Temporal Segment Networks: Towards Good Practices for Deep Action Recognition

Abstract

Deep convolutional networks have achieved great success for visual recognition in still images. However, for action recognition in videos, the advantage over traditional methods is not so evident. This paper aims to discover the principles to design effective ConvNet architectures for action recognition in videos and learn these models given limited training samples. Our first contribution is temporal segment network (TSN), a novel framework for video-based action recognition. which is based on the idea of long-range temporal structure modeling. It combines a sparse temporal sampling strategy and video-level supervision to enable efficient and effective learning using the whole action video. The other contribution is our study on a series of good practices in learning ConvNets on video data with the help of temporal segment network. Our approach obtains the state-the-of-art performance on the datasets of HMDB51 ( $69.4\%$) and UCF101 ($94.2\%$). We also visualize the learned ConvNet models, which qualitatively demonstrates the effectiveness of temporal segment network and the proposed good practices.

Accepted by ECCV 2016. Based on this method, we won the ActivityNet challenge 2016 in untrimmed video classification

References in corpus (1)

• UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild

Cited by in corpus (10)

• Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition
• Revisiting the Effectiveness of Off-the-shelf Temporal Modeling Approaches for Large-scale Video Classification
• Multi-Modality Fusion based on Consensus-Voting and 3D Convolution for Isolated Gesture Recognition
• Attention Clusters: Purely Attention Based Local Feature Integration for Video Classification
• Pillar Networks++: Distributed non-parametric deep and wide networks
• Generalized Zero-Shot Learning for Action Recognition with Web-Scale Video Data
• Action Recognition with Coarse-to-Fine Deep Feature Integration and Asynchronous Fusion
• Video Representation Learning and Latent Concept Mining for Large-scale Multi-label Video Classification
• Learning Spatiotemporal Features for Infrared Action Recognition with 3D Convolutional Neural Networks
• Large-Scale Mapping of Human Activity using Geo-Tagged Videos