Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/MIST

MIST

Reported on 27 benchmarks across 9 tasks · 4 papers · 7 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision10 results

Video UnderstandingonShanghaiTech Weakly Supervised
AUC-ROC· 2021-04-04
94.83
best: 98.14 (PEL)
MIST: Multiple Instance Self-Training Framework for Video Anomaly Detection arXiv:2104.01633
Video UnderstandingonUCF-Crime
ROC AUC· 2021-04-04
82.3
best: 91.34 (STEAD-Base)
MIST: Multiple Instance Self-Training Framework for Video Anomaly Detection arXiv:2104.01633
VideoonShanghaiTech Weakly Supervised
AUC-ROC· 2021-04-04
94.83
best: 98.14 (PEL)
MIST: Multiple Instance Self-Training Framework for Video Anomaly Detection arXiv:2104.01633
VideoonUCF-Crime
ROC AUC· 2021-04-04
82.3
best: 91.34 (STEAD-Base)
MIST: Multiple Instance Self-Training Framework for Video Anomaly Detection arXiv:2104.01633
3D Anomaly DetectiononUBnormal
AUC-ROC· 2021-04-04
65.32
best: 76.51 (DDRO (SSALA))
MIST: Multiple Instance Self-Training Framework for Video Anomaly Detection arXiv:2104.01633
3D Anomaly DetectiononShanghaiTech Weakly Supervised
AUC-ROC· 2021-04-04
94.83
best: 97.91 (DDRO)
MIST: Multiple Instance Self-Training Framework for Video Anomaly Detection arXiv:2104.01633
3D Anomaly DetectiononShanghaiTech Weakly Supervised
FAR-Normal· 2021-04-04
0.05
best: 1.06 (RTFM)
MIST: Multiple Instance Self-Training Framework for Video Anomaly Detection arXiv:2104.01633
Video Anomaly DetectiononUBnormal
AUC-ROC· 2021-04-04
65.32
best: 76.51 (DDRO (SSALA))
MIST: Multiple Instance Self-Training Framework for Video Anomaly Detection arXiv:2104.01633
Video Anomaly DetectiononShanghaiTech Weakly Supervised
AUC-ROC· 2021-04-04
94.83
best: 97.91 (DDRO)
MIST: Multiple Instance Self-Training Framework for Video Anomaly Detection arXiv:2104.01633
Video Anomaly DetectiononShanghaiTech Weakly Supervised
FAR-Normal· 2021-04-04
0.05
best: 1.06 (RTFM)
MIST: Multiple Instance Self-Training Framework for Video Anomaly Detection arXiv:2104.01633

Miscellaneous8 results

Molecule retrieval from MS/MS spectrumonMassSpecGym
Hit rate @ 1· 2024-10-30
14.64
best: 15.62 (JESTR_NR)
SOTA
MassSpecGym: A benchmark for the discovery and identification of molecules arXiv:2410.23326
Molecule retrieval from MS/MS spectrumonMassSpecGym
Hit rate @ 20· 2024-10-30
59.15
best: 60.55 (JESTR_NR)
SOTA
MassSpecGym: A benchmark for the discovery and identification of molecules arXiv:2410.23326
Molecule retrieval from MS/MS spectrumonMassSpecGym
Hit rate @ 5· 2024-10-30
34.87
best: 37.47 (JESTR_NR)
SOTA
MassSpecGym: A benchmark for the discovery and identification of molecules arXiv:2410.23326
Molecule retrieval from MS/MS spectrum (bonus chemical formulae)onMassSpecGym
Hit rate @ 1· 2024-10-30
9.57
best: 11.85 (JESTR)
SOTA
MassSpecGym: A benchmark for the discovery and identification of molecules arXiv:2410.23326
Molecule retrieval from MS/MS spectrum (bonus chemical formulae)onMassSpecGym
Hit rate @ 20· 2024-10-30
41.12
best: 61.46 (JESTR)
SOTA
MassSpecGym: A benchmark for the discovery and identification of molecules arXiv:2410.23326
Molecule retrieval from MS/MS spectrum (bonus chemical formulae)onMassSpecGym
Hit rate @ 5· 2024-10-30
22.11
best: 33.48 (JESTR_NR)
SOTA
MassSpecGym: A benchmark for the discovery and identification of molecules arXiv:2410.23326
Molecule retrieval from MS/MS spectrumonMassSpecGym
MCES @ 1· 2024-10-30
15.37
best: 30.81 (Random)
MassSpecGym: A benchmark for the discovery and identification of molecules arXiv:2410.23326
Molecule retrieval from MS/MS spectrum (bonus chemical formulae)onMassSpecGym
MCES @ 1· 2024-10-30
12.75
best: 15.04 (DeepSets)
MassSpecGym: A benchmark for the discovery and identification of molecules arXiv:2410.23326

Methodology5 results

Anomaly DetectiononShanghaiTech Weakly Supervised
AUC-ROC· 2021-04-04
94.83
best: 98.14 (PEL)
MIST: Multiple Instance Self-Training Framework for Video Anomaly Detection arXiv:2104.01633
Anomaly DetectiononUCF-Crime
ROC AUC· 2021-04-04
82.3
best: 91.34 (STEAD-Base)
MIST: Multiple Instance Self-Training Framework for Video Anomaly Detection arXiv:2104.01633
Anomaly DetectiononUBnormal
AUC-ROC· 2021-04-04
65.32
best: 76.51 (DDRO (SSALA))
MIST: Multiple Instance Self-Training Framework for Video Anomaly Detection arXiv:2104.01633
Anomaly DetectiononShanghaiTech Weakly Supervised
AUC-ROC· 2021-04-04
94.83
best: 98.14 (PEL)
MIST: Multiple Instance Self-Training Framework for Video Anomaly Detection arXiv:2104.01633
Anomaly DetectiononShanghaiTech Weakly Supervised
FAR-Normal· 2021-04-04
0.05
best: 1.06 (RTFM)
MIST: Multiple Instance Self-Training Framework for Video Anomaly Detection arXiv:2104.01633

Medical3 results

Medical Image SegmentationonSynapse multi-organ CT
Avg DSC· 2023-10-30
86.92
best: 90.66 (Interactive AI-SAM gt box)
MIST: Medical Image Segmentation Transformer with Convolutional Attention Mixing (CAM) Decoder arXiv:2310.19898
Medical Image SegmentationonSynapse multi-organ CT
Avg HD· 2023-10-30
11.07
best: 31.69 (TransUNet)
MIST: Medical Image Segmentation Transformer with Convolutional Attention Mixing (CAM) Decoder arXiv:2310.19898
Medical Image SegmentationonAutomatic Cardiac Diagnosis Challenge (ACDC)
Avg DSC· 2023-10-30
92.56
best: 94.26 (FCT)
MIST: Medical Image Segmentation Transformer with Convolutional Attention Mixing (CAM) Decoder arXiv:2310.19898

Reasoning2 results

Video Question AnsweringonNExT-QA
Accuracy· 2022-12-19
57.2
best: 85.5 (LinVT-Qwen2-VL (7B))
SOTA
MIST: Multi-modal Iterative Spatial-Temporal Transformer for Long-form Video Question Answering arXiv:2212.09522
Video Question AnsweringonSTAR Benchmark
Average Accuracy· 2022-12-19
51.13
best: 67.1 (VLAP (4 frames))
MIST: Multi-modal Iterative Spatial-Temporal Transformer for Long-form Video Question Answering arXiv:2212.09522