相关论文: LAViTeR: Learning Aligned Visual and Textual Repre…

Embedding models have been crucial in enabling various downstream tasks such as semantic similarity, information retrieval, and clustering. Recently, there has been a surge of interest in developing universal text embedding models that can…

Computer vision tasks such as object detection and semantic/instance segmentation rely on the painstaking annotation of large training datasets. In this paper, we propose LocTex that takes advantage of the low-cost localized textual…

Video-to-Text (VTT) is the task of automatically generating descriptions for short audio-visual video clips, which can support visually impaired people to understand scenes of a YouTube video for instance. Transformer architectures have…

Pre-trained contextual vision-and-language (V&L) models have achieved impressive performance on various benchmarks. However, existing models require a large amount of parallel image-caption data for pre-training. Such data are costly to…

Vision and touch are two fundamental sensory modalities for robots, offering complementary information that enhances perception and manipulation tasks. Previous research has attempted to jointly learn visual-tactile representations to…

In this paper, we introduce a new vision-language pre-trained model -- ImageBERT -- for image-text joint embedding. Our model is a Transformer-based model, which takes different modalities as input and models the relationship between them.…

Vision-Language Models (VLMs) are powerful tools for processing and understanding text and images. We study the processing of visual tokens in the language model component of LLaVA, a prominent VLM. Our approach focuses on analyzing the…

Recent advancements in vision-language models have achieved remarkable results in making language models understand vision inputs. However, a unified approach to align these models across diverse tasks such as image captioning and visual…

The platonic representation hypothesis suggests that sufficiently large models converge to a shared representation geometry, even across modalities. Motivated by this, we ask: Can the semantic knowledge of a language model efficiently…

Previous vision-language pre-training models mainly construct multi-modal inputs with tokens and objects (pixels) followed by performing cross-modality interaction between them. We argue that the input of only tokens and object features…

We introduce a novel self-supervised pretext task for learning representations from audio-visual content. Prior work on audio-visual representation learning leverages correspondences at the video level. Approaches based on audio-visual…

Video-text retrieval is a class of cross-modal representation learning problems, where the goal is to select the video which corresponds to the text query between a given text query and a pool of candidate videos. The contrastive paradigm…

Advancements at the intersection of computer vision and natural language processing are crucial for applications like assistive tech, multimedia querying, and robotics. This dissertation proposes novel architectures to improve intelligent…

Text spotting, a task involving the extraction of textual information from image or video sequences, faces challenges in cross-domain adaption, such as image-to-image and image-to-video generalization. In this paper, we introduce a new…

Text-to-image generation has made significant advancements with the introduction of text-to-image diffusion models. These models typically consist of a language model that interprets user prompts and a vision model that generates…

Vision Transformers (ViTs) have emerged as popular models in computer vision, demonstrating state-of-the-art performance across various tasks. This success typically follows a two-stage strategy involving pre-training on large-scale…

Generating representations of video data is of key importance in advancing the field of machine perception. Most current techniques rely on hand-annotated data, which can be difficult to work with, expensive to generate, and hard to scale.…

Text-to-audio (TTA) generation is a recent popular problem that aims to synthesize general audio given text descriptions. Previous methods utilized latent diffusion models to learn audio embedding in a latent space with text embedding as…

In the field of multi-modal language models, the majority of methods are built on an architecture similar to LLaVA. These models use a single-layer ViT feature as a visual prompt, directly feeding it into the language models alongside…

Humans are far better learners who can learn a new concept very fast with only a few samples compared with machines. The plausible mystery making the difference is two fundamental learning mechanisms: learning to learn and learning by…