Weakly Supervised Learning of Interactions between Humans and Objects

By Alessandro Prest, Cordelia Schmid, Vittorio Ferrari. 2012

243 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

Object-Proposal Evaluation Protocol is ‘Gameable’ (2015, background): “Object proposal algorithms have quickly become the defacto pre-processing step in a number of vision pipelines – object detection [12–21], segmentation [22–26], object discovery [27–30], weakly supervised learning of object-object interactions [31, 32], content aware media retargeting [33], action r”
The Open Images Dataset V4 (2018, background): “, 2017b), or focusing on humanobject relations (Gupta et al., 2009; Yao and Fei-Fei, 2010; Prest et al., 2012).”
Contextual Action Recognition with R*CNN (2015, background): “[26] learn humanobject interactions using only action labels.”
Weakly-Supervised Learning of Visual Relations (2017, background): “This task was studied for the special case of human-object interactions [8, 9, 17, 38, 39, 48, 49, 50], where the triplet is in the form ( person, action, object ) .”
Visual Semantic Role Labeling (2015, background): “[28] collect and analyze the Sports, People Playing Musi-”
Anticipating Human Activities Using Object Affordances for Reactive Robotic Response (2013, methodology): “These methods use an intermediate level of representation such as the presence or absence of semantic concepts (e.g., scene types, actions, objects, etc.) in order to generalize to unseen instances.”
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].”
On Recognizing Actions in Still Images via Multiple Features (2012, background): “[4] also propose weakly supervised learning of human-object interactions.”
A similarity measure for analyzing human activities using human-object interaction context (2014, methodology): “human action results in achieving considerable improvements [5, 8-10], especially in the case of human action recognition using still images, where the motion cue is not available [5, 6].”
Dynamic Eye Movement Datasets and Learnt Saliency Models for Visual Action Recognition (2012, background): “Interestingly, this supports recent computer vision strategies based on object detectors for action recognition[7, 9, 8, 26].”
Learning semantic relationships for better action retrieval in images (2015, methodology): “Action recognition Action recognition in images has been widely studied in different works such as [15, 27, 32, 41, 42].”
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].”
Action Recognition with Exemplar Based 2.5D Graph Matching (2012, background): “The idea of using human poses for action recognition has been studied in some previous work which either detect local pose features [4, 6] or model the spatial configuration between human body parts and objects [2, 3, 7, 8].”
Human action recognition by learning bases of action attributes and parts (2011, background): “There is some recent work which uses objects [10, 27, 5, 22] interacting with the person or human poses [25, 20] to build action classifiers.”
Advanced Deep-Learning Techniques for Salient and Category-Specific Object Detection: A Survey (2018, background): “To alleviate this problem, weakly supervised object detection approaches [3], [13], [76], [99] have received wide interest in recent years.”