Hallucinated Humans as the Hidden Context for Labeling 3D Scenes

By Yun Jiang, Hema Swetha Koppula, Ashutosh Saxena. 2013

139 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, 3D Vision & Pose

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

In 3D Vision & Pose

Citations in the corpus

Learning Trajectory Preferences for Manipulators via Iterative Improvement (2013, background): “In previous work, such relations were considered in the context of scene understanding [10, 12].”
Semantically-enriched 3D models for common-sense knowledge (2015, neutral): “• How big are apples?”
Anticipating Human Activities Using Object Affordances for Reactive Robotic Response (2013, background): “Few recent works explore the physical aspects of affordances based on human interactions [5], [73], [74], [75], [76].”
From Lifestyle Vlogs to Everyday Interactions (2017, background): “This area has been extensively studied in vision, typically aiming to infer affordances in still images [12, 14, 32, 47, 46], understand scenes by observing them over time [9, 6], or use them as a building block for scene understanding [20].”
Ieee Transactions on Pattern Analysis and Machine Intelligence 1 3d Reasoning from Blocks to Stability (background): “…that integrating depth with color information improves the performances of many vision tasks, such as segmentation (in [7]), contour detection (in [24]), object recognition (in [25], [26], and [27]), scene labeling (in [28], [29], [30] and [31]), and activity detection (in [32], [33] and [34]).”
Resolving 3D Human Pose Ambiguities With 3D Scene Constraints (2019, background): “Another direction models human-scene interactions by hallucinating synthetic people either in real RGB images of scenes [29] for general scene labeling, or in synthetic 3D scenes to learn affordances [21, 33] or 3D object layout in the scene [30], or in real 3D scans of scenes [16] for scene synthes”
Tell me Dave: Context-sensitive grounding of natural language to manipulation instructions (2014, background): “In the area of computer vision, some works have considered relating phrases and attributes to images and videos [39, 15, 26, 25, 21, 50].”
Scene Understanding by Reasoning Stability and Safety (2015, background): “Jiang et al. (2013) and Jiang and Saxena (2013) proposed scene labeling algorithms by considering humans as the hidden context.”
PiGraphs (2016, background): “Another line of work encodes human interactions from RGB-D data to hallucinate plausible human poses for labeling objects or for learning priors on the spatial distribution of objects with respect to people [Jiang et al. 2012; Jiang et al. 2013; Jiang and Saxena 2013].”
Detecting potential falling objects by inferring human action and natural disturbance (2014, background): “Jiang [25] [26] proposed scene labeling algorithms by considering humans as the hidden context.”
Robust real-time visual odometry for dense RGB-D mapping (2013, methodology): “Since the release of KinectFusion in 2011 a number of derived works have followed, notably our own system Kintinuous [1], the commercial ReconstructMe product [12], the KinFu Large Scale open source PCL project [13] and the Moving Volume KinectFusion work of Roth and Vona [14].”
SceneGrok (2014, background): “…new; much prior work has targeted this domain [Gibson 1977; Gupta et al. 2011; Pandey and Alami 2012; Fouhey et al. 2012; Koppula et al. 2013; Koppula and Saxena 2013; ACM Transactions on Graphics, Vol. 33, No. 6, Article 212, Publication Date: November 2014 Jiang et al. 2013; Wei et al. 2013a].”
Reasoning about Object Affordances in a Knowledge Base Representation (2014, background): “[20] represent affordances by hallucinating humans as the hidden context.”
Dark, Beyond Deep: A Paradigm Shift to Cognitive AI with Humanlike Common Sense (2020, methodology): “proposed methods that use human context to learn object arrangement [287] and object labeling [110].”