Discriminative Hierarchical Rank Pooling for Activity Recognition
We present hierarchical rank pooling, a video sequence encoding method for activity recognition. It consists of a network of rank pooling functions which captures the dynamics of rich convolutional neural network features within a video sequence. By stacking non-linear feature functions and rank pooling over one another, we obtain a high capacity dynamic encoding mechanism, which is used for action recognition. We present a method for jointly learning the video representation and activity classifier parameters. Our method obtains state-of-the art results on three important activity recognition benchmarks: 76.7% on Hollywood2, 66.9% on HMDB51 and, 91.4% on UCF101.
Code (0)
등록된 구현이 없습니다.
Tasks
Action RecognitionActivity RecognitionTemporal Action LocalizationSimilar Papers 제목 키워드 기반
Discriminatively Learned Hierarchical Rank Pooling Networks
In this work, we present novel temporal encoding methods for action and activity classification by extending the unsupervised rank pooling temporal encoding method in two ways. First, we present "discriminative rank pool…
Activity RecognitionBilevel OptimizationGeneral ClassificationAttentive pooling for Group Activity Recognition
In group activity recognition, hierarchical framework is widely adopted to represent the relationships between individuals and their corresponding group, and has achieved promising performance. However, the existing meth…
Activity RecognitionGroup Activity RecognitionGeneralized Rank Pooling for Activity Recognition
Most popular deep models for action recognition split video sequences into short sub-sequences consisting of a few frames; frame-based features are then pooled for recognizing the activity. Usually, this pooling step dis…
Action RecognitionActivity RecognitionRiemannian optimizationTemporal Action LocalizationNon-Linear Temporal Subspace Representations for Activity Recognition
Representations that can compactly and effectively capture the temporal evolution of semantic content are important to computer vision and machine learning algorithms that operate on multi-variate time-series data. We in…
Action RecognitionActivity RecognitionRiemannian optimizationTemporal Action Localization+2Rank Pooling for Action Recognition
We propose a function-based temporal pooling method that captures the latent structure of the video sequence data - e.g. how frame-level features evolve over time in a video. We show how the parameters of a function that…
Action RecognitionGesture RecognitionLearning-To-RankTemporal Action Localization