429 citations · 2.5k across the 69 of their papers we have counts for
6 papers · 1 filter
Dense RepPoints: Representing Visual Objects with Dense Point Sets
Ze Yang, Yinghao Xu, Han Xue +5
We present a new object representation, called Dense RepPoints, that utilizes a large set of points to describe an object at multiple levels, including both box level and pixel lev…
Distributed Machine Learning through Heterogeneous Edge Systems
Hanpeng Hu, Dan Wang, Chuan Wu
Many emerging AI applications request distributed machine learning (ML) among edge systems (e.g., IoT devices and PCs at the edge of the Internet), where data cannot be uploaded to…
GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond
Yue Cao, Jiarui Xu, Stephen Lin +2
The Non-Local Network (NLNet) presents a pioneering approach for capturing long-range dependencies, via aggregating query-specific global context to each query position. However, t…
Local Relation Networks for Image Recognition
Han Hu, Zheng Zhang, Zhenda Xie +1
The convolution layer has been the dominant feature extractor in computer vision for years. However, the spatial aggregation in convolution is basically a pattern matching process…
Spatial-Temporal Relation Networks for Multi-Object Tracking
Jiarui Xu, Yue Cao, Zheng Zhang +1
Recent progress in multiple object tracking (MOT) has shown that a robust similarity score is key to the success of trackers. A good similarity score is expected to reflect multipl…
RepPoints: Point Set Representation for Object Detection
Ze Yang, Shaohui Liu, Han Hu +2
Modern object detectors rely heavily on rectangular bounding boxes, such as anchors, proposals and the final predictions, to represent objects at various recognition stages. The bo…