相关论文: TVLT: Textless Vision-Language Transformer

Video paragraph captioning aims to generate a multi-sentence description of an untrimmed video with several temporal event locations in coherent storytelling. Following the human perception process, where the scene is effectively understood…

The integration of Large Language Model (LLMs) blocks with Vision Transformers (ViTs) holds immense promise for vision-only tasks by leveraging the rich semantic knowledge and reasoning capabilities of LLMs. However, a fundamental challenge…

The success of Vision Language Models (VLMs) on various vision-language tasks heavily relies on pre-training with large scale web-crawled datasets. However, the noisy and incomplete nature of web data makes dataset scale crucial for…

In this paper, we introduce ResNetVLLM (ResNet Vision LLM), a novel cross-modal framework for zero-shot video understanding that integrates a ResNet-based visual encoder with a Large Language Model (LLM. ResNetVLLM addresses the challenges…

Vision-Language Pre-training (VLP) has advanced the performance of many vision-language tasks, such as image-text retrieval, visual entailment, and visual reasoning. The pre-training mostly utilizes lexical databases and image queries in…

We propose VisualBERT, a simple and flexible framework for modeling a broad range of vision-and-language tasks. VisualBERT consists of a stack of Transformer layers that implicitly align elements of an input text and regions in an…

Large Language Models (LLMs) have been widely used in various tasks, motivating us to develop an LLM-based assistant for videos. Instead of training from scratch, we propose a module to transform arbitrary well-trained image-based LLMs into…

While generative modeling on multimodal image-text data has been actively developed with large-scale paired datasets, there have been limited attempts to generate both image and text data by a single model rather than a generation of one…

Large vision-language models (VLMs) typically process hundreds or thousands of visual tokens per image or video frame, incurring quadratic attention cost and substantial redundancy. Existing token reduction methods often ignore the textual…

Recently, test-time adaptation has garnered attention as a method for tuning models without labeled data. The conventional modus operandi for adapting pre-trained vision-language models (VLMs) during test-time primarily focuses on tuning…

As the open community of large language models (LLMs) matures, multimodal LLMs (MLLMs) have promised an elegant bridge between vision and language. However, current research is inherently constrained by challenges such as the need for…

Learning efficient and expressive visual representation has long been the pursuit of computer vision research. While Vision Transformers (ViTs) gradually replace traditional Convolutional Neural Networks (CNNs) as more scalable vision…

Audio-visual automatic speech recognition (AV-ASR) introduces the video modality into the speech recognition process, often by relying on information conveyed by the motion of the speaker's mouth. The use of the video signal requires…

Sign language translation (SLT) is a challenging task that involves translating sign language images into spoken language. For SLT models to perform this task successfully, they must bridge the modality gap and identify subtle variations in…

We propose the Vision-and-Augmented-Language Transformer (VAuLT). VAuLT is an extension of the popular Vision-and-Language Transformer (ViLT), and improves performance on vision-and-language (VL) tasks that involve more complex text inputs…

We present a masked vision-language transformer (MVLT) for fashion-specific multi-modal representation. Technically, we simply utilize vision transformer architecture for replacing the BERT in the pre-training model, making MVLT the first…

With recent progress in joint modeling of visual and textual representations, Vision-Language Pretraining (VLP) has achieved impressive performance on many multimodal downstream tasks. However, the requirement for expensive annotations…

Recent research tries to extend image restoration capabilities from human perception to machine perception, thereby enhancing the performance of high-level vision tasks in degraded environments. These methods, primarily based on supervised…

Vision-and-language models (VLMs) have been increasingly explored in the medical domain, particularly following the success of CLIP in general domain. However, unlike the relatively straightforward pairing of 2D images and text, curating…

Multimodal large language models (MLLMs) suffer from high computational costs due to excessive visual tokens, particularly in high-resolution and video-based scenarios. Existing token reduction methods typically focus on isolated pipeline…