Recognizing Complex Events Using Large Margin Joint Low-Level Event Model

By Hamid Izadinia, Mubarak Shah. 2012

121 citations recorded by the source corpus.

Subfields: Artificial Intelligence, 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 Artificial Intelligence

1. Li Fei-Fei
2. Abhinav Kumar Gupta
3. Ali Farhadi
4. Mohit Bansal
5. Trevor Darrell
6. Chen Sun
7. Eric P. Xing
8. Yi Yang

In Computer Vision and Pattern Recognition

1. Luc Van Gool
2. Dacheng Tao
3. Yi Yang
4. Li Fei-Fei
5. Xiaogang Wang
6. Andrew Zisserman
7. Trevor Darrell
8. Abhinav Kumar Gupta

Citations in the corpus

• Actions ~ Transformations (2015, background): “Temporal structure of videos have also been shown effective in action recognition [47, 6, 44, 13, 34].”
• Asynchronous Temporal Fields for Action Recognition (2016, background): “Capturing the whole information of the video in terms of temporal evolution of the video stream has been the focus of some recent approaches [51, 6, 12, 35, 49, 30].”
• Action and Event Recognition with Fisher Vectors on a Compact Feature Set (2013, unknown): “[10] use a tree-structured CRF to model co-occurrence relations among sub-events and complex event categories, but require additional labeling of the sub-events unlike Tang et al .”
• DISCOVER: Discovering Important Segments for Classification of Video Events and Recounting (2014, methodology): “We used two datasets UCF 101 [18] and MED action annotation set [8] to learn primitive action classifiers.”
• Semantic Pooling for Complex Event Analysis in Untrimmed Videos (2016, methodology): “Similar to our work, [44] also considered decomposing a complex video event into several low-level events (which we call concepts).”
• Rank Pooling for Action Recognition (2015, methodology): “At the same time, rank pooling is compatible with and complementary to several appearance and local motion based methods and features, such as improved trajectories and deep learning features.”
• Video Event Understanding Using Natural Language Descriptions (2013, methodology): “4 against baseline methods as well as state-of-the-art results from [8] in Tab.”
• Compositional Models for Video Event Detection: A Multiple Kernel Learning Latent Variable Approach (2013, methodology): “Izadinia and Shah [4] developed a similar method, but with manual annotations on the training data – extending the image-attribute method of Wang and Mori [17] to the video domain.”
• Learning Temporal Embeddings for Complex Video Analysis (2015, methodology): “Another related line of work is the use of subevents defined manually [7], or clustered from data [20] to improve recognition.”
• Modeling video evolution for action recognition (2015, background): “Temporal ordering models have also been applied in the context of complex activity recognition [6, 26, 32].”
• ACTIVE: Activity Concept Transitions in Video Event Classification (2013, methodology): “To compare our framework with [5], we followed their protocol and randomly selected 70% videos from EventKit for training and 30% for testing.”
• A Robust and Efficient Video Representation for Action Recognition (2015, unknown): “Izadinia and Shah (2012) use a tree-structured CRF to model co-occurrence relations among sub-events and complex event categories, but require additional labeling of the sub-events unlike Tang et al (2012).”
• Leveraging Weak Semantic Relevance for Complex Video Event Classification (2017, methodology): “To alleviate this issue, methods utilizing semantic information have been proposed [1, 30, 10, 25, 12, 13, 32].”