Ieee Transactions on Pattern Analysis and Machine Intelligence 1 Exploring Tiny Images: the Roles of Appearance and Contextual Information for Machine and Human Object Recognition
By Devi Parikh, C. Lawrence Zitnick, Tsuhan Chen
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
- Alan L. Yuille
- Bernt Schiele
- Liang-Chieh Chen
- Gong Cheng
- Chunhua Shen
- Li Fei-Fei
- Trevor Darrell
- Xiaodan Liang
Citations in the corpus
- Not Using the Car to See the Sidewalk — Quantifying and Controlling the Effects of Context in Classification and Segmentation (2018, background): “when dealing with difficult low resolution images [15, 1].”
- Building a Large-scale Multimodal Knowledge Base System for Answering Visual Queries (2015, methodology): “Joint Models in Vision A series of context models have leveraged MRFs in various vision tasks, such as image segmentation [16, 27, 33], object recognition [9, 26], object detection [46], pose and activity recognition [52] and other recognition tasks [20, 36].”
- Towards Large-Scale Small Object Detection: Survey and Benchmarks (2022, background): “The contextual information is of critical importance not only in visual systems of human [120], [124], but also in scene understanding tasks such as object recognition [126], semantic segmentation [127] and instance segmentation [128], etc .”
- The Role of Context for Object Detection and Semantic Segmentation in the Wild (2014, background): “[27] showed that context is an tree sky”
- Building a Large-scale Multimodal Knowledge Base for Visual Question Answering (2015, background): “Joint Models in Vision A series of context models have leveraged MRFs in various vision tasks, such as image segmentation [20, 24], object recognition [4, 19], object detection [33], pose and activity recognition [36] and other recognition tasks [13, 27].”
- Human vs. Computer in Scene and Object Recognition (2014, unknown): “Several previous studies, under the names of humans in the loop, human debugging, finding weak links (and often using Amazon Mechanical Turk) [27, 26, 36, 28, 34], have used humans to estimate the relative strengths and weaknesses of different algorithm components (e.g., [18, 36]).”