“Who are you?” - Learning person specific classifiers from video

By Josef Sivic, Mark Everingham, Andrew Zisserman. 2009

267 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

Aligning Books and Movies: Towards Story-Like Visual Explanations by Watching Movies and Reading Books (2015, background): “Such alignment has been exploited to provide weak labels for person naming tasks [6, 33, 28].”
End-to-End Learning of Visual Representations From Uncurated Instructional Videos (2019, methodology): “Table 2: Comparison on the Buffy benchmark [35] using AP.”
MovieQA: Understanding Stories in Movies through Question-Answering (2015, background): “For TV series in particular, the majority of work aims at recognizing and tracking characters in the videos [2, 4, 28, 35].”
Movie Description (2016, methodology): “In order to obtain word role labels, we link verbs to VerbNet (Kipper et al. 2006; Schuler et al. 2009), a manually curated high-quality linguistic resource for English verbs.”
Weakly Supervised Action Labeling in Videos under Ordering Constraints (2014, background): “One possible source for such data is movies with their associated scripts [5, 7, 22, 32].”
Beyond frontal faces: Improving Person Recognition using multiple cues (2015, methodology): “In [9, 29, 8], the authors proposed approach to automatically label the characters by using aligned subtitle and script text.”
Detecting People Looking at Each Other in Videos (2013, background): “…towards a fuller video understanding, and complements recent work on automatic character identi-ﬁcation (Everingham et al. 2006; Cour et al. 2009; Sivic et al. 2009), human pose estimation (Ferrari et al. 2009; Andriluka et al. 2009; Bourdev et al. 2010; Sapp et al. 2010;Yang et al. 2012),…”
Who's that Actor? Automatic Labelling of Actors in TV Series Starting from IMDB Images (2016, methodology): “[1,8] proposes to combine the two (using words in the dialogues) to get the label for an active speaker, if one exists, in each frame.”
Attention-Aware Deep Reinforcement Learning for Video Face Recognition (2017, methodology): “employ a simple and effective thresholding method to get reliable features from video frames [33].”
Face recognition in unconstrained videos with matched background similarity (2011, background): “More recently [3, 14] focus on the task of aligning subtitle information with faces appearing in TV shows.”
Deep Face Recognition (2015, methodology): “Shallow methods start by extracting a representation of the face image using handcrafted local image descriptors such as SIFT, LBP, HOG [5, 13, 22, 23, 32]; then they aggregate such local descriptors into an overall face descriptor by using a pooling mechanism, for example the Fisher Vector [15, 20]”
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].”
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.”
Speech2Action: Cross-Modal Supervision for Action Recognition (2020, background): “Aligning Screenplays to Movies: A number of works have explored the use of screenplays to learn and automatically annotate character identity in TV series [5, 9, 30, 35, 39].”
"Here's looking at you, kid". Detecting people looking at each other in videos (2011, background): “There are two main strands in previous work: 2D approaches, where detectors are built for several aspects of the head (such as frontal and profile [27]) or the pose is classified into discrete viewpoints [4, 28], or regressed [20].”
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.”
Robust Face Landmark Estimation under Occlusion (2013, background): “Accurate object shape computation is key to many visual tasks; for instance, classification of facial expression [17, 30], facial identity [38], action analysis [4], and fine-grained categorization [34, 3, 18, 40] require accurate registration of a (deformable, part-based) model to the image.”
Baby talk: Understanding and generating simple image descriptions (2011, background): “This works especially well in constrained recognition scenarios—for recognizing particular classes of objects—such as for labeling faces in news photographs with associated captions [4], [5] or characters in television or movie videos with associated scripts [12], [39].”