activity
20162022
most citedLearning Disentangled Representation for Robust Person Re-identification

36 citations · 106 across the 15 of their papers we have counts for

collaborators
Showing cs.CVShow all

22 papers · 1 filter

cs.CV202211 cited

ALIFE: Adaptive Logit Regularizer and Feature Replay for Incremental Semantic Segmentation

Youngmin Oh, Donghyeon Baek, Bumsub Ham

We address the problem of incremental semantic segmentation (ISS) recognizing novel object/stuff categories continually without forgetting previous ones that have been learned. The…

cs.CV20224 cited

Decomposed Knowledge Distillation for Class-Incremental Semantic Segmentation

Donghyeon Baek, Youngmin Oh, Sanghoon Lee +2

Class-incremental semantic segmentation (CISS) labels each pixel of an image with a corresponding object/stuff class continually. To this end, it is crucial to learn novel classes…

cs.CV2021

Video-based Person Re-identification with Spatial and Temporal Memory Networks

Chanho Eom, Geon Lee, Junghyup Lee +1

Video-based person re-identification (reID) aims to retrieve person videos with the same identity as a query person across multiple cameras. Spatial and temporal distractors in per…

cs.CV2021

Learning by Aligning: Visible-Infrared Person Re-identification using Cross-Modal Correspondences

Hyunjong Park, Sanghoon Lee, Junghyup Lee +1

We address the problem of visible-infrared person re-identification (VI-reID), that is, retrieving a set of person images, captured by visible or infrared cameras, in a cross-modal…

cs.CV20211 cited

Distance-aware Quantization

Dohyung kim, Junghyup Lee, Bumsub Ham

We address the problem of network quantization, that is, reducing bit-widths of weights and/or activations to lighten network architectures. Quantization methods use a rounding fun…

cs.CV20212 cited

Exploiting a Joint Embedding Space for Generalized Zero-Shot Semantic Segmentation

Donghyeon Baek, Youngmin Oh, Bumsub Ham

We address the problem of generalized zero-shot semantic segmentation (GZS3) predicting pixel-wise semantic labels for seen and unseen classes. Most GZS3 methods adopt a generative…