Image Parsing: Unifying Segmentation, Detection, and Recognition

By Zhuowen Tu, Xiangrong Chen, Alan L. Yuille, Song-Chun Zhu. 2003

644 citations recorded by the source corpus.

Subfields: 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 Computer Vision and Pattern Recognition

Citations in the corpus

UPSNet: A Unified Panoptic Segmentation Network (2019, background): “Notable ones include image parsing [33], scene parsing [33] and holistic scene understanding [36].”
Panoptic Feature Pyramid Networks (2019, background): “Panoptic segmentation: The joint task of thing and stuff segmentation has a rich history, including early work on scene parsing [51], image parsing [52], and holistic scene understanding [56].”
Panoptic Segmentation (2018, background): “The seminal work on image parsing [43] proposed a general bayesian framework to jointly model segmentation, detection, and recognition.”
OneFormer: One Transformer to Rule Universal Image Segmentation (2022, methodology): “The concept of universal image segmentation has existed for some time, starting with image and scene parsing [47, 48, 58], followed by panoptic segmentation as an effort to unify semantic and instance segmentation [29].”
K-Net: Towards Unified Image Segmentation (2021, background): “There are also pioneer attempts [19, 29, 50, 62] to joint the two segmentation tasks for more comprehensive scene understanding.”
Conditional Random Fields as Recurrent Neural Networks (2015, background): “Lack of such smoothness constraints can result in poor object delineation and small spurious regions in the segmentation output [31, 30, 14, 21].”
UberNet: Training a Universal Convolutional Neural Network for Low-, Mid-, and High-Level Vision Using Diverse Datasets and Limited Memory (2016, background): “Finally, the particular motivation for this research has been the interest in studying the synergy between different visual tasks (e.g. the long-standing problem of combining segmentation and recognition [9, 47, 50, 53, 68, 72, 99]), so this work can be understood as a ﬁrst step in this direction.”
On the Binding Problem in Artificial Neural Networks (2020, background): “The results that can be obtained by incorporating domain-specific knowledge are impressive (Zhao and Zhu, 2011; Del Pero et al., 2012, 2013; Tu et al., 2005; Tu and Zhu, 2002).”
Covariant Compositional Networks For Learning Graphs (2018, methodology): “At a conceptual level, this is similar to part-based modeling, which has a long history in machine learning (Fischler & Elschlager, 1973; Ohta et al., 1978; Tu et al., 2005; Felzenszwalb & Hutten-locher, 2005; Zhu & Mumford, 2006; Felzenszwalb et al., 2010).”
Joint Video and Text Parsing for Understanding Events and Answering Queries (2013, background): “In particular, spatial parsing identiﬁes the spatial compositional structures of objects and scenes [21], [6], [22], [23], [24], [25], [7], [8]; temporal parsing recognizes the temporal compositional structures of events [26], [27], [28], [29], [30], [31], [9], [32]; and causal parsing detects the…”
Character Recognition in Natural Images (2009, background): “For instance, (Tu et al., 2005) used insights from natural language processing and present a Markov chain framework for parsing images.”
Learning to Fuse Things and Stuff (2018, background): “[38] proposed a hierarchical probabilistic graphical model for scene parsing, disentangling objects, faces, textures, segments, and shapes.”
Approximate Bayesian Image Interpretation using Generative Probabilistic Graphics Programs (2013, background): “Generative models for a range of image parsing tasks are also being explored [17, 4, 18, 22, 20].”
DeeperLab: Single-Shot Image Parser (2019, background): “This paper addresses the problem of efficient whole image parsing (in short, image parsing) [1], also known as Panoptic Segmentation [2].”
GroupViT: Semantic Segmentation Emerges from Text Supervision (2022, background): “Beyond bottom-up inference, top-down feedback from recognition can also provide signals to perform better visual grouping [74, 93].”
MSeg: A Composite Dataset for Multi-Domain Semantic Segmentation (2020, background): “order to overcome this limitation, object detection and segmentation have been jointly studied under the term of image parsing [40].”
Pictorial structures revisited: People detection and articulated pose estimation (2009, methodology): “As has been argued before [22], using discriminatively learned detectors allows to reduce the search space for the generative model significantly thereby enabling not only efficient but also effective inference in challenging real world scenes.”
Recovering Surface Layout from an Image (2007, background): “Barbu and Zhu (2005) propose a model-driven segmentation with potential applications to image parsing (Tu et al., 2005).”