Related papers: ComicsPAP: understanding comic strips by picking t…
Recently, scaling images to high resolution has received much attention in multimodal large language models (MLLMs). Most existing practices adopt a sliding-window-style cropping strategy to adapt to resolution increase. Such a cropping…
Large language models (LLMs) have demonstrated impressive performance and spurred numerous AI applications, in which role-playing agents (RPAs) are particularly popular, especially for fictional characters. The prerequisite for these RPAs…
Large multimodal models (LMMs) have exhibited proficiencies across many visual tasks. Although numerous well-known benchmarks exist to evaluate model performance, they increasingly have insufficient headroom. As such, there is a pressing…
Recent Video-Language Models (VLMs) achieve promising results on long-video understanding, but their performance still lags behind that achieved on tasks involving images or short videos. This has led to great interest in improving the long…
In this paper, we develop a MultiTask Learning (MTL) model to achieve dense predictions for comics panels to, in turn, facilitate the transfer of comics from one publication channel to another by assisting authors in the task of…
Understanding infographic charts with design-driven visual elements (e.g., pictograms, icons) requires both visual recognition and reasoning, posing challenges for multimodal large language models (MLLMs). However, existing visual-question…
Multimodal Large Language Models (MLLMs) have shown remarkable versatility in understanding diverse multimodal data and tasks. However, these capabilities come with an increased model scale. While post-training pruning reduces model size in…
Multimodal large language models (MLLMs) have demonstrated promising results in a variety of tasks that combine vision and language. As these models become more integral to research and applications, conducting comprehensive evaluations of…
Image descriptions can help visually impaired people to quickly understand the image content. While we made significant progress in automatically describing images and optical character recognition, current approaches are unable to include…
Chart understanding is a quintessential information fusion task, requiring the seamless integration of graphical and textual data to extract meaning. The advent of Multimodal Large Language Models (MLLMs) has revolutionized this domain, yet…
The emergence of Large Vision-Language Models (LVLMs) has significantly advanced video understanding capabilities. However, existing benchmarks focus predominantly on coarse-grained tasks such as action segmentation, classification,…
Reasoning over sequences of images remains a challenge for multimodal large language models (MLLMs). While recent models incorporate multi-image data during pre-training, they still struggle to recognize sequential structures, often…
Comics, as a medium, uniquely combine text and images in styles often distinct from real-world visuals. For the past three decades, computational research on comics has evolved from basic object detection to more sophisticated tasks.…
Charts are widely used to present complex information. Deriving meaningful insights in real-world contexts often requires interpreting multiple related charts together. Research on understanding multi-chart images has not been extensively…
Memes are a popular element of modern web communication, used not only as static artifacts but also as interactive replies within conversations. While computational research has focused on analyzing the intrinsic properties of memes, the…
We present Perceive Anything Model (PAM), a conceptually straightforward and efficient framework for comprehensive region-level visual understanding in images and videos. Our approach extends the powerful segmentation model SAM 2 by…
Estimating the depth of comics images is challenging as such images a) are monocular; b) lack ground-truth depth annotations; c) differ across different artistic styles; d) are sparse and noisy. We thus, use an off-the-shelf unsupervised…
As multimodal large language models (MLLMs) grow increasingly capable, fixed benchmarks are gradually losing their effectiveness in evaluating high-level scientific understanding. In this paper, we introduce the Multimodal Academic Cover…
While Multimodal Large Language Models (MLLMs) are adept at answering what is in an image-identifying objects and describing scenes-they often lack the ability to understand how an image feels to a human observer. This gap is most evident…
The advent of large Vision-Language Models (VLMs) has significantly advanced multimodal tasks, enabling more sophisticated and accurate reasoning across various applications, including image and video captioning, visual question answering,…