TriCoS: A Tri-level Class-Discriminative Co-segmentation Method for Image Classification
By Yuning Chai, Esa Rahtu, Victor S. Lempitsky, Luc Van Gool, Andrew Zisserman. 2012
112 citations recorded by the source corpus.
Subfields: Computer Vision and Pattern Recognition, Media Technology
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
- Trevor Darrell
- Xiaogang Wang
- Li Fei-Fei
- Andrew Zisserman
- Ming-Hsuan Yang
- Jitendra Malik
In Media Technology
- Li Fei-Fei
- Yu Qiao
- Vittorio Ferrari
- Tinne Tuytelaars
- Andrew Zisserman
- Arnold M. W. Smeulders
- Xiaoou Tang
- Victor S. Lempitsky
Citations in the corpus
- ImageNet Auto-Annotation with Segmentation Propagation (2014, background): “Similar to [14,15,8], we share appearance models when segmenting many images of the same class.”
- Local Alignments for Fine-Grained Categorization (2014, methodology): “Locality-constrained linear coding in Yao et al. (2011), bag-of-words in Zhang et al. (2012) and Fisher vectors in Sanchez et al. (2011); Chai et al. (2012, 2013) were shown to describe fine-grained categories accurately.”
- Pairwise Rotation Invariant Co-Occurrence Local Binary Pattern (2014, background): “[57]), which significantly exceeded the results of using each of them alone.”
- Learning Discriminative Part Detectors for Image Classification and Cosegmentation (2013, unknown): “Recently, discriminative cosegmentation [8] has successfully been applied to image classification.”
- Nonparametric Part Transfer for Fine-Grained Recognition (2014, methodology): “[7] replace the histogram with powerful Fisher vectors.”
- Which Looks Like Which: Exploring Inter-class Relationships in Fine-Grained Visual Categorization (2014, methodology): “We compare with a multiple kernel learning (MKL) method [11], a bag-of-features approach using the LLC [36], a randomization based method [42], a multi-cue representation [26], the TriCoS[13], the UTL [40], the KDES [10] and two recent approaches [1,14].”
- Beyond pixels: A comprehensive survey from bottom-up to semantic image segmentation and cosegmentation (2015, methodology): “Later, a TriCos model [140] containing three levels were further proposed, including image level (GrabCut), dataset-level, and category level, which outperforms the bilevel model.”
- Fine-Grained Crowdsourcing for Fine-Grained Recognition (2013, background): “Our work shares the same end goal as existing work on fine grained recognition [16, 6, 15, 25, 19, 37, 36], but our approach is more aligned with the general line of research that places humans in the loop [20, 11, 22, 29, 9, 5, 24, 23, Figure 2.”
- Learning Features and Parts for Fine-Grained Recognition (2014, methodology): “In addition to the approaches outlined above, segmentation has also been found to be particularly useful [21], [30]–[32] in fine-grained recognition tasks.”
- Leveraging the Wisdom of the Crowd for Fine-Grained Recognition (2016, background): “Examples include distinguishing different breeds of dogs, species of birds, models of cars, and categories of mushrooms.”
- Fine-grained visual categorization via multi-stage metric learning (2014, background): “A recent development is to train the convolutional neural network (CNN) [18] on a large-scale image dataset (e.g., ImageNet [26]) and then use the trained model to extract features [12].”
- Symbiotic Segmentation and Part Localization for Fine-Grained Categorization (2013, methodology): “However, [10, 22, 24] demonstrated that at the subordinate category level, the background is seldom discriminative and it is beneficial to segment out the foreground and to discard the visual information in the background.”