Finding Action Tubes

Abstract

We address the problem of action detection in videos. Driven by the latest progress in object detection from 2D images, we build action models using rich feature hierarchies derived from shape and kinematic cues. We incorporate appearance and motion in two ways. First, starting from image region proposals we select those that are motion salient and thus are more likely to contain the action. This leads to a significant reduction in the number of regions being processed and allows for faster computations. Second, we extract spatio-temporal feature representations to build strong classifiers using Convolutional Neural Networks. We link our predictions to produce detections consistent in time, which we call action tubes. We show that our approach outperforms other techniques in the task of action detection.

References in corpus (2)

• Two-Stream Convolutional Networks for Action Recognition in Videos
• UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild

Cited by in corpus (25)

• Sequence to Sequence -- Video to Text
• Temporal Action Detection with Structured Segment Networks
• Every Moment Counts: Dense Detailed Labeling of Actions in Complex Videos
• Learning to track for spatio-temporal action localization
• Contextual Action Recognition with R*CNN
• Temporal Context Network for Activity Localization in Videos
• CDC: Convolutional-De-Convolutional Networks for Precise Temporal Action Localization in Untrimmed Videos
• Weakly Supervised Action Localization by Sparse Temporal Pooling Network
• End-to-end Learning of Action Detection from Frame Glimpses in Videos
• Rethinking the Faster R-CNN Architecture for Temporal Action Localization
• Efficient Two-Stream Motion and Appearance 3D CNNs for Video Classification
• Generalized Rank Pooling for Activity Recognition
• Let's Dance: Learning From Online Dance Videos
• Deep 360 Pilot: Learning a Deep Agent for Piloting through 360° Sports Video
• Incremental Tube Construction for Human Action Detection
• Asynchronous Temporal Fields for Action Recognition
• AMTnet: Action-Micro-Tube Regression by End-to-end Trainable Deep Architecture
• Spatio-temporal Human Action Localisation and Instance Segmentation in Temporally Untrimmed Videos
• Feature Sampling Strategies for Action Recognition
• Spatio-Temporal Instance Learning: Action Tubes from Class Supervision
• Action Tubelet Detector for Spatio-Temporal Action Localization
• Action Detection from a Robot-Car Perspective
• Generic Tubelet Proposals for Action Localization
• Improving Human Action Recognition by Non-action Classification
• Chained Multi-stream Networks Exploiting Pose, Motion, and Appearance for Action Classification and Detection