paper-with-me

홈 › Papers

GLIMPSE : Real-Time Text Recognition and Contextual Understanding for VQA in Wearables

2026-02-13 · Akhil Ramachandran, Ankit Arun, Ashish Shenoy, Abhay Harpale, Srihari Jayakumar, Debojeet Chatterjee, Mohsen Moslehpour, Pierce Chuang, Yichao Lu, Vikas Bhardwaj, Peyman Heidari arxiv

Video Large Language Models (Video LLMs) have shown remarkable progress in understanding and reasoning about visual content, particularly in tasks involving text recognition and text-based visual question answering (Text VQA). However, deploying Text VQA on wearable devices faces a fundamental tension: text recognition requires high-resolution video, but streaming high-quality video drains battery and causes thermal throttling. Moreover, existing models struggle to maintain coherent temporal context when processing text across multiple frames in real-time streams. We observe that text recognition and visual reasoning have asymmetric resolution requirements - OCR needs fine detail while scene understanding tolerates coarse features. We exploit this asymmetry with a hybrid architecture that performs selective high-resolution OCR on-device while streaming low-resolution video for visual context. On a benchmark of text-based VQA samples across five task categories, our system achieves 72% accuracy at 0.49x the power consumption of full-resolution streaming, enabling sustained VQA sessions on resource-constrained wearables without sacrificing text understanding quality.

📄 PDF Abstract BibTeX arXiv:2602.13479

Code (0)

등록된 구현이 없습니다.

Tasks

Visual Question AnsweringScene UnderstandingVisual Reasoning

Similar Papers 제목 키워드 기반

Glimpse Clouds: Human Activity Recognition from Unstructured Feature Points

2018-02-22 · CVPR 2018 6 · Fabien Baradel, Christian Wolf, Julien Mille, Graham W. Taylor

We propose a method for human activity recognition from RGB data that does not rely on any pose information during test time and does not explicitly calculate pose information internally. Instead, a visual attention modu…

Action RecognitionActivity PredictionActivity RecognitionHuman Activity Recognition+2

RobustScanner: Dynamically Enhancing Positional Clues for Robust Text Recognition

2020-07-15 · ECCV 2020 8 · Xiaoyu Yue, Zhanghui Kuang, Chenhao Lin, Hongbin Sun 외

The attention-based encoder-decoder framework has recently achieved impressive results for scene text recognition, and many variants have emerged with improvements in recognition quality. However, it performs poorly on c…

DecoderIrregular Text RecognitionPositionScene Text Recognition

Multi-Glimpse LSTM with Color-Depth Feature Fusion for Human Detection

2017-11-03 · Hengduo Li, Jun Liu, Guyue Zhang, Yuan Gao 외

With the development of depth cameras such as Kinect and Intel Realsense, RGB-D based human detection receives continuous research attention due to its usage in a variety of applications. In this paper, we propose a new …

Human Detection

Recurrent Attention Models with Object-centric Capsule Representation for Multi-object Recognition

2021-10-11 · Hossein Adeli, Seoyoung Ahn, Gregory Zelinsky

The visual system processes a scene using a sequence of selective glimpses, each driven by spatial and object-based attention. These glimpses reflect what is relevant to the ongoing task and are selected through recurren…

DecoderObjectObject Recognition

GliTr: Glimpse Transformers with Spatiotemporal Consistency for Online Action Prediction

2022-10-24 · Samrudhdhi B Rangrej, Kevin J Liang, Tal Hassner, James J Clark

Many online action prediction models observe complete frames to locate and attend to informative subregions in the frames called glimpses and recognize an ongoing action based on global and local information. However, in…

Action Recognition