相关论文: SPair-71k: A Large-scale Benchmark for Semantic Co…
We propose a novel approach for disentangling visual and semantic features from the backbones of pre-trained diffusion models, enabling visual correspondence in a manner analogous to the well-established semantic correspondence. While…
Graphics (e.g., figures and charts) are ubiquitous in scientific papers, yet separating graphics from text increases cognitive load in understanding text-graphic connections. Research has found that word-scale graphics, or visual…
We present a method for finding cross-modal space-time correspondences. Given two images from different visual modalities, such as an RGB image and a depth map, our model identifies which pairs of pixels correspond to the same physical…
Image-text matching aims to build correspondences between visual and textual data by learning their pairwise similarities. Most existing approaches have adopted sparse binary supervision, indicating whether a pair of images and sentences…
Transferring visual style between images while preserving semantic correspondence between similar objects remains a central challenge in computer vision. While existing methods have made great strides, most of them operate at global level…
Large language models (LLMs) are increasingly deployed in multi-agent settings where communication must balance informativeness and secrecy. In such settings, an agent may need to signal information to collaborators while preventing an…
Learning commonsense reasoning from visual contexts and scenes in real-world is a crucial step toward advanced artificial intelligence. However, existing video reasoning benchmarks are still inadequate since they were mainly designed for…
Comparing research papers is a conventional method to demonstrate progress in experimental research. We present COMPARE, a taxonomy and a dataset of comparison discussions in peer reviews of research papers in the domain of experimental…
We propose an approach to semantic segmentation that achieves state-of-the-art supervised performance when applied in a zero-shot setting. It thus achieves results equivalent to those of the supervised methods, on each of the major semantic…
We introduce EXAMS-V, a new challenging multi-discipline multimodal multilingual exam benchmark for evaluating vision language models. It consists of 20,932 multiple-choice questions across 20 school disciplines covering natural science,…
This paper introduces "Semantic Scaling," a novel method for ideal point estimation from text. I leverage large language models to classify documents based on their expressed stances and extract survey-like data. I then use item response…
In surgical computer vision applications, obtaining labeled training data is challenging due to data-privacy concerns and the need for expert annotation. Unpaired image-to-image translation techniques have been explored to automatically…
Vision-Language Models (VLMs) excel at understanding single images, aided by high-quality instruction datasets. However, multi-image reasoning remains underexplored in the open-source community due to two key challenges: (1) scaling…
Camera pose estimation is crucial for many computer vision applications, yet existing benchmarks offer limited insight into method limitations across different geometric challenges. We introduce RUBIK, a novel benchmark that systematically…
Scientific machine reading comprehension (SMRC) aims to understand scientific texts through interactions with humans by given questions. As far as we know, there is only one dataset focused on exploring full-text scientific machine reading…
By design, word embeddings are unable to model the dynamic nature of words' semantics, i.e., the property of words to correspond to potentially different meanings. To address this limitation, dozens of specialized meaning representation…
We present a dataset of large-scale indoor spaces that provides a variety of mutually registered modalities from 2D, 2.5D and 3D domains, with instance-level semantic and geometric annotations. The dataset covers over 6,000m2 and contains…
Stereo matching is one of the widely used techniques for inferring depth from stereo images owing to its robustness and speed. It has become one of the major topics of research since it finds its applications in autonomous driving, robotic…
A machine can understand human activities, and the meaning of signs can help overcome the communication barriers between the inaudible and ordinary people. Sign Language Recognition (SLR) is a fascinating research area and a crucial task…
The integration of language and 3D perception is critical for embodied AI and robotic systems to perceive, understand, and interact with the physical world. Spatial reasoning, a key capability for understanding spatial relationships between…