A Pursuit of Temporal Accuracy in General Activity Detection

03/08/2017
by   Yuanjun Xiong, et al.
0

Detecting activities in untrimmed videos is an important but challenging task. The performance of existing methods remains unsatisfactory, e.g., they often meet difficulties in locating the beginning and end of a long complex action. In this paper, we propose a generic framework that can accurately detect a wide variety of activities from untrimmed videos. Our first contribution is a novel proposal scheme that can efficiently generate candidates with accurate temporal boundaries. The other contribution is a cascaded classification pipeline that explicitly distinguishes between relevance and completeness of a candidate instance. On two challenging temporal activity detection datasets, THUMOS14 and ActivityNet, the proposed framework significantly outperforms the existing state-of-the-art methods, demonstrating superior accuracy and strong adaptivity in handling activities with various temporal structures.

READ FULL TEXT
research
10/17/2017

Single Shot Temporal Action Detection

Temporal action detection is a very important yet challenging problem, s...
research
03/31/2020

Revisiting Few-shot Activity Detection with Class Similarity Control

Many interesting events in the real world are rare making preannotated m...
research
03/12/2020

ZSTAD: Zero-Shot Temporal Activity Detection

An integral part of video analysis and surveillance is temporal activity...
research
01/28/2018

Contextual Multi-Scale Region Convolutional 3D Network for Activity Detection

Activity detection is a fundamental problem in computer vision. Detectin...
research
10/14/2021

Talking Detection In Collaborative Learning Environments

We study the problem of detecting talking activities in collaborative le...
research
03/22/2017

R-C3D: Region Convolutional 3D Network for Temporal Activity Detection

We address the problem of activity detection in continuous, untrimmed vi...
research
01/27/2020

rCRF: Recursive Belief Estimation over CRFs in RGB-D Activity Videos

For assistive robots, anticipating the future actions of humans is an es...

Please sign up or login with your details

Forgot password? Click here to reset