相关论文: VAR-CLIP: Text-to-Image Generator with Visual Auto…

In this work, we propose the use of "aligned visual captions" as a mechanism for integrating information contained within videos into retrieval augmented generation (RAG) based chat assistant systems. These captions are able to describe the…

Procedure planning requires a model to predict a sequence of actions that transform a start visual observation into a goal in instructional videos. While most existing methods rely primarily on visual observations as input, they often…

Text-to-video generation is an emerging field in generative AI, enabling the creation of realistic, semantically accurate videos from text prompts. While current models achieve impressive visual quality and alignment with input text, they…

Visual AutoRegressive (VAR) models based on next-scale prediction enable efficient hierarchical generation, yet the inference cost grows quadratically at high resolutions. We observe that the computationally intensive later scales…

We present ART$\boldsymbol{\cdot}$V, an efficient framework for auto-regressive video generation with diffusion models. Unlike existing methods that generate entire videos in one-shot, ART$\boldsymbol{\cdot}$V generates a single frame at a…

Vision-Language Models (VLMs) like CLIP offer promising solutions for Dynamic Facial Expression Recognition (DFER) but face challenges such as inefficient full fine-tuning, high complexity, and poor alignment between textual and visual…

Contrastive language-image pretraining (CLIP) using image-text pairs has achieved impressive results on image classification in both zero-shot and transfer learning settings. However, we show that directly applying such models to recognize…

Conditional image modeling based on textual descriptions is a relatively new domain in unsupervised learning. Previous approaches use a latent variable model and generative adversarial networks. While the formers are approximated by using…

In this work, we are dedicated to text-guided image generation and propose a novel framework, i.e., CLIP2GAN, by leveraging CLIP model and StyleGAN. The key idea of our CLIP2GAN is to bridge the output feature embedding space of CLIP and…

In this paper we explore the bi-directional mapping between images and their sentence-based descriptions. We propose learning this mapping using a recurrent neural network. Unlike previous approaches that map both sentences and images to a…

Video prediction is an important yet challenging problem; burdened with the tasks of generating future frames and learning environment dynamics. Recently, autoregressive latent video models have proved to be a powerful video prediction…

Contrastive Language-Image Pre-training (CLIP) has recently shown great promise in pixel-level zero-shot learning tasks. However, existing approaches utilizing CLIP's text and patch embeddings to generate semantic masks often misidentify…

We develop an approach for text-to-image generation that embraces additional retrieval images, driven by a combination of implicit visual guidance loss and generative objectives. Unlike most existing text-to-image generation methods which…

Latent diffusion models such as Stable Diffusion achieve state-of-the-art results on text-to-image generation tasks. However, the extent to which these models have a semantic understanding of the images they generate is not well understood.…

Advancements in generative models have sparked significant interest in generating images while adhering to specific structural guidelines. Scene graph to image generation is one such task of generating images which are consistent with the…

Masked autoregressive models (MAR) have emerged as a powerful paradigm for image and video generation, combining the flexibility of masked modeling with the expressiveness of continuous tokenizers. However, when sampling individual frames,…

Perceptual video compression leverages generative priors to reconstruct realistic textures and motions at low bitrates. However, existing perceptual codecs often lack native support for variable bitrate and progressive delivery, and their…

Recent text-to-image matching models apply contrastive learning to large corpora of uncurated pairs of images and sentences. While such models can provide a powerful score for matching and subsequent zero-shot tasks, they are not capable of…

There are a thousand ways to caption an image. Contrastive Language Pretraining (CLIP) on the other hand, works by mapping an image and its caption to a single vector -- limiting how well CLIP-like models can represent the diverse ways to…

While the Contrastive Language-Image Pretraining(CLIP) model has achieved remarkable success in a variety of downstream vison language understanding tasks, enhancing its capability for fine-grained image-text alignment remains an active…