Visual recognition by counting instances: A multi-instance cardinality potential kernel
Authors:
- 1 June 2015
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 2596-2605
Abstract
Many visual recognition problems can be approached by counting instances. To determine whether an event is present in a long internet video, one could count how many frames seem to contain the activity. Classifying the activity of a group of people can be done by counting the actions of individual people. Encoding these cardinality relationships can reduce sensitivity to clutter, in the form of irrelevant frames or individuals not involved in a group activity. Learned parameters can encode how many instances tend to occur in a class of interest. To this end, this paper develops a powerful and flexible framework to infer any cardinality relation between latent labels in a multi-instance model. Hard or soft cardinality relations can be encoded to tackle diverse levels of ambiguity. Experiments on tasks such as human activity recognition, video event detection, and video summarization demonstrate the effectiveness of using cardinality relations for improving recognition results.Keywords
All Related Versions
This publication has 18 references indexed in Scilit:
- Video Event Detection by Inferring Temporal Instance Labels2014
- Event Detection Using Multi-level Relevance Labels and Multiple Features2014
- Joint Summarization of Large-Scale Collections of Web Images and Videos for Storyline Reconstruction2014
- Weakly Supervised Action Labeling in Videos under Ordering Constraints2014
- Context-Aware Modeling and Recognition of Activities in Video2013
- Spatiotemporal Deformable Part Models for Action Detection2013
- Large-Scale Video Summarization Using Web-Image Priors2013
- Discriminative Latent Models for Recognizing Contextual Group ActivitiesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2011
- Text-based image retrieval using progressive multi-instance learning2011
- Action recognition by dense trajectories2011