AI Paper Atlas

Research map / Benchmarks / PHOENIX-2014

PHOENIX-2014 leaderboard

11 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on PHOENIX-2014. Best WER: 16.7 (CSL-Daily+Phoenix-2014T->Phoenix-2014 (TwoStream), ICCV 2023).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

PHOENIX-2014 · WER

11 papers, each with its best reported number for its own method; lower is better.

#WER ↓MethodPaperTopic
116.7CSL-Daily+Phoenix-2014T->Phoenix-2014 (TwoStream)
TwoStream-SLR
Improving Continuous Sign Language Recognition with Cross-Lingual Signs
ICCV 2023 · Table 2
Language, safety and interpretability
217.7C2ST
Swin-T + BERT-Base
C2ST: Cross-Modal Contextualized Sequence Transduction for Continuous Sign Language Recognition
ICCV 2023 · Table 1
Video segmentation and tracking
318.8HyperSignHyperSign: Hierarchical Hypergraph-based Co-occurrence Modeling for Sign Language Recognition and Translation
AAAI 2026 · Table 1
Knowledge and temporal graphs
418.8TwoStream-SLRTwo-Stream Network for Sign Language Recognition and Translation
NeurIPS 2022 · SLR comparison table
Language, safety and interpretability
519.2SCOPE-SLR w/o ContextSCOPE: Sign Language Contextual Processing with Embedding from LLMs
AAAI 2025 · SLR comparison table
Language, safety and interpretability
620.1CVT-SLR (Ours4)
ResNet18
CVT-SLR: Contrastive Visual-Textual Transformation for Sign Language Recognition With Variational Alignment
CVPR 2023 · Table 1
Cross-modal learning
720.4C2SLR
VLT
C2SLR: Consistency-Enhanced Continuous Sign Language Recognition
CVPR 2022 · Table 6
Language, safety and interpretability
820.7STMC
VGG-11
Spatial-Temporal Multi-Cue Network for Continuous Sign Language Recognition
AAAI 2020 · Table: Comparison with methods
Video segmentation and tracking
925.3SFD+SGS+SFL+LMStochastic Fine-grained Labeling of Multi-state Sign Glosses for Continuous Sign Language Recognition
ECCV 2020 · Table 2
Recognition and long-tail
1026.8CNN-2BLSTM re-aligned
GoogLeNet
Re-Sign: Re-Aligned End-To-End Sequence Modelling With Deep Recurrent CNN-HMMs
CVPR 2017 · Table 9
Action recognition
1 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.