Chao Wu, Wenhang Ge, Ancong Wu, Xiaobin Chang
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
To learn camera-view invariant features for person Re-IDentification (Re-ID), the cross-camera image pairs of each person play an important role. However, such crossview training samples could be unavailable under the ISolated Camera Supervised (ISCS) setting, e.g., a surveillance system deployed across distant scenes. To handle this challenging problem, a new pipeline is introduced by synthesizing the cross-camera samples in the feature space for model training. Specifically, the feature encoder and generator are end-to-end optimized under a novel method, Camera-Conditioned Stable Feature Generation (CCSFG). Its joint learning procedure raises concern on the stability of generative model training. Therefore, a new feature generator, σ-Regularized Conditional Variational Autoencoder (σ-Reg. CVAE), is proposed with theoretical and experimental analysis on its robustness. Extensive experiments on two ISCS person Re-ID datasets demonstrate the superiority of our CCSFG to the competitors. 1 * indicates corresponding author.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2203.15210")
get_code_for_paper("2203.15210")
have("2203.15210")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2203.15210.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2203.15210)
Connect an agent — have() is free.