Microsoft COCO: Common Objects in Context
By Tsung-Yi Lin, Michael Maire, Serge J. Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Doll'ar, C. Lawrence Zitnick. 2014
54,126 citations recorded by the source corpus.
We present a new dataset with the goal of advancing the state-of-the-art in object recognition by placing the question of object recognition in the context of the broader question of scene understanding. This is achieved by gathering images of complex everyday scenes containing common objects in their natural context. Objects are labeled using per-instance segmentations to aid in precise object localization. Our dataset contains photos of 91 objects types that would be easily recognizable by a 4 year old. With a total of 2.5 million labeled instances in 328k images, the creation of our dataset drew upon extensive crowd worker involvement via novel user interfaces for category detection, instance spotting and instance segmentation. We present a detailed statistical analysis of the dataset in comparison to PASCAL, ImageNet, and SUN. Finally, we provide baseline performance analysis for bounding box and segmentation detection results using a Deformable Parts Model.
Subfields: Computer Vision and Pattern Recognition, Evaluation & Benchmarks
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Dacheng Tao
- Ming-Hsuan Yang
- Trevor Darrell
- Xiaogang Wang
- Jitendra Malik
- Andrew Zisserman
- Yi Yang
In Evaluation & Benchmarks
- Mohit Bansal
- Luc Van Gool
- Jitendra Malik
- Trevor Darrell
- Yejin Choi
- Jianfeng Gao
- Vladlen Koltun
- Li Fei-Fei
Citations in the corpus
- Layer Normalization (2016, methodology): “Unless otherwise noted, the default initialization of layer normalization is to set the adaptive gains to 1 and the biases to 0 in the experiments.”
- An efficient framework for learning sentence representations (2018, methodology): “The MSCOCO dataset (Lin et al., 2014) has been traditionally used for this task. We use the train/val/test split proposed in Karpathy & Fei-Fei (2015). The training, validation and test sets respectively consist of 113,287, 5000, 5000 images, each annotated with 5 captions.”
- Skip-Thought Vectors (2015, methodology): “For this experiment, we use the Microsoft COCO dataset [35] which is the largest publicly available dataset of images with high-quality sentence descriptions.”
- Aligning Books and Movies: Towards Story-Like Visual Explanations by Watching Movies and Reading Books (2015, background): “Figure 6: CoCoBook: We generate a caption for a CoCo image via [13] and retrieve its best matched sentence (+ 2 before and after) from a large book corpus.”
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks (2015, methodology): “Region proposal methods typically rely on inexpensive features and economical inference schemes.”
- Object Detection via a Multi-region and Semantic Segmentation-Aware CNN Model (2015, background): “704 DEEP ENSEMBLE COCO VOC07+12, COCO [21] 0.”
- Object Detection Networks on Convolutional Feature Maps (2015, methodology): “Experimental Settings In this section we experiment on the more challenging MS COCO dataset [31] with 80 categories.”
- End-to-End Object Detection with Transformers (2020, methodology): “We evaluate DETR on one of the most popular object detection datasets, COCO [24], against a very competitive Faster R-CNN baseline [37].”
- Mask R-CNN (2017, methodology): “All instantiations of our model outperform baseline variants of previous state-of-the-art models.”
- Momentum Contrast for Unsupervised Visual Representation Learning (2019, methodology): “Next we compare MoCo with ImageNet supervised pre-training, transferred to various tasks including PASCAL VOC [18], COCO [42], etc .”
- UNITER: Learning UNiversal Image-TExt Representations (2019, methodology): “We construct our pre-training dataset based on four existing V+L datasets: COCO (Lin et al., 2014), Visual Genome (VG) (Krishna et al.”
- Can You Tell Me How to Get Past Sesame Street? Sentence-Level Pretraining Beyond Language Modeling (2018, methodology): “These include image-caption matching with MSCOCO (Lin et al., 2014), following Kiela et al. (2018); the small-to-medium-data textunderstanding tasks collected in NLI format by Poliak et al. (2018); ordinal common sense inference (Zhang et al., 2017); POS tagging on the Penn Treebank (Marcus et al.,…”