Recognizing action at a distance
- Alexei A. Efros, A. Berg, Greg Mori, Jitendra Malik
- Computer ScienceProceedings Ninth IEEE International Conferenceā¦
- 13 October 2003
A novel motion descriptor based on optical flow measurements in a spatiotemporal volume for each stabilized human figure is introduced, and an associated similarity measure to be used in a nearest-neighbor framework is introduced.
A Hierarchical Deep Temporal Model for Group Activity Recognition
- Mostafa S. Ibrahim, S. Muralidharan, Zhiwei Deng, Arash Vahdat, Greg Mori
- Computer ScienceComputer Vision and Pattern Recognition
- 19 November 2015
A 2-stage deep temporal model designed to represent action dynamics of individual people in a sequence and another LSTM model is designed to aggregate person-level information for whole activity understanding is presented.
Similarity-Preserving Knowledge Distillation
- Frederick Tung, Greg Mori
- Computer ScienceIEEE International Conference on Computer Vision
- 23 July 2019
This paper proposes a new form of knowledge distillation loss that is inspired by the observation that semantically similar inputs tend to elicit similar activation patterns in a trained network.
Action recognition by learning mid-level motion features
A method constructing mid-level motion features which are built from low-level optical flow information are developed, tuned to discriminate between different classes of action, and are efficient to compute at run-time.
End-to-End Learning of Action Detection from Frame Glimpses in Videos
- Serena Yeung, Olga Russakovsky, Greg Mori, Li Fei-Fei
- Computer ScienceComputer Vision and Pattern Recognition
- 22 November 2015
A fully end-to-end approach for action detection in videos that learns to directly predict the temporal bounds of actions and uses REINFORCE to learn the agent's decision policy.
Discriminative figure-centric models for joint action localization and recognition
This paper develops an algorithm for action recognition and localization in videos that does not require reliable human detection and tracking as input and uses a figure-centric visual word representation.
Every Moment Counts: Dense Detailed Labeling of Actions in Complex Videos
- Serena Yeung, Olga Russakovsky, Ning Jin, M. Andriluka, Greg Mori, Li Fei-Fei
- Computer ScienceInternational Journal of Computer Vision
- 21 July 2015
A novel variant of long short-term memory deep networks is defined for modeling these temporal relations via multiple input and output connections and it is shown that this model improves action labeling accuracy and further enables deeper understanding tasks ranging from structured retrieval to action prediction.
Discriminative Latent Models for Recognizing Contextual Group Activities
- Tian Lan, Yang Wang, Weilong Yang, S. Robinovitch, Greg Mori
- Computer ScienceIEEE Transactions on Pattern Analysis and Machineā¦
- 1 August 2012
This paper proposes a novel framework for recognizing group activities which jointly captures the group activity, the individual person actions, and the interactions among them and introduces a new feature representation called the action context (AC) descriptor.
Recognizing objects in adversarial clutter: breaking a visual CAPTCHA
- Greg Mori, Jitendra Malik
- Computer ScienceIEEE Computer Society Conference on Computerā¦
- 18 June 2003
Efficient methods based on shape context matching are developed that can identify the word in an EZ-Gimpy image with a success rate of 92%, and the requisite 3 words in a Gimpy image 33% of the time.
Human Action Recognition by Semilatent Topic Models
- Yang Wang, Greg Mori
- Computer ScienceIEEE Transactions on Pattern Analysis and Machineā¦
- 1 October 2009
Two new models for human action recognition from video sequences using topic models differ from previous latent topic models for visual recognition in two major aspects: first of all, the latent topics in the models directly correspond to class labels; second, some of the latent variables in previous topic models become observed in this case.
...
...