activity
20182020
most citedComputation Reallocation for Object Detection

30 citations · 59 across the 6 of their papers we have counts for

collaborators

8 papers

cs.CV20203 cited

SAMOT: Switcher-Aware Multi-Object Tracking and Still Another MOT Measure

Weitao Feng, Zhihao Hu, Baopu Li +3

Multi-Object Tracking (MOT) is a popular topic in computer vision. However, identity issue, i.e., an object is wrongly associated with another object of a different identity, still…

cs.CV20209 cited

Collaborative Distillation in the Parameter and Spectrum Domains for Video Action Recognition

Haisheng Su, Jing Su, Dongliang Wang +5

Recent years have witnessed the significant progress of action recognition task with deep networks. However, most of current video networks require large memory and computational r…

cs.CV2020

Complementary Boundary Generator with Scale-Invariant Relation Modeling for Temporal Action Localization: Submission to ActivityNet Challenge 2020

Haisheng Su, Jinyuan Feng, Hao Shao +6

This technical report presents an overview of our solution used in the submission to ActivityNet Challenge 2020 Task 1 (\textbf{temporal action localization/detection}). Temporal a…

cs.CV202016 cited

Class-wise Dynamic Graph Convolution for Semantic Segmentation

Hanzhe Hu, Deyi Ji, Weihao Gan +3

Recent works have made great progress in semantic segmentation by exploiting contextual information in a local or global manner with dilated convolutions, pyramid pooling or self-a…

cs.CV20201 cited

Scope Head for Accurate Localization in Object Detection

Geng Zhan, Dan Xu, Guo Lu +3

Existing anchor-based and anchor-free object detectors in multi-stage or one-stage pipelines have achieved very promising detection performance. However, they still encounter the d…

cs.CV201930 cited

Computation Reallocation for Object Detection

Feng Liang, Chen Lin, Ronghao Guo +4

The allocation of computation resources in the backbone is a crucial issue in object detection. However, classification allocation pattern is usually adopted directly to object det…