COCO Attributes: Attributes for People, Animals, and Objects
By Genevieve Patterson, James Hays. 2016
110 citations recorded by the source corpus.
Subfields: Artificial Intelligence, 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 Artificial Intelligence
- Abhinav Kumar Gupta
- Antonio Torralba
- Mohit Bansal
- Trevor Darrell
- Sergey Levine
- Jianfeng Gao
- Andrew Zisserman
- Martial Hebert
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Abhinav Kumar Gupta
- Xiaogang Wang
- Dacheng Tao
- Trevor Darrell
- Bernt Schiele
- Jitendra Malik
- Antonio Torralba
In Evaluation & Benchmarks
- Bolei Zhou
- Antonio Torralba
- Abhinav Kumar Gupta
- Sanja Fidler
- Hang Zhao
- Nuno Vasconcelos
- Carl Vondrick
- Martial Hebert
Citations in the corpus
- Semantic Understanding of Scenes Through the ADE20K Dataset (2016, methodology): “Recently COCO stuff dataset [4] provides additional stuff segmentation complementary to the 80 object categories in COCO dataset, while COCO attributes dataset [26] annotates attributes for some objects in COCO dataset.”
- RESOUND: Towards Action Recognition Without Representation Bias (2018, methodology): “The networks varied on how they were trained: φ object was trained on the 1,000 object classes of ImageNet [4], φ scene on the 365 scene classes of the Places365 scene classification dataset [25], and φ people on the 204 classes of people attributes of the COCO-attributes dataset [12].”
- Doubly Right Object Recognition: A Why Prompt for Visual Rationales (2022, background): “Visual Attributes Several works have studied visual attributes in images [17, 25, 27, 35, 36, 39, 63].”
- From Red Wine to Red Tomato: Composition with Context (2017, background): “We study compositionality in visual recognition in the context of two well known problems - objects and attributes [13, 28, 29, 46, 48], and subject-verb-object (SVO) phrases [24, 39, 53, 57].”
- Zero Shot Detection (2018, methodology): “While an attribute dataset for MS COCO has been published in [45], we could not utilize it for two reasons: (1) The dataset only labels 29 out of the 80 object classes.”
- Context-Aware Emotion Recognition Networks (2019, unknown): “MS-COCO database [28] has been recently annotated with object attributes, including some emotion categories for human, but the attributes are not intended to be exhaustive for emotion recognition, and not all people are annotated with emotion attributes.”