paper-with-me

홈 › Papers

OSCaR: Object State Captioning and State Change Representation

2024-02-27 · Nguyen Nguyen, Jing Bi, Ali Vosoughi, Yapeng Tian, Pooyan Fazli, Chenliang Xu

The capability of intelligent models to extrapolate and comprehend changes in object states is a crucial yet demanding aspect of AI research, particularly through the lens of human interaction in real-world settings. This task involves describing complex visual environments, identifying active objects, and interpreting their changes as conveyed through language. Traditional methods, which isolate object captioning and state change detection, offer a limited view of dynamic environments. Moreover, relying on a small set of symbolic words to represent changes has restricted the expressiveness of the language. To address these challenges, in this paper, we introduce the Object State Captioning and State Change Representation (OSCaR) dataset and benchmark. OSCaR consists of 14,084 annotated video segments with nearly 1,000 unique objects from various egocentric video collections. It sets a new testbed for evaluating multimodal large language models (MLLMs). Our experiments demonstrate that while MLLMs show some skill, they lack a full understanding of object state changes. The benchmark includes a fine-tuned model that, despite initial capabilities, requires significant improvements in accuracy and generalization ability for effective understanding of these changes. Our code and dataset are available at https://github.com/nguyennm1024/OSCaR.

📄 PDF Abstract BibTeX arXiv:2402.17128

Code (1)

nguyennm1024/oscar 공식 구현

Tasks

Change DetectionObject

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically
OSCAR OSCAR is a new learning method that uses object tags detected in images as anchor points to ease the learning of image-text alignment. The model take a triple as input…

Similar Papers 제목 키워드 기반

OSCAR: Open-Set CAD Retrieval from a Language Prompt and a Single Image

2026-01-12 · Tessa Pulli, Jean-Baptiste Weibel, Peter Hönig, Matthias Hirschmanner 외 arxiv

6D object pose estimation plays a crucial role in scene understanding for applications such as robotics and augmented reality. To support the needs of ever-changing object sets in such context, modern zero-shot object po…

Scene UnderstandingImage CaptioningPose Estimation

OSCAR-Net: Object-centric Scene Graph Attention for Image Attribution

2021-08-07 · ICCV 2021 10 · Eric Nguyen, Tu Bui, Vishy Swaminathan, John Collomosse

Images tell powerful stories but cannot always be trusted. Matching images back to trusted sources (attribution) enables users to make a more informed judgment of the images they encounter online. We propose a robust ima…

Contrastive LearningGraph AttentionImage Attribution

A Thorough Review on Recent Deep Learning Methodologies for Image Captioning

2021-07-28 · Ahmed Elhagry, Karima Kadaoui

Image Captioning is a task that combines computer vision and natural language processing, where it aims to generate descriptive legends for images. It is a two-fold process relying on accurate image understanding and cor…

Caption GenerationDescriptiveImage CaptioningMeta-Learning

mOSCAR: A Large-scale Multilingual and Multimodal Document-level Corpus

2024-06-13 · Matthieu Futeral, Armel Zebaze, Pedro Ortiz Suarez, Julien Abadji 외

Multimodal Large Language Models (mLLMs) are trained on a large amount of text-image data. While most mLLMs are trained on caption-like data only, Alayrac et al. [2022] showed that additionally training them on interleav…

Few-Shot LearningIn-Context Learning

Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks

2020-04-13 · ECCV 2020 8 · Xiujun Li, Xi Yin, Chunyuan Li, Pengchuan Zhang 외

Large-scale pre-training methods of learning cross-modal representations on image-text pairs are becoming popular for vision-language tasks. While existing methods simply concatenate image region features and text featur…

Cross-Modal RetrievalImage CaptioningImage RetrievalImage-text matching+2