Interpreting multimodal referring expressions in real time

75 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

LILA: Language-Informed Latent Actions (2021, background): “Other work combines several modalities on top of language like gaze, gesture, and intonation to further help lift representations of human intent from language [58, 59].”
A Joint Speaker-Listener-Reinforcer Model for Referring Expressions (2016, background): “Recently, the research focus has shifted to more complex natural image datasets and has expanded to include the Referring Expression Comprehension task [13, 19, 31] as well as to real-world interactions with robotics [4, 3].”
Probabilistic Human Intent Recognition for Shared Autonomy in Assistive Robotics (2019, background): “Gestures, along with language referential expressions, are utilized for object inference in human-robot interactions [36].”
Robots That Use Language (2020, unknown): “(166) merged information from language and gesture to interpret multimodal referring expressions in real time using a filtering approach and a joint classification approach, respectively; an image from Matuszek et al.”