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/MA-LMM

MA-LMM

Reported on 9 benchmarks across 5 tasks · 1 paper · 4 SOTA

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

Computer Vision6 results

VideoonBreakfast
Accuracy (%)· 2024-04-08
93
best: 95.2 (HERMES)
SOTA
MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding arXiv:2404.05726
VideoonCOIN
Accuracy (%)· 2024-04-08
93.2
best: 93.5 (HERMES)
SOTA
MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding arXiv:2404.05726
Video ClassificationonBreakfast
Accuracy (%)· 2024-04-08
93
best: 95.2 (HERMES)
SOTA
MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding arXiv:2404.05726
Video ClassificationonCOIN
Accuracy (%)· 2024-04-08
93.2
best: 93.5 (HERMES)
SOTA
MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding arXiv:2404.05726
Video CaptioningonYouCook2
CIDEr· 2024-04-08
1.31
best: 116.4 (HowToCaption)
MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding arXiv:2404.05726
Video CaptioningonYouCook2
METEOR· 2024-04-08
17.6
best: 22.56 (UniVL + MELTR)
MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding arXiv:2404.05726

Reasoning2 results

Video Question AnsweringonActivityNet-QA
Accuracy· 2024-04-08
49.8
best: 61.6 (Tarsier (34B))
MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding arXiv:2404.05726
Video Question AnsweringonMSRVTT-QA
Accuracy· 2024-04-08
48.5
best: 72.4 (Flash-VStream)
MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding arXiv:2404.05726

Natural Language Processing1 result

Visual Question Answering (VQA)onMSVD-QA
Accuracy· 2024-04-08
0.606
best: 0.61 (VLAB)
MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding arXiv:2404.05726