相关论文: From Pixels to Words -- Towards Native One-Vision …

Building state-of-the-art Vision-Language Models (VLMs) with strong captioning capabilities typically necessitates training on billions of high-quality image-text pairs, requiring millions of GPU hours. This paper introduces the…

In this paper, we consider the problem of open-vocabulary semantic segmentation (OVS), which aims to segment objects of arbitrary classes instead of pre-defined, closed-set categories. The main contributions are as follows: First, we…

Zero-shot scene understanding in real-world settings presents major challenges due to the complexity and variability of natural scenes, where models must recognize new objects, actions, and contexts without prior labeled examples. This work…

VILA-U is a Unified foundation model that integrates Video, Image, Language understanding and generation. Traditional visual language models (VLMs) use separate modules for understanding and generating visual content, which can lead to…

The ability to construct mental models of the world is a central aspect of understanding. Similarly, visual understanding can be viewed as the ability to construct a representative model of the system depicted in an image. This work…

The development of Neural Radiance Fields (NeRFs) has provided a potent representation for encapsulating the geometric and appearance characteristics of 3D scenes. Enhancing the capabilities of NeRFs in open-vocabulary 3D semantic…

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…

Self-supervised visual foundation models produce powerful embeddings that achieve remarkable performance on a wide range of downstream tasks. However, unlike vision-language models such as CLIP, self-supervised visual features are not…

Robots are increasingly envisioned to interact in real-world scenarios, where they must continuously adapt to new situations. To detect and grasp novel objects, zero-shot pose estimators determine poses without prior knowledge. Recently,…

Open-vocabulary semantic segmentation models aim to accurately assign a semantic label to each pixel in an image from a set of arbitrary open-vocabulary texts. In order to learn such pixel-level alignment, current approaches typically rely…

Current pre-trained vison-language models (PVLMs) achieve excellent performance on a range of multi-modal datasets. Recent work has aimed at building multilingual models, and a range of novel multilingual multi-modal datasets have been…

Autonomous Vehicles (AVs) are transforming the future of transportation through advances in intelligent perception, decision-making, and control systems. However, their success is tied to one core capability, reliable object detection in…

Current large vision-language models (LVLMs) typically employ a connector module to link visual features with text embeddings of large language models (LLMs) and use end-to-end training to achieve multi-modal understanding in a unified…

We study joint learning of Convolutional Neural Network (CNN) and Transformer for vision-language pre-training (VLPT) which aims to learn cross-modal alignments from millions of image-text pairs. State-of-the-art approaches extract salient…

It is highly desirable yet challenging to generate image captions that can describe novel objects which are unseen in caption-labeled training data, a capability that is evaluated in the novel object captioning challenge (nocaps). In this…

Vision-language models, such as CLIP, have achieved significant success in aligning visual and textual representations, becoming essential components of many multi-modal large language models (MLLMs) like LLaVA and OpenFlamingo. However,…

Large-scale vision-language models (VLMs), trained on extensive datasets of image-text pairs, exhibit strong multimodal understanding capabilities by implicitly learning associations between textual descriptions and image regions. This…

In this study, we propose NOVO (NO text, Visual-Only prompts), a novel framework that bridges vision-language models (VLMs) and segmentation models through visual-only prompts. Unlike prior approaches that feed text-derived SEG token…

Large Language Model-based Vision-Language Models (LLM-based VLMs) have demonstrated impressive results in various vision-language understanding tasks. However, how well these VLMs can see image detail beyond the semantic level remains…

In cognitive science and AI, a longstanding question is whether machines learn representations that align with those of the human mind. While current models show promise, it remains an open question whether this alignment is superficial or…