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/ST-LLM

ST-LLM

Reported on 18 benchmarks across 6 tasks · 1 paper · 3 SOTA

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

Reasoning18 results

Generative Visual Question AnsweringonVideoInstruct
gpt-score· 2024-03-30
3.74
best: 4.21 (PPLLaVA-7B)
SOTA
ST-LLM: Large Language Models Are Effective Temporal Learners arXiv:2404.00308
Video-based Generative Performance BenchmarkingonVideoInstruct
gpt-score· 2024-03-30
3.74
best: 4.21 (PPLLaVA-7B)
SOTA
ST-LLM: Large Language Models Are Effective Temporal Learners arXiv:2404.00308
Video Question AnsweringonTVBench
Average Accuracy· 2024-03-30
35.7
best: 63.6 (Seed1.5-VL thinking)
ST-LLM: Large Language Models Are Effective Temporal Learners arXiv:2404.00308
Video Question AnsweringonMVBench
Avg.· 2024-03-30
54.9
best: 69.3 (LinVT-Qwen2-VL (7B))
ST-LLM: Large Language Models Are Effective Temporal Learners arXiv:2404.00308
Video Question AnsweringonMSVD-QA
Accuracy· 2024-03-30
74.6
best: 80.3 (Tarsier (34B))
ST-LLM: Large Language Models Are Effective Temporal Learners arXiv:2404.00308
Video Question AnsweringonMSVD-QA
Confidence Score· 2024-03-30
3.9
best: 2.5 (Video LLaMA-7B)
ST-LLM: Large Language Models Are Effective Temporal Learners arXiv:2404.00308
Video Question AnsweringonMSRVTT-QA
Accuracy· 2024-03-30
63.2
best: 72.4 (Flash-VStream)
ST-LLM: Large Language Models Are Effective Temporal Learners arXiv:2404.00308
Video Question AnsweringonMSRVTT-QA
Confidence Score· 2024-03-30
3.4
best: 1.8 (Video LLaMA-7B)
ST-LLM: Large Language Models Are Effective Temporal Learners arXiv:2404.00308
Video Question AnsweringonActivityNet-QA
Accuracy· 2024-03-30
50.9
best: 61.6 (Tarsier (34B))
ST-LLM: Large Language Models Are Effective Temporal Learners arXiv:2404.00308
Video Question AnsweringonActivityNet-QA
Confidence Score· 2024-03-30
3.3
best: 1.1 (Video LLaMA)
ST-LLM: Large Language Models Are Effective Temporal Learners arXiv:2404.00308
Generative Visual Question AnsweringonVideoInstruct
gpt-score· 2024-03-30
3.23
best: 4.21 (PPLLaVA-7B)
ST-LLM: Large Language Models Are Effective Temporal Learners arXiv:2404.00308
Generative Visual Question AnsweringonVideoInstruct
gpt-score· 2024-03-30
3.05
best: 4.21 (PPLLaVA-7B)
ST-LLM: Large Language Models Are Effective Temporal Learners arXiv:2404.00308
Generative Visual Question AnsweringonVideoInstruct
gpt-score· 2024-03-30
2.93
best: 4.21 (PPLLaVA-7B)
ST-LLM: Large Language Models Are Effective Temporal Learners arXiv:2404.00308
Generative Visual Question AnsweringonVideoInstruct
gpt-score· 2024-03-30
2.81
best: 4.21 (PPLLaVA-7B)
ST-LLM: Large Language Models Are Effective Temporal Learners arXiv:2404.00308
Video-based Generative Performance BenchmarkingonVideoInstruct
gpt-score· 2024-03-30
3.23
best: 4.21 (PPLLaVA-7B)
ST-LLM: Large Language Models Are Effective Temporal Learners arXiv:2404.00308
Video-based Generative Performance BenchmarkingonVideoInstruct
gpt-score· 2024-03-30
3.05
best: 4.21 (PPLLaVA-7B)
ST-LLM: Large Language Models Are Effective Temporal Learners arXiv:2404.00308
Video-based Generative Performance BenchmarkingonVideoInstruct
gpt-score· 2024-03-30
2.93
best: 4.21 (PPLLaVA-7B)
ST-LLM: Large Language Models Are Effective Temporal Learners arXiv:2404.00308
Video-based Generative Performance BenchmarkingonVideoInstruct
gpt-score· 2024-03-30
2.81
best: 4.21 (PPLLaVA-7B)
ST-LLM: Large Language Models Are Effective Temporal Learners arXiv:2404.00308

Natural Language Processing11 results

Visual Question Answering (VQA)onVideoInstruct
gpt-score· 2024-03-30
3.74
best: 4.21 (PPLLaVA-7B)
SOTA
ST-LLM: Large Language Models Are Effective Temporal Learners arXiv:2404.00308
Question AnsweringonMSVD-QA
Accuracy· 2024-03-30
74.6
best: 80.3 (Tarsier (34B))
ST-LLM: Large Language Models Are Effective Temporal Learners arXiv:2404.00308
Question AnsweringonMSVD-QA
Confidence Score· 2024-03-30
3.9
best: 2.5 (Video LLaMA-7B)
ST-LLM: Large Language Models Are Effective Temporal Learners arXiv:2404.00308
Question AnsweringonMSRVTT-QA
Accuracy· 2024-03-30
63.2
best: 72.4 (Flash-VStream)
ST-LLM: Large Language Models Are Effective Temporal Learners arXiv:2404.00308
Question AnsweringonMSRVTT-QA
Confidence Score· 2024-03-30
3.4
best: 1.8 (Video LLaMA-7B)
ST-LLM: Large Language Models Are Effective Temporal Learners arXiv:2404.00308
Question AnsweringonActivityNet-QA
Accuracy· 2024-03-30
50.9
best: 61.6 (Tarsier (34B))
ST-LLM: Large Language Models Are Effective Temporal Learners arXiv:2404.00308
Question AnsweringonActivityNet-QA
Confidence Score· 2024-03-30
3.3
best: 1.1 (Video LLaMA)
ST-LLM: Large Language Models Are Effective Temporal Learners arXiv:2404.00308
Visual Question Answering (VQA)onVideoInstruct
gpt-score· 2024-03-30
3.23
best: 4.21 (PPLLaVA-7B)
ST-LLM: Large Language Models Are Effective Temporal Learners arXiv:2404.00308
Visual Question Answering (VQA)onVideoInstruct
gpt-score· 2024-03-30
3.05
best: 4.21 (PPLLaVA-7B)
ST-LLM: Large Language Models Are Effective Temporal Learners arXiv:2404.00308
Visual Question Answering (VQA)onVideoInstruct
gpt-score· 2024-03-30
2.93
best: 4.21 (PPLLaVA-7B)
ST-LLM: Large Language Models Are Effective Temporal Learners arXiv:2404.00308
Visual Question Answering (VQA)onVideoInstruct
gpt-score· 2024-03-30
2.81
best: 4.21 (PPLLaVA-7B)
ST-LLM: Large Language Models Are Effective Temporal Learners arXiv:2404.00308

Other1 result

Video-based Generative Performance Benchmarking (Correctness of Information)onVideoInstruct
gpt-score· 2024-03-30
3.23
best: 3.85 (PPLLaVA-7B)
ST-LLM: Large Language Models Are Effective Temporal Learners arXiv:2404.00308