相关论文: SynC: Synthetic Image Caption Dataset Refinement w…

Deep neural networks (DNNs) have been recently found popular for image captioning problems in remote sensing (RS). Existing DNN based approaches rely on the availability of a training set made up of a high number of RS images with their…

Recent advancements in multimodal models highlight the value of rewritten captions for improving performance, yet key challenges remain. For example, while synthetic captions often provide superior quality and image-text alignment, it is…

Web-scale training on paired text-image data is becoming increasingly central to multimodal learning, but is challenged by the highly noisy nature of datasets in the wild. Standard data filtering approaches succeed in removing mismatched…

Contrastive Language and Image Pairing (CLIP), a transformative method in multimedia retrieval, typically trains two neural networks concurrently to generate joint embeddings for text and image pairs. However, when applied directly, these…

Automated image captioning has the potential to be a useful tool for people with vision impairments. Images taken by this user group are often noisy, which leads to incorrect and even unsafe model predictions. In this paper, we propose a…

Zero-shot Composed Image Retrieval (ZS-CIR) aims to retrieve a target image given a reference image and a relative text, without relying on costly triplet annotations. Existing CLIP-based methods face two core challenges: (1) union-based…

Customization of text-to-image models enables users to insert new concepts or objects and generate them in unseen settings. Existing methods either rely on comparatively expensive test-time optimization or train encoders on single-image…

Vision-Language Models (VLMs) are pretrained on large, diverse, and noisy web-crawled datasets. This underscores the critical need for dataset pruning, as the quality of these datasets is strongly correlated with the performance of VLMs on…

Visual recognition in a low-data regime is challenging and often prone to overfitting. To mitigate this issue, several data augmentation strategies have been proposed. However, standard transformations, e.g., rotation, cropping, and…

Training-free zero-shot composed image retrieval models are recently gaining increasing research interest due to their generalizability and flexibility in unseen multimodal retrieval. Recent LLM-based advances focus on generating the…

We present an approach to synthesizing photographic images conditioned on semantic layouts. Given a semantic label map, our approach produces an image with photographic appearance that conforms to the input layout. The approach thus…

Current vision-language generative models rely on expansive corpora of paired image-text data to attain optimal performance and generalization capabilities. However, automatically collecting such data (e.g. via large-scale web scraping)…

Zero-shot image captioning (IC) without well-paired image-text data can be divided into two categories, training-free and text-only-training. Generally, these two types of methods realize zero-shot IC by integrating pretrained…

Image captioning systems have recently improved dramatically, but they still tend to produce captions that are insensitive to the communicative goals that captions should meet. To address this, we propose Issue-Sensitive Image Captioning…

Contrastive Language-Image Pre-training (CLIP) has significantly boosted the performance of various vision-language tasks by scaling up the dataset with image-text pairs collected from the web. However, the presence of intrinsic noise and…

Zero-Shot Composed Image Retrieval (ZS-CIR) aims to retrieve target images given a multimodal query (comprising a reference image and a modification text), without training on annotated triplets. Existing methods typically convert the…

Remote sensing change captioning (RSICC) aims to describe changes between bitemporal images in natural language. Existing methods often fail under challenges like illumination differences, viewpoint changes, blur effects, leading to…

Generative vision-language models (VLMs) exhibit strong high-level image understanding but lack spatially dense alignment between vision and language modalities, as our findings indicate. Orthogonal to advancements in generative VLMs,…

Recent contributions of semantic information theory reveal the set-element relationship between semantic and syntactic information, represented as synonymous relationships. In this paper, we propose a synonymous variational inference (SVI)…

Automatic image captioning evaluation is critical for benchmarking and promoting advances in image captioning research. Existing metrics only provide a single score to measure caption qualities, which are less explainable and informative.…