paper-with-me

홈 › Papers

Sequential Person Recognition in Photo Albums with a Recurrent Network

2016-11-30 · CVPR 2017 7 · Yao Li, Guosheng Lin, Bohan Zhuang, Lingqiao Liu, Chunhua Shen, Anton Van Den Hengel

Recognizing the identities of people in everyday photos is still a very challenging problem for machine vision, due to non-frontal faces, changes in clothing, location, lighting and similar. Recent studies have shown that rich relational information between people in the same photo can help in recognizing their identities. In this work, we propose to model the relational information between people as a sequence prediction task. At the core of our work is a novel recurrent network architecture, in which relational information between instances' labels and appearance are modeled jointly. In addition to relational cues, scene context is incorporated in our sequence prediction model with no additional cost. In this sense, our approach is a unified framework for modeling both contextual cues and visual appearance of person instances. Our model is trained end-to-end with a sequence of annotated instances in a photo as inputs, and a sequence of corresponding labels as targets. We demonstrate that this simple but elegant formulation achieves state-of-the-art performance on the newly released People In Photo Albums (PIPA) dataset.

📄 PDF Abstract BibTeX arXiv:1611.09967

Code (0)

등록된 구현이 없습니다.

Tasks

Person Recognition

Similar Papers 제목 키워드 기반

PETA: Photo Albums Event Recognition using Transformers Attention

2021-09-26 · Tamar Glaser, Emanuel Ben-Baruch, Gilad Sharir, Nadav Zamir 외

In recent years the amounts of personal photos captured increased significantly, giving rise to new challenges in multi-image understanding and high-level image understanding. Event recognition in personal photo albums p…

Zoom-RNN: A Novel Method for Person Recognition Using Recurrent Neural Networks

2018-09-24 · Sina Mokhtarzadeh Azar, Sajjad Azami, Mina Ghadimi Atigh, Mohammad Javadi 외

The overwhelming popularity of social media has resulted in bulk amounts of personal photos being uploaded to the internet every day. Since these photos are taken in unconstrained settings, recognizing the identities of …

Person Recognition

Beyond Frontal Faces: Improving Person Recognition Using Multiple Cues

2015-01-23 · CVPR 2015 6 · Ning Zhang, Manohar Paluri, Yaniv Taigman, Rob Fergus 외

We explore the task of recognizing peoples' identities in photo albums in an unconstrained setting. To facilitate this, we introduce the new People In Photo Albums (PIPA) dataset, consisting of over 60000 instances of 20…

Person Recognition

A Multi-Level Contextual Model For Person Recognition in Photo Albums

2016-06-01 · CVPR 2016 6 · Haoxiang Li, Jonathan Brandt, Zhe Lin, Xiaohui Shen 외

In this work, we present a new framework for person recognition in photo albums that exploits contextual cues at multiple levels, spanning individual persons, individual photos, and photo groups. Through experiments, we…

Person Recognition

Focal Visual-Text Attention for Memex Question Answering

2018-12-14 · IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 2018 12 · Junwei Liang, Lu Jiang, Liangliang Cao, Yannis Kalantidis 외

Recent insights on language and vision with neural networks have been successfully applied to simple single-image visual question answering. However, to tackle real-life question answering problems on multimedia collecti…

Memex Question AnsweringQuestion AnsweringVisual Question AnsweringVisual Question Answering (VQA)