AI Paper Atlas

Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning

BiCrossNet with Decoupled Dual Generators: A Parameter‑Efficient and Generalizable Few‑Shot Custom Gesture Recognition Framework

Chunyang Yu, Ning SUN, Shenyue Wang

ICML 2026 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Fine-tuning strategies for few-shot

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add data augmentation (Embedding Generator) (ablation)BiCroNet · UMAHandF1 (%): 54.56 -> 98.13Improved
add data augmentation (Embedding Generator) (ablation)BiCroNet · GRHandF1 (%): 54.51 -> 96.13Improved
replace Delta Encoder with Delta Generator (ablation)BiCroNet · UMAHandF1 (%): 92.50 -> 97.14Improved
replace Delta Encoder with Embedding Generator (ablation)BiCroNet · UMAHandF1 (%): 92.50 -> 98.13Improved
replace Delta Encoder with Delta Generator (ablation)BiCroNet · GRHandF1 (%): 89.51 -> 90.99Improved
replace Delta Encoder with Embedding Generator (ablation)BiCroNet · GRHandF1 (%): 89.51 -> 96.13Improved
replace Delta Encoder with Delta Generator (ablation)Improved TCNN · UMAHandaccuracy (%): 82.18 -> 97.39Improved
replace Delta Encoder with Embedding Generator (ablation)Improved TCNN · UMAHandaccuracy (%): 82.18 -> 98.10Improved
replace Delta Encoder with Embedding Generator (ablation)Improved TCNN · GRHandF1 (%): 81.04 -> 77.99Mixed
use BiCrossNet extractor instead of Improved TCNN (Embedding Generator) (ablation)Embedding Generator · UMAHandparameters: 45198 -> 32642Improved
use BiCrossNet extractor instead of AppleDE (Delta Encoder)Delta Encoder · UMAHandF1 (%): 88.31 -> 92.50Improved
use BiCrossNet extractor instead of Apple extractorCPU inference · Xeon Gold 6342latency (ms): 11.07 -> 9.16Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy