Leveraging the Wisdom of the Crowd for Fine-Grained Recognition
By Jia Deng, Jonathan Krause, Michael Stark, Li Fei-Fei. 2016
54 citations recorded by the source corpus.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Dacheng Tao
- Trevor Darrell
- Xiaogang Wang
- Devi Parikh
- Jitendra Malik
- Cordelia Schmid
- Ming-Hsuan Yang
Citations in the corpus
- Global-and-local attention networks for visual recognition (2018, background): “Previous work has shown that it is possible to augment vision systems with human perceptual judgments on difficult problems including face recognition and localization [23–25], bird categorization [26], action recognition [27], and object detection and segmentation [28–31].”
- Teaching Categories to Human Learners with Visual Explanations (2018, methodology): “[8], but present an interesting avenue for future human-in-the-loop explanation generation.”
- Human Attention in Visual Question Answering: Do Humans and Deep Networks look at the same regions? (2016, background): “(Jia Deng and Jonathan Krause and Li Fei-Fei, 2013; Deng et al., 2015) leverage crowdsourcing to help computers select discriminative features for fine-grained recognition.”
- Crowdsourcing in Computer Vision (2016, unknown): “Deza and Parikh [2015] model the popularity or “virality” of images, and conduct a study to determine how well humans can predict if a photograph will be popular, by having 20 annotators judge each image. Peng et al. [2015] collect a dataset of emotions evoked by images.”
- Fine-Grained Image Analysis With Deep Learning: A Survey (2021, unknown): “tures [167] for fine-grained recognition.”
- Fully Automated Deep Learning System for Bone Age Assessment (2017, background): “Subcategory recognition tasks are known to be more challenging compared to basic level recognition as less data and fewer discriminative features are available [17].”