Search Results for author: Menglin Wang

Found 7 papers, 5 papers with code

Learning Intra and Inter-Camera Invariance for Isolated Camera Supervised Person Re-identification

1 code implementation2 Nov 2023 Menglin Wang, Xiaojin Gong

To eliminate the confounding effect of camera bias, we propose to learn both intra- and inter-camera invariance under a unified framework.

Contrastive Learning Person Re-Identification

Offline-Online Associated Camera-Aware Proxies for Unsupervised Person Re-identification

1 code implementation15 Jan 2022 Menglin Wang, Jiachen Li, Baisheng Lai, Xiaojin Gong, Xian-Sheng Hua

Assisted with the camera-aware proxies, we design two proxy-level contrastive learning losses that are, respectively, based on offline and online association results.

Clustering Contrastive Learning +1

The DeepFake Detection Challenge (DFDC) Dataset

7 code implementations12 Jun 2020 Brian Dolhansky, Joanna Bitton, Ben Pflaum, Jikuo Lu, Russ Howes, Menglin Wang, Cristian Canton Ferrer

In addition to Deepfakes, a variety of GAN-based face swapping methods have also been published with accompanying code.

DeepFake Detection Face Swapping

Towards Precise Intra-camera Supervised Person Re-identification

no code implementations12 Feb 2020 Menglin Wang, Baisheng Lai, Haokun Chen, Jianqiang Huang, Xiaojin Gong, Xian-Sheng Hua

Our approach performs even comparable to state-of-the-art fully supervised methods in two of the datasets.

Person Re-Identification

Deep Active Learning for Video-based Person Re-identification

no code implementations14 Dec 2018 Menglin Wang, Baisheng Lai, Zhongming Jin, Xiaojin Gong, Jianqiang Huang, Xian-Sheng Hua

With the gained annotations of the actively selected candidates, the tracklets' pesudo labels are updated by label merging and further used to re-train our re-ID model.

Active Learning Video-Based Person Re-Identification

Cannot find the paper you are looking for? You can Submit a new open access paper.