Temporal Action Localization aims to detect activities in the video stream and output beginning and end timestamps. It is closely related to Temporal Action Proposal Generation.
|TREND||DATASET||BEST METHOD||PAPER TITLE||PAPER||CODE||COMPARE|
The AVA dataset densely annotates 80 atomic visual actions in 430 15-minute video clips, where actions are localized in space and time, resulting in 1. 58M action labels with multiple labels per person occurring frequently.
Ranked #2 on Temporal Action Localization on J-HMDB-21
To address these difficulties, we introduce the Boundary-Matching (BM) mechanism to evaluate confidence scores of densely distributed proposals, which denote a proposal as a matching pair of starting and ending boundaries and combine all densely distributed BM pairs into the BM confidence map.
Temporal action proposal generation is an important yet challenging problem, since temporal proposals with rich action content are indispensable for analysing real-world videos with long duration and high proportion irrelevant content.
Ranked #1 on Temporal Action Proposal Generation on THUMOS' 14
Second, frame-based models perform quite well on action recognition; is pre-training for good image features sufficient or is pre-training for spatio-temporal features valuable for optimal transfer learning?
Ranked #1 on Action Recognition on Kinetics-400
In this paper we discuss several forms of spatiotemporal convolutions for video analysis and study their effects on action recognition.
Ranked #3 on Action Recognition on Sports-1M
Dynamics of human body skeletons convey significant information for human action recognition.
Ranked #2 on Multimodal Activity Recognition on EV-Action
Furthermore, based on the temporal segment networks, we won the video classification track at the ActivityNet challenge 2016 among 24 teams, which demonstrates the effectiveness of TSN and the proposed good practices.
Ranked #10 on Action Classification on Moments in Time (Top 5 Accuracy metric)
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.
Ranked #3 on Multimodal Activity Recognition on EV-Action
Consider end-to-end training of a multi-modal vs. a single-modal network on a task with multiple input modalities: the multi-modal network receives more information, so it should match or outperform its single-modal counterpart.