Blog Archives

Deep Action Parsing in Videos with Large-scale Synthesized Data, IEEE Transactions on Image Processing (TIP), 2018.

Action parsing in videos with complex scenes is an interesting but challenging task in computer vision. In this paper, we propose a generic 3D convolutional neural network in a multi-task learning manner for effective Deep Action Parsing (DAP3D-Net) in videos. …

Read More »

Posted in Publications | Comments Off on Deep Action Parsing in Videos with Large-scale Synthesized Data, IEEE Transactions on Image Processing (TIP), 2018.

Zero-shot Learning Using Synthesized Unseen Visual Data with Diffusion Regularization, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2018.

Sufficient training examples are the fundamental requirement for most of the learning tasks. However, collecting well-labeled training examples is costly. Inspired by Zero-shot Learning (ZSL) that can make use of visual attributes or natural language semantics as an intermediate level …

Read More »

Posted in Publications | Comments Off on Zero-shot Learning Using Synthesized Unseen Visual Data with Diffusion Regularization, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2018.

BMVC – 2018

Prof. Ling Shao will be serving as the General Chair for the British Machine Vision Conference 2018, which will be held in Newcastle, UK.

Posted in Events | Comments Off on BMVC – 2018

Towards Universal Representation for Unseen Action Recognition, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018

Unseen Action Recognition (UAR) aims to recognise novel action categories without training examples. While previous methods focus on inner-dataset seen/unseen splits, this paper proposes a pipeline using a large-scale training source …

Read More »

Posted in Publications, Research | Comments Off on Towards Universal Representation for Unseen Action Recognition, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018

Vehicle Re-identification by Deep Hidden Multi-View Inference, IEEE Transactions on Image Processing (TIP), 2018.

Abstract: Vehicle re-identification (re-ID) is an area that has received far less attention in the computer vision community than the prevalent person re-ID. Possible reasons for this slow progress are the lack of appropriate research data and the special 3D structure of a vehicle.

Read More »

Posted in Publications, Research | Comments Off on Vehicle Re-identification by Deep Hidden Multi-View Inference, IEEE Transactions on Image Processing (TIP), 2018.

IIAI will be organizing the 2nd CEFRL workshop at ECCV2018

IIAI will be organizing the workshop “CEFRL 2018: 2nd International Workshop on Compact and Efficient Feature Representation and Learning in Computer Vision” in conjunction with ECCV 2018.

Posted in News | Comments Off on IIAI will be organizing the 2nd CEFRL workshop at ECCV2018

IIAI will be organizing the workshop “Cross-domain Sketch Analysis Using Deep Learning Methods”

IIAI will be organizing the workshop “Cross-domain Sketch Analysis Using Deep Learning Methods” in conjunction with British Machine Vision Conference 2018.

Posted in News | Comments Off on IIAI will be organizing the workshop “Cross-domain Sketch Analysis Using Deep Learning Methods”

4 papers are accepted by CVPR2018

Four papers are accepted by IEEE Conference on Computer Vision and Pattern Recognition 2018! Congratulations to the authors.

Posted in News | Comments Off on 4 papers are accepted by CVPR2018