Cross-Caption Coreference Resolution for Automatic Image Understanding

14 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.

From image descriptions to visual denotations: New similarity metrics for semantic inference over event descriptions (2014, methodology): “To do this, we use the heuristic cross-caption coreference algo-rithm of Hodosh et al. (2010) to identify coreferent NP chunks among the original ﬁve captions of each image.”
Unsupervised Visual-Linguistic Reference Resolution in Instructional Videos (2017, background): “On the other hand, coreference resolution in texts aligned with the image/video has been shown to be beneficial to the task of human naming [47], image understanding [15], and 3D scene understanding [27].”
Automatic Caption Generation for News Images (2013, background): “The datasets created by Farhadi et al. [16] and Hodosh et al. [40] contain image descriptions; however, as mentioned above, they are limited to specific object categories and scene types (e.g., actions).”
Linking People in Videos with "Their" Names Using Coreference Resolution (2014, unknown): “[20] and more recently, Kong et al.”
Finding "It": Weakly-Supervised Reference-Aware Visual Grounding in Instructional Videos (2018, background): “Recent work has used reference for improving visual tasks, such as image and 3D scene understanding [14, 24], and actor recognition [41, 44].”