“Knock! Knock! Who is it?” probabilistic person identification in TV-series

By Makarand Tapaswi, Martin Bäuml, Rainer Stiefelhagen. 2012

145 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

End-to-End Learning of Visual Representations From Uncurated Instructional Videos (2019, methodology): “Examples of such methods include learning of person names from image captions or video scripts [3, 10, 35, 37].”
Movie Description (2016, methodology): “Another line of work (Cour et al. 2009; Everingham et al. 2006; Ramanathan et al. 2014; Sivic et al. 2009; Tapaswi et al. 2012) proposed datasets for character identiﬁcation targeting TV shows.”
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.”
Beyond frontal faces: Improving Person Recognition using multiple cues (2015, methodology): “Tapaswi et al. [33] proposed a Markov Random Field (MRF) method to combine face recognition and clothing features and they tried to name all the appearance of characters in TV series including non frontal face appearance.”
Learnable PINs: Cross-Modal Embeddings for Person Identity (2018, methodology): “Recently there has been a growing interest in the use of the audio-track to aid identification [7, 30, 40] which comes for free with multimedia videos.”
Aligning plot synopses to videos for story-based retrieval (2015, methodology): “Instead of nearest-neighbour matching like in [14], we use tracks as weakly labeled training data and train second order polynomial kernel SVM classifiers for each character in a 1-vs-all fashion [42].”
Finding Actors and Actions in Movies (2013, methodology): “Previous work has explored video scripts to learn and automatically annotate characters in TV series [6, 22, 23].”
It ’ s in the bag : Stronger supervision for automated face labelling (2015, methodology): “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].”
Condensed Movies: Story Based Retrieval with Contextual Embeddings (2020, background): “Early works, however, focused on using film and TV to learn human identity [21,22,23,24,25,26] or human actions [27,28,29,30,31] from the scripts or captions accompanying movies.”
CoDeL: A Human Co-detection and Labeling Framework (2013, background): “Another stream of human identity identification [18, 21] is to handle videos via trackers.”
Who's that Actor? Automatic Labelling of Actors in TV Series Starting from IMDB Images (2016, background): “In the absence of transcripts, [2,3,4] use supervision from hand-labelled ground-truth for some of the video data.”
Linking People in Videos with "Their" Names Using Coreference Resolution (2014, background): “Pioneering works such as [11, 37, 7, 38, 4, 6] sidestep this challenge by only using proper names in scripts, ignoring pronouns and nominals.”
Learning from Video and Text via Large-Scale Discriminative Clustering (2017, methodology): “Examples of such methods include learning of person names from image captions or video scripts [3, 10, 36, 38].”
MovieNet: A Holistic Dataset for Movie Understanding (2020, background): “For example, [22,65,3] take several episodes from TV series for character identification, [39] uses clips from twelve movies for action recognition, and [49] exploits scene segmentation with only three movies.”