal downstream applications. However, most existing end-to-end VLP methods use high-resolution image-text box data to perform well on…

Self-attention and transformers have been widely used in deep learning. Recent efforts have been devoted to incorporating transformer blocks into different neural architectures, including those with convolutions, leading to various visual…