Computational Vision and Active Perception

Citations in the corpus

• Joint Discovery of Object States and Manipulation Actions (2017, background): “Modeling co-occurrences of objects and actions have shown benefits for recognizing actions in [11, 19, 26, 35, 47].”
• A self-organizing neural network architecture for learning human-object interactions (2017, background): “Results from other approaches on recognition of human-object interactions and on the learning of object affordances [36, 23] have shown that tracking objects’ positions and spatial re-”
• Learning human activities and object affordances from RGB-D videos (2012, methodology): “Kjellström et al. (2011) used a factorial CRF to simultaneously segment and classify human hand actions, as well as classify the object affordances involved in the activity from 2D videos.”
• Anticipating Human Activities Using Object Affordances for Reactive Robotic Response (2013, background): “These works take a recognition based approach to identify the semantic affordance labels [70], [71], [72].”
• Affordance detection of tool parts from geometric features (2015, methodology): “From the computer vision community, [19] classify human hand actions in context of the objects being used, Grabner et al.”
• Joint Hand Motion and Interaction Hotspots Prediction from Egocentric Videos (2022, background): “Object affordance grounding [19,21,42,60,69,74] refers to locating where the interaction occurs on an object.”
• Interactive Perception: Leveraging Action in Perception and Perception in Action (2016, background): “Approaches that assume deterministic dynamics are labeled (DDM), stochastic dynamics (SDM), deterministic observations (DOM), stochastic observations (SOM) and approaches that estimate uncertainty are labeled (EU).”
• Reasoning about Object Affordances in a Knowledge Base Representation (2014, background): “growing interest in recognizing object and scene affordances (some call “functionalities”) [21,17,15,37,20,22,19].”
• ShapeStacks: Learning Vision-Based Physical Intuition for Generalised Object Stacking (2018, background): “Such object affordances are typically pre-defined given knowledge of the task at hand [3,4].”
• Holistic++ Scene Understanding: Single-View 3D Holistic Scene Parsing and Human Pose Estimation With Human-Object Interaction and Physical Commonsense (2019, background): “In robotics and computer vision, prior work has exploited human-object relations in event, object, and scene modeling, but most work focuses on human-object relation detection in images [5, 30, 25, 21], probabilistic modeling from multiple data sources [45, 33, 13], and snapshots generation or scene”
• AffordanceNet: An End-to-End Deep Learning Approach for Object Affordance Detection (2017, methodology): “In [14], the authors introduced a method to detect object affordances via object-action interactions from human demonstrations.”
• First Person Action-Object Detection with EgoNet (2016, background): “ our defined concept of action-objects overlaps with several concepts from prior work such as object-action complexes (OAC) [26], handled-objects [44, 6], objects-in-action [16], or object affordances [24]. However, we point out that these prior methods typically focus exclusively on physically manip”
• Human Activity Learning using Object Affordances from RGB-D Videos (2012, methodology): “[20] used a Factorial CRF to simultaneously segment and classify human hand actions, as well as classify the object affordances involved in the activity from 2D videos.”
• Functional categorization of objects using real-time markerless motion capture (2011, background): “As shown in the literature, for applications like autonomous robotics, a categorization based on functional similarity is more taskrelevant [29, 27, 16 ].”