A large-scale benchmark dataset for event recognition in surveillance video

By Sangmin Oh, A. Hoogs, A. Perera, Naresh P. Cuntoor, Chia-Chih Chen, Jong Taek Lee, Saurajit Mukherjee, Jake K. Aggarwal, Hyungtae Lee, Larry S. Davis and 14 more. Computer Vision and Pattern Recognition, 2011

442 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/89d80d34bc0cf1cc9f62a76c0ffa5b01f05b9ee7

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

AVSS 2011 demo session: A large-scale benchmark dataset for event recognition in surveillance video (2011, methodology): “The following lists the 23 event types in our dataset with meaningful number of instances: • Single Person Events (8): walking, running, standing, throwing, gesturing, carrying, loitering, picking up; • Person to Person Events (6): following, meeting, gathering, moving as a group, dispersing, carryi”
MFC Datasets: Large-Scale Benchmark Datasets for Media Forensic Challenge Evaluation (2019, background): “Many general benchmark media datasets are available in literature: UCID (2003) [14] and ImageCLEF (2004-2013) [15] for image retrieval; Caltech-256 (2007) [16], 80 million tiny images (2008) [17], Mammal Image (2008) [18], PASCAL (2008-2015) [19], ImageNet (2009) [20], SUN (2010) [21], Kitti (2013) ”
A database for fine grained activity detection of cooking activities (2012, methodology): “Surveillance datasets PETS 2007 [11] det 3 10 32,107 768x576 UT interaction [28] cls,det 6 120 6 VIRAT [23] det 23 17 1920x1080”
LEMMA: A Multi-view Dataset for Learning Multi-agent Multi-task Activities (2020, background): “Another related stream of work is the learning of group-level activities in a multi-agent setting [26], such as detecting key actors [43], predicting future trajectories [40,34], and recognizing collective activities [11,39,50].”
Human motion trajectory prediction: a survey (2019, background): “…scenarios, e.g. indoor (Zhou et al. 2012; Brˇsˇci´c et al. 2013; Yan et al. 2017) and outdoor environments (Pellegrini et al. 2009; Lerner et al. 2007; Oh et al. 2011), pedestrian areas (Majecka 2009; Benfold and Reid 2011), urban zones (Robicquet et al. 2016; Schneider and Gavrila 2013) and…”
A Benchmark Dataset and Evaluation Methodology for Video Object Segmentation (2016, background): “Video datasets designed to benchmark tracking algorithms typically focus on surveillance scenarios with static cameras [9, 16, 32], and usually contain multiple instances of similar objects [50] (e.”
Hierarchical Deep Temporal Models for Group Activity Recognition (2016, background): “In the context of surveillance video, the TRECVid Surveillance Event Detection [54], UT-Interaction [55], VIRAT [56], and UCLA Courtyard datasets [57] are examples of challenging tasks including individual and pair-wise interactions.”
Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding (2016, background): “Standard approaches in the past have used videos downloaded from the Internet [3,4,5,6,7,8] gathered from movies [9,10,11] or recorded in controlled environments [12,13,14,15,16,17].”
Instructing people for training gestural interactive systems (2012, background): “Whilst popular for controlling entertainment consoles, applications of such systems also exist in tutoring [6], security [20] and healthcare [30].”
SoPhie: An Attentive GAN for Predicting Paths Compliant to Social and Physical Constraints (2018, background): “Autonomous systems such as social and household robots [1, 8, 14], security systems [21, 24, 23], and self driving cars can do tasks like delivery, cleaning, security, and driving.”
PIE: A Large-Scale Dataset and Models for Pedestrian Intention Estimation and Trajectory Prediction (2019, background): “A number of datasets for trajectory prediction contain videos collected from a top-down view [18, 25, 22, 31] or surveillance camera perspective [23, 4, 45].”
Watch and learn: Semi-supervised learning of object detectors from videos (2015, background): “A relevant thread of work which also uses bounding box annotations is that of tracking-by-detection.”
A visual Turing test for computer vision systems (2014, unknown): “Finally, a few other datasets have been assembled and annotated to evaluate the quality of detected object attributes such as color, orientation and activity; examples are the Core dataset [26], with annotated object parts and attributes, and the Virat dataset [27] for event detection in videos.”