mlsanityData to 14 Oct 2026

ImageSubject: A Large-scale Dataset for Subject Detection

arXiv 2201.03101 ↗First posted 9 Jan 2022cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Main subjects usually exist in the images or videos, as they are the objects that the photographer wants to highlight. Human viewers can easily identify them but algorithms often confuse them with other objects. Detecting the main subjects is an important technique to help machines understand the content of images and videos. We present a new dataset with the goal of training models to understand the layout of the objects and the context of the image then to find the main subjects among them. This is achieved in three aspects. By gathering images from movie shots created by directors with professional shooting skills, we collect the dataset with strong diversity, specifically, it contains 107,700 images from 21,540 movie shots. We labeled them with the bounding box labels for two classes: subject and non-subject foreground object. We present a detailed analysis of the dataset and compare the task with saliency detection and object detection. ImageSubject is the first dataset that tries to localize the subject in an image that the photographer wants to highlight. Moreover, we find the transformer-based detection model offers the best result among other popular model architectures. Finally, we discuss the potential applications and conclude with the importance of the dataset.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 21 of its 43 references that are in the map. First posted on arXiv 9 Jan 2022.

Builds on

21 of 43 references.

References · 21

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  5. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  6. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  7. 2020End-to-End Object Detection with Transformerscited by 7,414
  8. 2017Mask R-CNNcited by 7,277
  9. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,852
  10. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,422
  11. 2015SSD: Single Shot MultiBox Detectorcited by 3,130
  12. 2018Self-Attention Generative Adversarial Networkscited by 809
9 more
  1. 2020Sparse R-CNN: End-to-End Object Detection with Learnable Proposalscited by 495
  2. 2017Relation Networks for Object Detectioncited by 305
  3. 2014The Secrets of Salient Object Segmentationcited by 200
  4. 2015Visual Saliency Based on Multiscale Deep Featurescited by 185
  5. 2020Memory Enhanced Global-Local Aggregation for Video Object Detectioncited by 128
  6. 2016Predicting Human Eye Fixations via an LSTM-based Saliency Attentive Modelcited by 91
  7. 2019Relation Distillation Networks for Video Object Detectioncited by 77
  8. 2018Salient Objects in Clutter: Bringing Salient Object Detection to the Foregroundcited by 47
  9. 2020A Unified Framework for Shot Type Classification Based on Subject Centric Lenscited by 44

Built on by

Not cited yet.