相关论文: TPCap: Unlocking Zero-Shot Image Captioning with T…

Vision-language models (VLMs), such as CLIP, have demonstrated strong performance across a range of downstream tasks. However, CLIP is still limited in negation understanding: the ability to recognize the absence or exclusion of a concept.…

Recent lightweight retrieval-augmented image caption models often utilize retrieved data solely as text prompts, thereby creating a semantic gap by leaving the original visual features unenhanced, particularly for object details or complex…

Large Multimodal Models (LMMs) have recently shown remarkable promise in low-level visual perception tasks, particularly in Image Quality Assessment (IQA), demonstrating strong zero-shot capability. However, achieving state-of-the-art…

Dense image captioning is critical for cross-modal alignment in vision-language pretraining and text-to-image generation, but scaling expert-quality annotations is prohibitively expensive. While synthetic captioning via strong…

CLIP (Contrastive Language-Image Pre-Training) has shown remarkable zero-shot transfer capabilities in cross-modal correlation tasks such as visual classification and image retrieval. However, its performance in cross-modal generation tasks…

Large-scale pre-trained multi-modal models (e.g., CLIP) demonstrate strong zero-shot transfer capability in many discriminative tasks. Their adaptation to zero-shot image-conditioned text generation tasks has drawn increasing interest.…

Tags are pivotal in facilitating the effective distribution of multimedia content in various applications in the contemporary Internet era, such as search engines and recommendation systems. Recently, large language models (LLMs) have…

Visual question answering (VQA) is known as an AI-complete task as it requires understanding, reasoning, and inferring about the vision and the language content. Over the past few years, numerous neural architectures have been suggested for…

Recent investigations into effective context lengths of modern flagship large language models (LLMs) have revealed major limitations in effective question answering (QA) and reasoning over long and complex contexts for even the largest and…

Automatic music captioning, which generates natural language descriptions for given music tracks, holds significant potential for enhancing the understanding and organization of large volumes of musical data. Despite its importance,…

Large web-sourced multimodal datasets have powered a slew of new methods for learning general-purpose visual representations, advancing the state of the art in computer vision and revolutionizing zero- and few-shot recognition. One crucial…

Figure captions are crucial for helping readers understand and remember a figure's key message. Many models have been developed to generate these captions, helping authors compose better quality captions more easily. Yet, authors almost…

Large Language Models (LLMs) are capable of performing zero-shot closed-book question answering tasks, based on their internal knowledge stored in parameters during pre-training. However, such internalized knowledge might be insufficient…

Detailed image captioning is essential for tasks like data generation and aiding visually impaired individuals. High-quality captions require a balance between precision and recall, which remains challenging for current multimodal large…

While recent advances in reinforcement learning have significantly enhanced reasoning capabilities in large language models (LLMs), these techniques remain underexplored in multi-modal LLMs for video captioning. This paper presents the…

The recent large-scale vision-language pre-training (VLP) of dual-stream architectures (e.g., CLIP) with a tremendous amount of image-text pair data, has shown its superiority on various multimodal alignment tasks. Despite its success, the…

CLIP is a seminal multimodal model that maps images and text into a shared representation space through contrastive learning on billions of image-caption pairs. Inspired by the rapid progress of large language models (LLMs), we investigate…

Generative language models (LMs) such as GPT-2/3 can be prompted to generate text with remarkable quality. While they are designed for text-prompted generation, it remains an open question how the generation process could be guided by…

Recently, Multimodal Large Language Models (MLLMs) encounter two key issues in multi-image contexts: (1) a lack of fine-grained perception across disparate images, and (2) a diminished capability to effectively reason over and synthesize…

While Large Language Models (LLMs) excel in zero-shot Question Answering (QA), they tend to expose biases in their internal knowledge when faced with socially sensitive questions, leading to a degradation in performance. Existing zero-shot…