DISCOVER: Discovering Important Segments for Classification of Video Events and Recounting
We propose a unified framework DISCOVER to simultaneously discover important segments, classify high-level events and generate recounting for large amounts of unconstrained web videos. The motivation is our observation that many video events are characterized by certain important segments. Our goal is to find the important segments and capture their information for event classification and recounting. We introduce an evidence localization model where evidence locations are modeled as latent variables. We impose constraints on global video appearance, local evidence appearance and the temporal structure of the evidence. The model is learned via a max-margin framework and allows efficient inference. Our method does not require annotating sources of evidence, and is jointly optimized for event classification and recounting. Experimental results are shown on the challenging TRECVID 2013 MEDTest dataset.
Code (0)
등록된 구현이 없습니다.
Tasks
General ClassificationSimilar Papers 제목 키워드 기반
All Eyes on the Workflow: Automated and Efficient Event Discovery from Video Streams
Disciplines such as business process management and process mining aid organizations by discovering insights about processes on the basis of recorded event data. However, an obstacle to process analysis is data multi-mod…
Measuring similarity between geo-tagged videos using largest common view
This paper presents a novel problem for discovering the similar trajectories based on the field of view (FoV) of the video data. The problem is important for many societal applications such as grouping moving objects, cl…
Cross-Modality Attention with Semantic Graph Embedding for Multi-Label Classification
Multi-label image and video classification are fundamental yet challenging tasks in computer vision. The main challenges lie in capturing spatial or temporal dependencies between labels and discovering the locations of d…
ClassificationGeneral ClassificationGraph Embeddingimage-classification+5Temporally Coherent Bayesian Models for Entity Discovery in Videos by Tracklet Clustering
A video can be represented as a sequence of tracklets, each spanning 10-20 frames, and associated with one entity (eg. a person). The task of \emph{Entity Discovery} in videos can be naturally posed as tracklet clusterin…
ClusteringVideo SummarizationPredictive Subspace Learning for Multi-view Data: a Large Margin Approach
Learning from multi-view data is important in many applications, such as image classification and annotation. In this paper, we present a large-margin learning framework to discover a predictive latent subspace represent…
General Classificationimage-classificationImage Classificationparameter estimation+1