794 citations · 1.3k across the 14 of their papers we have counts for
17 papers
Improving Description-based Person Re-identification by Multi-granularity Image-text Alignments
Kai Niu, Yan Huang, Wanli Ouyang +1
Description-based person re-identification (Re-id) is an important task in video surveillance that requires discriminative cross-modal representations to distinguish different peop…
MMDetection: Open MMLab Detection Toolbox and Benchmark
Kai Chen, Jiaqi Wang, Jiangmiao Pang +22
We present MMDetection, an object detection toolbox that contains a rich set of object detection and instance segmentation methods as well as related components and modules. The to…
Contextualized Spatial-Temporal Network for Taxi Origin-Destination Demand Prediction
Lingbo Liu, Zhilin Qiu, Guanbin Li +3
Taxi demand prediction has recently attracted increasing research interest due to its huge potential application in large-scale intelligent transportation systems. However, most of…
Box-driven Class-wise Region Masking and Filling Rate Guided Loss for Weakly Supervised Semantic Segmentation
Chunfeng Song, Yan Huang, Wanli Ouyang +1
Semantic segmentation has achieved huge progress via adopting deep Fully Convolutional Networks (FCN). However, the performance of FCN based models severely rely on the amounts of…
Learning Deep Structured Multi-Scale Features using Attention-Gated CRFs for Contour Prediction
Dan Xu, Wanli Ouyang, Xavier Alameda-Pineda +3
Recent works have shown that exploiting multi-scale representations deeply learned via convolutional neural networks (CNN) is of tremendous importance for accurate contour detectio…
Visual Question Generation as Dual Task of Visual Question Answering
Yikang Li, Nan Duan, Bolei Zhou +3
Recently visual question answering (VQA) and visual question generation (VQG) are two trending topics in the computer vision, which have been explored separately. In this work, we…