Lune

ICCV2019Top-tier venue

Uncertainty Modeling of Contextual-Connections Between Tracklets for Unconstrained Video-Based Face Recognition

Jingxiao Zheng, Ruichi Yu, Jun-Cheng Chen, Boyu Lu, Carlos Domingo Castillo, Rama Chellappa

Abstract

Unconstrained video-based face recognition is a challenging problem due to significant within-video variations caused by pose, occlusion and blur. To tackle this problem, an effective idea is to propagate the identity from high-quality faces to low-quality ones through contextual connections, which are constructed based on context such as body appearance. However, previous methods have often propagated erroneous information due to lack of uncertainty modeling of the noisy contextual connections. In this paper, we propose the Uncertainty-Gated Graph (UGG), which conducts graph-based identity propagation between tracklets, which are represented by nodes in a graph. UGG explicitly models the uncertainty of the contextual connections by adaptively updating the weights of the edge gates according to the identity distributions of the nodes during inference. UGG is a generic graphical model that can be applied at only inference time or with end-to-end training. We demonstrate the effectiveness of UGG with state-of-the-art results in the recently released challenging Cast Search in Movies and IARPA Janus Surveillance Video Benchmark dataset.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

2 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • KeyPoint Relative Position Encoding for Face Recognition cites Cluster and Aggregate: Face Recognition with Large Probe Set
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers2

  1. Cluster and Aggregate: Face Recognition with Large Probe SetMinchul Kim, Feng Liu, Anil K. Jain, Xiaoming LiuNeurIPS 2022 · 36 citations
  2. KeyPoint Relative Position Encoding for Face RecognitionMinchul Kim, Yiyang Su, Feng Liu, Anil Jain et al.CVPR 2024

Related papers

  1. Unsupervised Graph Association for Person Re-IdentificationJinlin Wu, Hao Liu, Yang Yang, Zhen Lei et al.ICCV 2019 · 116 citations
  2. Rethinking Pseudo-Label-Based Unsupervised Person Re-ID with Hierarchical Prototype-based GraphBen Sha, Baopu Li, Tao Chen, Jiayuan Fan et al.ACM MM 2023 · 1 citation
  3. UGG-ReID: Uncertainty-Guided Graph Model for Multi-Modal Object Re-IdentificationXixi Wan, Aihua Zheng, Bo Jiang, Beibei Wang et al.NeurIPS 2025 · 4 citations
  4. NCSTR: Node-Centric Decoupled Spatio-Temporal Reasoning for Video-based Human Pose EstimationQuang Dang Huynh, Xuefei Yin, Andrew Busch, Hugo G. Espinosa, Alan Wee-Chung Liew, Matthew T.O. Worsey, Yanming ZhuCVPR Findings 2026
  5. Learning Multi-Granular Hypergraphs for Video-Based Person Re-IdentificationYichao Yan, Jie Qin, Jiaxin Chen, Li Liu et al.CVPR 2020
Dusk over the sea between two cliffs drawn in fine vertical lines