Yuanjun Xiong

Yuanjun Xiong
Are you Yuanjun Xiong?

Claim your profile, edit publications, add additional information:

Contact Details

Name
Yuanjun Xiong
Affiliation
Location

Pubs By Year

Pub Categories

 
Computer Science - Computer Vision and Pattern Recognition (8)

Publications Authored By Yuanjun Xiong

Detecting activities in untrimmed videos is an important yet challenging task. In this paper, we tackle the difficulties of effectively locating the start and the end of a long complex action, which are often met by existing methods. Our key contribution is the structured segment network, a novel framework for temporal action detection, which models the temporal structure of each activity instance via a structured temporal pyramid. Read More

Current action recognition methods heavily rely on trimmed videos for model training. However, it is very expensive and time-consuming to acquire a large-scale trimmed video dataset. This paper presents a new weakly supervised architecture, called UntrimmedNet, which is able to directly learn from untrimmed videos without the need of temporal annotations of action instances. Read More

Detecting activities in untrimmed videos is an important but challenging task. The performance of existing methods remains unsatisfactory, e.g. Read More

Convolutional Neural Networks (CNNs) have made remarkable progress on scene recognition, partially due to these recent large-scale scene datasets, such as the Places and Places2. Scene categories are often defined by multi-level information, including local objects, global layout, and background environment, thus leading to large intra-class variations. In addition, with the increasing number of scene categories, label ambiguity has become another crucial issue in large-scale classification. Read More

This paper presents the method that underlies our submission to the untrimmed video classification task of ActivityNet Challenge 2016. We follow the basic pipeline of temporal segment networks and further raise the performance via a number of other techniques. Specifically, we use the latest deep model architecture, e. Read More

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. Read More

Deep convolutional networks have achieved great success for object recognition in still images. However, for action recognition in videos, the improvement of deep convolutional networks is not so evident. We argue that there are two reasons that could probably explain this result. Read More

In this paper, we propose multi-stage and deformable deep convolutional neural networks for object detection. This new deep learning object detection diagram has innovations in multiple aspects. In the proposed new deep architecture, a new deformation constrained pooling (def-pooling) layer models the deformation of object parts with geometric constraint and penalty. Read More