AI Paper Atlas

Research map / Benchmarks / HAR

HAR leaderboard

16 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on HAR. Best accuracy: 98.1 (CC, NeurIPS 2020).

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.

HAR · accuracy

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

#accuracy ↑MethodPaperTopic
198.1CC
Linear Model
Provably Consistent Partial-Label Learning
NeurIPS 2020 · Table 3
Recognition and long-tail
297.31CauDiTSCauDiTS: Causal Disentangled Domain Adaptation of Multivariate Time Series
ICML 2024 · Table 2
Foundation models for time series
397.1DSN+S3
DSN
Segment, Shuffle, and Stitch: A Simple Layer for Improving Time-Series Representations
NeurIPS 2024 · Classification results table
Foundation models for time series
496.82DSNDynamic Sparse Network for Time Series Classification: Learning What to “See”
NeurIPS 2022 · Table 2
Foundation models for time series
595.5Hi-Time
GPT-2
Hi-Time: Hierarchical Latent Prediction for Multivariate Time Series Classification
ICML 2026 · Table 1
Foundation models for time series
695.35REBARREBAR: Retrieval-Based Reconstruction for Time-series Contrastive Learning
ICLR 2024 · Table, Linear Probe Classifica
Foundation models for time series
795Frequency masking + SimPSI (Spectrum-preservative map)
3-layer CNN
SimPSI: A Simple Strategy to Preserve Spectral Information in Time Series Data Augmentation
AAAI 2024 · Table 1
Foundation models for time series
894.63BTSFUnsupervised Time-Series Representation Learning with Iterative Bilinear Temporal-Spectral Fusion
ICML 2022 · Table 1
Foundation models for time series
994.6mdDFA Refined Margin Distribution Analysis for Forest Representation Learning
NeurIPS 2019 · Table 1
Kernels and regression theory
1094.27MEGAGraph-Aware Contrasting for Multivariate Time-Series Classification
AAAI 2024 · Table: Comparisons with State-
Foundation models for time series
6 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.