Linking People in Videos with "Their" Names Using Coreference Resolution

By Vignesh Ramanathan, Armand Joulin, Percy Liang, Li Fei-Fei. 2014

105 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Information Extraction

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

1. Luc Van Gool
2. Andrew Zisserman
3. Trevor Darrell
4. Dacheng Tao
5. Cordelia Schmid
6. Li Fei-Fei
7. Xiaogang Wang
8. Bernt Schiele

In Information Extraction

1. Ivan Laptev
2. Li Fei-Fei
3. Zhiwu Lu
4. Josef Sivic
5. Dahua Lin
6. Julia Hockenmaier
7. Marcus Rohrbach
8. Byoung-Tak Zhang

Citations in the corpus

• End-to-End Learning of Visual Representations From Uncurated Instructional Videos (2019, neutral): “Multiple instance learning methods have been employed in many weakly-supervised video understanding problems including: person recognition in movies using scripts [12, 50, 61], anomaly detection [70], weakly supervised action classification [47, 68] and localization [17, 22, 82], co-reference resolu”
• Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models (2015, background): “latively rare in this dataset. Therefore, unlike in standard coreference resolution in running text (Soon et al. 2001), which can be beneficial for identifying all mentions of people in movie scripts (Ramanathan et al. 2014), we ignore anaphoric references between pronouns and their antecedents and f”
• A dataset for Movie Description (2015, background): “Their corpus is based on the original sources to create the DVS and contains different kinds of artifacts not present in actual description, such as dialogs and production notes.”
• Connectionist Temporal Modeling for Weakly Supervised Action Labeling (2016, background): “Our work is also related to recent progress on using instructional videos or movie scripts [2,4,9,25,30,35,51] as supervision for video parsing.”
• Learning from Video and Text via Large-Scale Discriminative Clustering (2017, background): “This framework has shown promising results in weakly supervised and unsupervised computer vision tasks [1, 4, 5, 6, 16, 17, 30, 32].”
• 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].”
• Book2Movie: Aligning video scenes with book chapters (2015, background): “Fan transcripts with subtitles are emerging as the de facto standard in automatic person identification [6, 8, 19, 24] and action recognition [5, 12].”
• It ’ s in the bag : Stronger supervision for automated face labelling (2015, background): “This topic has received plenty of attention in the community and papers have investigated the problem under various assumptions on the available information [2, 3, 5, 4, 6, 8, 9, 12, 17, 18, 20, 22, 24].”
• Visual Coreference Resolution in Visual Dialog using Neural Module Networks (2018, background): “For example, [37] links character mentions in TV show descriptions with their occurrence in the video, while [25] links text phrases to objects in a 3D scene.”
• Unsupervised Visual-Linguistic Reference Resolution in Instructional Videos (2017, background): “ing [6, 30], and joint vision and language domains [27, 32, 45, 47].”
• Recursive Visual Attention in Visual Dialog (2018, methodology): “Co-reference resolution has been used to improve visual comprehension in many tasks, such as visual grounding [13], action recognition [25, 26] and scene understanding [16].”
• Discover and Learn New Objects from Documentaries (2017, background): “Some studies [11, 34, 5] explore transcripts of movies and TV series to help identify characters.”