Related papers: Align before Fuse: Vision and Language Representat…

Weakly supervised violence detection refers to the technique of training models to identify violent segments in videos using only video-level labels. Among these approaches, multimodal violence detection, which integrates modalities such as…

Subtle semantic differences in retinal image and text data present great challenges for pre-training visual-language models. Moreover, false negative samples, i.e., image-text pairs having the same semantics but incorrectly regarded as…

Since the advent of popular visual generation frameworks like VQGAN and latent diffusion models, state-of-the-art image generation systems have generally been two-stage systems that first tokenize or compress visual data into a…

Large Vision-Language Models (LVLMs) commonly follow a paradigm that projects visual features and then concatenates them with text tokens to form a unified sequence input for Large Language Models (LLMs). However, this paradigm leads to a…

Vision-Language Models (VLMs) have demonstrated strong capability in a wide range of tasks such as visual recognition, document parsing, and visual grounding. Nevertheless, recent work shows that while VLMs often manage to capture the…

In this paper, we introduce LDGen, a novel method for integrating large language models (LLMs) into existing text-to-image diffusion models while minimizing computational demands. Traditional text encoders, such as CLIP and T5, exhibit…

This paper studies the problem of pre-training for small models, which is essential for many mobile devices. Current state-of-the-art methods on this problem transfer the representational knowledge of a large network (as a Teacher) into a…

Most existing methods in vision-language retrieval match two modalities by either comparing their global feature vectors which misses sufficient information and lacks interpretability, detecting objects in images or videos and aligning the…

We present Liquid, an auto-regressive generation paradigm that seamlessly integrates visual comprehension and generation by tokenizing images into discrete codes and learning these code embeddings alongside text tokens within a shared…

We propose Fast Language-Audio Pre-training (FLAP), a self-supervised approach that efficiently and effectively learns aligned audio and language representations through masking, contrastive learning and reconstruction. For efficiency, FLAP…

Driven by large-scale contrastive vision-language pre-trained models such as CLIP, recent advancements in the image-text matching task have achieved remarkable success in representation learning. Due to image-level visual-language…

Previous research has studied the task of segmenting cinematic videos into scenes and into narrative acts. However, these studies have overlooked the essential task of multimodal alignment and fusion for effectively and efficiently…

Vision-language pre-training like CLIP has shown promising performance on various downstream tasks such as zero-shot image classification and image-text retrieval. Most of the existing CLIP-alike works usually adopt relatively large image…

Vision-Language Models (VLMs) are a new family of models that align image content with natural language. Existing approaches typically fuse either (a) early: by mixing tokens/features inside the encoders, or (b) late: by comparing pooled…

Learning visual semantic similarity is a critical challenge in bridging the gap between images and texts. However, there exist inherent variations between vision and language data, such as information density, i.e., images can contain…

``Learning to hash'' is a practical solution for efficient retrieval, offering fast search speed and low storage cost. It is widely applied in various applications, such as image-text cross-modal search. In this paper, we explore the…

Recently, there has been a surge in the popularity of pre trained large language models (LLMs) (such as GPT-4), sweeping across the entire Natural Language Processing (NLP) and Computer Vision (CV) communities. These LLMs have demonstrated…

In this paper, we study how to use masked signal modeling in vision and language (V+L) representation learning. Instead of developing masked language modeling (MLM) and masked image modeling (MIM) independently, we propose to build joint…

Recent advancements in deep learning have significantly improved performance on computer vision tasks. Previous image classification methods primarily modify model architectures or add features, and they optimize models using cross-entropy…

Relational Language-Image Pre-training (RLIP) aims to align vision representations with relational texts, thereby advancing the capability of relational reasoning in computer vision tasks. However, hindered by the slow convergence of RLIPv1…