Related papers: ECCV Caption: Correcting False Negatives by Collec…
Most pre-trained learning systems are known to suffer from bias, which typically emerges from the data, the model, or both. Measuring and quantifying bias and its sources is a challenging task and has been extensively studied in image…
Story visualization is an under-explored task that falls at the intersection of many important research directions in both computer vision and natural language processing. In this task, given a series of natural language captions which…
Although image captioning models have made significant advancements in recent years, the majority of them heavily depend on high-quality datasets containing paired images and texts which are costly to acquire. Previous works leverage the…
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…
We argue that generative text-to-image models often struggle with prompt adherence due to the noisy and unstructured nature of large-scale datasets like LAION-5B. This forces users to rely heavily on prompt engineering to elicit desirable…
Image recaptioning is widely used to generate training datasets with enhanced quality for various multimodal tasks. Existing recaptioning methods typically rely on powerful multimodal large language models (MLLMs) to enhance textual…
The evaluation of machine-generated image captions is a complex and evolving challenge. With the advent of Multimodal Large Language Models (MLLMs), image captioning has become a core task, increasing the need for robust and reliable…
Jointing visual-semantic embeddings (VSE) have become a research hotpot for the task of image annotation, which suffers from the issue of semantic gap, i.e., the gap between images' visual features (low-level) and labels' semantic features…
Image captioning is a research hotspot where encoder-decoder models combining convolutional neural network (CNN) and long short-term memory (LSTM) achieve promising results. Despite significant progress, these models generate sentences…
Tremendous progress has been made in recent years in developing better image captioning models, yet most of them rely on a separate object detector to extract regional features. Recent vision-language studies are shifting towards the…
Memes are a widely popular tool for web users to express their thoughts using visual metaphors. Understanding memes requires recognizing and interpreting visual metaphors with respect to the text inside or around the meme, often while…
Image captioning models have achieved impressive results on datasets containing limited visual concepts and large amounts of paired image-caption training data. However, if these models are to ever function in the wild, a much larger…
The creation of high-quality human-labeled image-caption datasets presents a significant bottleneck in the development of Visual-Language Models (VLMs). In this work, we investigate an approach that leverages the strengths of Large Language…
Coherent entity-aware multi-image captioning aims to generate coherent captions for neighboring images in a news document. There are coherence relationships among neighboring images because they often describe same entities or events. These…
There is growing interest in systems that generate captions for scientific figures. However, assessing these systems output poses a significant challenge. Human evaluation requires academic expertise and is costly, while automatic…
Image captioning is an important task for benchmarking visual reasoning and for enabling accessibility for people with vision impairments. However, as in many machine learning settings, social biases can influence image captioning in…
Video captioning can be used to assess the video understanding capabilities of Multimodal Large Language Models (MLLMs). However, existing benchmarks and evaluation protocols suffer from crucial issues, such as inadequate or homogeneous…
Evaluating the quality of automatically generated image descriptions is challenging, requiring metrics that capture various aspects such as grammaticality, coverage, correctness, and truthfulness. While human evaluation offers valuable…
Image captioning, a fundamental task in vision-language understanding, seeks to generate accurate natural language descriptions for provided images. Current image captioning approaches heavily rely on high-quality image-caption pairs, which…
Since acquiring pixel-wise annotations for training convolutional neural networks for semantic image segmentation is time-consuming, weakly supervised approaches that only require class tags have been proposed. In this work, we propose…