AI Paper Atlas

Research map / Benchmarks / CSL-Daily

CSL-Daily leaderboard

28 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on CSL-Daily. Best BLEU-4: 32.08 (SCOPE-SLT w/o Context, AAAI 2025).

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.

CSL-Daily · BLEU-4

15 papers, each with its best reported number for its own method; higher is better.

#BLEU-4 ↑MethodPaperTopic
132.08SCOPE-SLT w/o ContextSCOPE: Sign Language Contextual Processing with Embedding from LLMs
AAAI 2025 · SLT comparison table
Language, safety and interpretability
228.94CV-SLTConditional Variational Autoencoder for Sign Language Translation with Cross-Modal Alignment
AAAI 2024 · Main Results table
Cross-modal learning
328.51SIGNET
mT5-base
SIGNET: Motion-Level Knowledge Transfer for Cross-Language Sign Language Translation
ECCV 2026 · Table 1
Language, safety and interpretability
427.42Geo-Sign (Hyperbolic Token)
Uni-Sign with mT5
Geo-Sign: Hyperbolic Contrastive Regularisation for Geometrically Aware Sign Language Translation
NeurIPS 2025 · CSL-Daily results table
RNNs and normalization
527.16VTaMo
Flan-T5-XL
Video-Text Alignment Model for Sign Language Translation
ECCV 2026 · Table 1
Video-language understanding
626.91Q-BridgeNet CSL-ZH multilingual
Qwen3-1.7B
Q-BridgeNet: A Quantization Network for Cross-Lingual Sign Language Translation
ECCV 2026 · Table 1
Language, safety and interpretability
726.36Uni-Sign (RGB-pose)
mT5-Base
Uni-Sign: Toward Unified Sign Language Understanding at Scale
ICLR 2025 · Complete Results of Experiment
Instruction and fine-tuning
825.46SignDINOLearning Effective Sign Features without Text for Gloss-free Sign Language Translation
CVPR 2026 · Table 9
Self-supervised and contrastive
921.11MMSLT
LLaVA-OneVision 7B descriptions + mBART
Leveraging the Power of MLLMs for Gloss-Free Sign Language Translation
ICCV 2025 · Table 2
Multimodal LLMs
1020.85VAP
CoSign-1s skeleton + mBART
Visual Alignment Pre-training for Sign Language Translation
ECCV 2024 · Table 1
Language, safety and interpretability
5 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

CSL-Daily · WER

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

#WER ↓MethodPaperTopic
123.1SCOPE-SLR w/o ContextSCOPE: Sign Language Contextual Processing with Embedding from LLMs
AAAI 2025 · SLR comparison table
Language, safety and interpretability
224.2HyperSign
ResNet34
HyperSign: Saliency-Aware Spatial Graphs and Temporal Hypergraphs for Continuous Sign Language Recognition
AAAI 2026 · Table 2
Knowledge and temporal graphs
324.7OLMD
ResNet34
OLMD: Orientation-aware Long-term Motion Decoupling for Continuous Sign Language Recognition
AAAI 2025 · Table 2
Video segmentation and tracking
425.3TwoStream-SLRTwo-Stream Network for Sign Language Recognition and Translation
NeurIPS 2022 · SLR comparison table
Language, safety and interpretability
525.7HyperSignHyperSign: Hierarchical Hypergraph-based Co-occurrence Modeling for Sign Language Recognition and Translation
AAAI 2026 · Table 1
Knowledge and temporal graphs
625.8C2ST
Swin-T + BERT-Base
C2ST: Cross-Modal Contextualized Sequence Transduction for Continuous Sign Language Recognition
ICCV 2023 · Table 3
Video segmentation and tracking
726.4MultiSignGraphSignGraph: A Sign Sequence is Worth Graphs of Nodes
CVPR 2024 · Table 5
Knowledge and temporal graphs
826.7CSGC
ResNet18
Cross-Sentence Gloss Consistency for Continuous Sign Language Recognition
AAAI 2024 · Table 7
Language, safety and interpretability
927.2CoSign-2sCoSign: Exploring Co-occurrence Signals in Skeleton-based Continuous Sign Language Recognition
ICCV 2023 · Table 1
Video segmentation and tracking
1027.9OursScaling up Multimodal Pre-Training for Sign Language Understanding
TPAMI 2025 · Table 5
CLIP and zero-shot
4 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.