huanglianghua / video-detection-benchmark

Video object detection benchmark.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Video Object Detection on ILSVRC VID Dataset

Video Detector Benchmark

Evaluation results on ILSVRC VID validation set. All entries are ordered by the mAP scores.

Methods mAP(%) Runtime(ms/fps) Venue
STMN (ResNet-101) 80.5 75 ms ECCV'18
MANet + SeqNMS 80.3 - ECCV'18
ST-Lattice (denser) 79.6 20 fps CVPR'18
ST-Lattice (sparser) 79.0 62 fps CVPR'18
D & T (τ=1) 79.8 5.3 fps ICCV'17
D & T (τ=10) 78.6 53 fps ICCV'17
THPVOD 78.6 13 fps CVPR'18
MANet 78.1 202 ms ECCV'18
FGFA 76.5 733 ms ICCV'17
D (& T loss) 75.8 - ICCV'17
D (R-FCN) 74.2 - ICCV'17
TCNN 73.8 - TCSVR'17
R-FCN 73.6 - NIPS'16
DFF 72.8 - CVPR'17
TPN-LSTM 68.4 2.1 fps CVPR'17
STMN (VGG-16) 61.7 - ECCV'18

Video Object Detection

ECCV 2018

  • MANet: Shiyao Wang, Yucong Zhou, Junjie Yan, Zhidong Deng. "Fully Motion-Aware Network for Video Object Detection." ECCV 2018. [pdf] [code]

  • STMN: Fanyi Xiao, Yong Jae Lee. "Video Object Detection with an Aligned Spatial-Temporal Memory." ECCV 2018. [pdf] [project] [code]

CVPR 2018

  • TAFM: Mason Liu, Menglong Zhu. "Mobile Video Object Detection With Temporally-Aware Feature Maps." CVPR 2018. [pdf]

  • THPVOD: Xizhou Zhu, Jifeng Dai, Lu Yuan, Yichen Wei. "Towards High Performance Video Object Detection." CVPR 2018. [pdf]

  • ST-Lattice: Kai Chen, Jiaqi Wang, Shuo Yang, Xingcheng Zhang, Yuanjun Xiong, Chen Change Loy, Dahua Lin. "Optimizing Video Object Detection via a Scale-Time Lattice." CVPR 2018. [pdf] [project] [code]

ICCV 2017

  • FGFA: Xizhou Zhu, Yujie Wang, Jifeng Dai, Lu Yuan, Yichen Wei. "Flow-Guided Feature Aggregation for Video Object Detection." ICCV 2017. [pdf] [video] [code]

  • TD-Graph LSTM: Yuan Yuan, Xiaodan Liang, Xiaolong Wang, Dit-Yan Yeung, Abhinav Gupta. "Temporal Dynamic Graph LSTM for Action-Driven Video Object Detection." ICCV 2017. [pdf] [supp]

  • a_LSTM: Yongyi Lu, Cewu Lu, Chi-Keung Tang. "Online Video Object Detection Using Association LSTM." ICCV 2017. [pdf]

  • ULFV: Ioana Croitoru, Simion-Vlad Bogolin, Marius Leordeanu. "Unsupervised Learning From Video to Detect Foreground Objects in Single Images." ICCV 2017. [pdf]

  • D & T: Christoph Feichtenhofer, Axel Pinz and Andrew Zisserman. "Detect to Track and Track to Detect." ICCV 2017. [pdf] [code]

CVPR 2017

  • VPNs: Varun Jampani, Raghudeep Gadde, Peter V. Gehler. "Video Propagation Networks." CVPR 2017. [pdf] [supp]

  • FCN-LSTM: Huazhe Xu, Yang Gao, Fisher Yu, Trevor Darrell. "End-To-End Learning of Driving Models From Large-Scale Video Datasets." CVPR 2017. [pdf]

  • TPN-LSTM: Kang Kai, Li Hongsheng, Xiao Tong, et al. "Object Detection in Videos with Tubelet Proposal Networks." CVPR 2017. [pdf]

ECCV 2016

  • Hanul Kim, Chang-Su Kim. "CDT: Cooperative Detection and Tracking for Tracing Multiple Objects in Video Sequences." [pdf]

  • Koteswar Jerripothula, Jianfei Cai, Junsong Yuan. "CATS: Co-saliency Activated Tracklet Selection for Video Co-localization." [pdf]

CVPR 2016

  • TCN: Kai Kang, Wanli Ouyang, Hongsheng Li, Xiaogang Wang. "Object Detection From Video Tubelets With Convolutional Neural Networks." [project] [pdf]

ArXiv 2016

  • SeqNMS: Wei Han, Pooya Khorrami, Tom Le Paine, et al. "Seq-NMS for Video Object Detection." ArXiv 2016. [pdf]

ICCV 2015

  • UnsupVideo: Suha Kwak, Minsu Cho, Ivan Laptev, Jean Ponce, Cordelia Schmid. "Unsupervised Object Discovery and Tracking in Video Collections." [pdf]

  • UnsupParse: Ozan Sener, Amir R. Zamir, Silvio Savarese, Ashutosh Saxena. "Unsupervised Semantic Parsing of Video Collections." [pdf]

ArXiv

  • Tuan-Hung Vu, Anton Osokin, Ivan Laptev. "Tube-CNN: Modeling temporal evolution of appearance for object detection in video." [pdf]

  • Shiyao Wang, Hongchao Lu, Pavel Dmitriev, Zhidong Deng. "Fast Object Detection in Compressed Video." [pdf]

  • Hao Luo, Wenxuan Xie, Xinggang Wang, Wenjun Zeng. "Detect or Track: Towards Cost-Effective Video Object Detection/Tracking." [pdf]

  • Vít Růžička, Franz Franchetti. "Fast and accurate object detection in high resolution 4K and 8K video using GPUs." [pdf]

About

Video object detection benchmark.