Observing Human-Object Interactions: Using Spatial and Functional Compatibility for Recognition

By Abhinav Kumar Gupta, Aniruddha Kembhavi, Larry S. Davis. 2009

551 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

Learning Visual Features from Large Weakly Supervised Data (2015, methodology): “…a range of computer-vision tasks: (1) the MIT Indoor dataset [38], (2) the MIT SUN dataset [55], (3) the Stanford 40 Actions dataset [57], (4) the Oxford Flowers dataset [33], (5) the Sports dataset [17], (6) the ImageNet ILSVRC 2014 dataset [42], and (7) the Pascal VOC 2007 dataset [11].”
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].”
RGB-D-based action recognition datasets: A survey (2016, background): “Human–object interactivity is another important characteristic of a dataset because some algorithms may benefit from the objects that the actors interact with [60,61,22].”
Learning human activities and object affordances from RGB-D videos (2012, background): “Only recently, some works have shown that modeling mutual context is beneficial (Gupta et al., 2009; Yao and Fei-Fei, 2010).”
Modeling Temporal Dynamics and Spatial Configurations of Actions Using Two-Stream Recurrent Neural Networks (2017, background): “Human action recognition [2] has become an active area in computer vision and there are many important research problems, such as event recognition [23], group based activities recognition [27], human object interactions [15] and activities in egocentric videos [29, 11].”
Structural-RNN: Deep Learning on Spatio-Temporal Graphs (2015, background): “Examples include human activity recognition and segmentation from videos [50, 47, 62, 60, 8, 25, 37, 36], context-rich human-object interactions [39, 33, 29, 20, 30], modeling human motion [14, 57, 56] etc.”
Visual Relationship Detection with Language Priors (2016, background): “There have been numerous efforts in human-object interaction [20,21,22] and action recognition [23] to learn discriminative models that distinguish between relationships where object1 is a human ( e.”
Weakly-Supervised Learning of Visual Relations (2017, background): “This task was studied for the special case of humanobject interactions [8, 9, 17, 38, 39, 48, 49, 50], where the triplet is in the form (person, action, object).”
Visual Semantic Role Labeling (2015, methodology): “While these methods signiﬁcantly boost performance over not using human object context and produce localization for the object of interaction as learned by their model, they do not quantify performance at the joint task of detecting people, classifying what they are doing and localizing the object…”
Detecting and Recognizing Human-Object Interactions (2017, background): “The task of recognizing human-object interactions [13, 33, 6, 14, 5] can be represented as detecting 〈human, verb, object〉 triplets and is of particular interest in applications and in research.”
Anticipating Human Activities Using Object Affordances for Reactive Robotic Response (2013, methodology): “However, these methods only address detection over small time periods, where temporal segmentation (i.e., knowledge of the spatio-temporal structure) is not an issue.”
Asynchronous Temporal Fields for Action Recognition (2016, background): “Understanding activities with emphasis on objects has been a particularly fruitful direction [25, 36, 9, 34, 54].”
Every Picture Tells a Story: Generating Sentences from Images (2010, unknown): “Gupta and Davis show that respecting relations between objects and actions improve recognition of each [10,11].”
Learning to Recognize Daily Actions Using Gaze (2012, methodology): “[9] follow a Bayesian approach using a likelihood model based on hand trajectories to analyze humanobject interactions.”
Modeling mutual context of object and human pose in human-object interaction activities (2010, methodology): “For simplicity, we assume that only one object is involved in each activity.”
HICO: A Benchmark for Recognizing Human-Object Interactions in Images (2015, background): “detecting human body parts) by deriving feature representations based on human poses [11, 38, 21, 30, 32, 31], whereas others focus more on spatial relations between humans and objects [34, 33, 23, 9, 5, 4].”
On Recognizing Actions in Still Images via Multiple Features (2012, background): “Object-person interactions are explored in other works such as [2, 3, 13, 14].”