Faster-TAD: Towards Temporal Action Detection with Proposal Generation and Classification in a Unified Network
Temporal action detection (TAD) aims to detect the semantic labels and boundaries of action instances in untrimmed videos. Current mainstream approaches are multi-step solutions, which fall short in efficiency and flexibility. In this paper, we propose a unified network for TAD, termed Faster-TAD, by re-purposing a Faster-RCNN like architecture. To tackle the unique difficulty in TAD, we make important improvements over the original framework. We propose a new Context-Adaptive Proposal Module and an innovative Fake-Proposal Generation Block. What's more, we use atomic action features to improve the performance. Faster-TAD simplifies the pipeline of TAD and gets remarkable performance on lots of benchmarks, i.e., ActivityNet-1.3 (40.01% mAP), HACS Segments (38.39% mAP), SoccerNet-Action Spotting (54.09% mAP). It outperforms existing single-network detector by a large margin.
Code (0)
등록된 구현이 없습니다.
Tasks
Action DetectionAction SpottingSimilar Papers 제목 키워드 기반
Rethinking the Faster R-CNN Architecture for Temporal Action Localization
We propose TAL-Net, an improved approach to temporal action localization in video that is inspired by the Faster R-CNN object detection framework. TAL-Net addresses three key shortcomings of existing approaches: (1) we i…
Action ClassificationAction LocalizationGeneral Classificationobject-detection+2Proposal-Free Temporal Action Detection via Global Segmentation Mask Learning
Existing temporal action detection (TAD) methods rely on generating an overwhelmingly large number of proposals per video. This leads to complex model designs due to proposal generation and/or per-proposal action instanc…
Action DetectionRepresentation LearningTemporal Action LocalizationSST: Single-Stream Temporal Action Proposals
Our paper presents a new approach for temporal detection of human actions in long, untrimmed video sequences. We introduce Single-Stream Temporal Action Proposals (SST), a new effective and efficient deep architecture fo…
Action DetectionTemporal Action Proposal GenerationMulti-region two-stream R-CNN for action detection
We propose a multi-region two-stream R-CNN model for action detection in realistic videos. We start from frame-level action detection based on faster R-CNN [1], and make three contributions: (1) we show that a motion reg…
Action DetectionAction RecognitionRegion ProposalSkeleton Based Action RecognitionDeformable Tube Network for Action Detection in Videos
We address the problem of spatio-temporal action detection in videos. Existing methods commonly either ignore temporal context in action recognition and localization, or lack the modelling of flexible shapes of action tu…
Action DetectionAction Recognition