Discriminative Models for Multi-Class Object Layout

By Chaitanya Desai, Deva Ramanan, Charless C. Fowlkes. 2009

544 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

Panoptic Segmentation (2018, background): “To produce algorithm outputs for PS, we start from the non-overlapping instance segments from the NMS-like procedure described previously.”
Soft-NMS — Improving Object Detection with One Line of Code (2017, methodology): “A few learning-based meth ds have been p oposed as an al ernative to greedy NMS hich obtain good performance for object class det ctio [5, 26, 21].”
Not Using the Car to See the Sidewalk — Quantifying and Controlling the Effects of Context in Classification and Segmentation (2018, background): “Early approaches built explicit context models by incorporating co-occurrences [18] and spatial location statistics [6].”
Scene Graph Generation by Iterative Message Passing (2017, background): “Visual scene understanding often harnesses the statistical patterns of object co-occurrence [11, 22, 30, 35] as well as spatial layout [2, 9].”
DeepID-Net: multi-stage and deformable deep convolutional neural networks for object detection (2014, methodology): “information investigated in previous works includes regions surrounding objects [9, 12, 22], object-scene interaction [13], and the presence, location, orientation and size relationship among objects [3, 57, 58, 11, 41, 22, 49, 13, 61, 12, 59, 40, 10, 45, 51]. In this paper, we utilize the image cla”
End-to-end integration of a Convolutional Network, Deformable Parts Model and non-maximum suppression (2014, background): “This was the ﬁrst analysis of its provided the community valuable and concrete feedback about which speciﬁc problem to to improve overall performance: in this case, classifying local image patches into one of person-part categories.”
Action Genome: Actions As Compositions of Spatio-Temporal Scene Graphs (2019, background): “Given its versatile utility, the task of scene graph prediction has resulted in a series of publications [14, 30, 43, 46, 48, 49, 59, 77, 78, 85] that have explored reinforcement learning [49], structured prediction [16, 40, 70], utilizing object attributes [20, 61], sequential prediction [59], few-”
Top-down and bottom-up cues for scene text recognition (2012, methodology): “The structured label computed in [10] does not have any semantic meaning, and simply states that image contains certain objects.”
Iterative Visual Reasoning Beyond Convolutions (2018, background): “scene-level reasoning [46], attributes [13, 36], structured prediction [24, 9, 47], relationship graph [21, 31, 52]) has approached this problem from different angles, the breakthrough comes from the idea of feature learning with ConvNets [16].”
Building a Large-scale Multimodal Knowledge Base System for Answering Visual Queries (2015, background): “While MRFs have been widely used in a variety of vision tasks [9, 26, 27, 46], applying them to a large-scale KB framework means that we need to conquer the challenge of scalable learning and inference.”
Toward Holistic Scene Understanding: Feedback Enabled Cascaded Classification Models (2012, background): “Many works also model context to capture the local interactions between neighboring regions [35], [36], [37], objects [38], [39], [40], [41], [42], or both [43], [44], [45].”
Recent advances and trends in visual tracking: A review (2011, background): “In the detection, only stable, long-term and statistically signiﬁcant object-context relationships are easily incorporated, e.g., [10,11].”
What is an object? (2010, background): “Many state-of-the-art class-specific object detectors [5, 10, 15] are based on sliding windows.”
Optimized Pedestrian Detection for Multiple and Occluded People (2013, background): “Recently, several other papers have also explored the application of combinatorial optimization methods to the problem of object detection [8, 2, 18, 6, 21].”
Object localization in ImageNet by looking out of the window (2015, methodology): “Several works [7, 10] model the co-occurrence and spatial relations between object classes in the training data and use them to post-process the output of individual object class detectors.”
Relating Things and Stuff via ObjectProperty Interactions (2014, methodology): “It can not only model spatial relationship in 2D such as the ones learned and employed in the approach proposed by [16] , but also model behind and infront relationships given the depth property.”
Ieee Transactions on Pattern Analysis and Machine Intelligence 1 Relating Things and Stuff via Object Property Interactions (background): “Similarly, thing-thing relationships have been incorporated into a random field for jointly detecting multiple objects (Desai et al. [16]).”
Visual Translation Embedding Network for Visual Relation Detection (2017, background): “Therefore, we follow the separate model that learns subject, object, and predicate individually [7, 14, 36, 27].”