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/VideoGPT+

VideoGPT+

Reported on 49 benchmarks across 7 tasks · 1 paper · 12 SOTA

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

Reasoning32 results

Generative Visual Question AnsweringonVideoInstruct
Consistency· 2024-06-13
3.39
best: 3.81 (PPLLaVA-7B-dpo)
SOTA
VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding arXiv:2406.09418
Video-based Generative Performance BenchmarkingonVideoInstruct
Consistency· 2024-06-13
3.39
best: 3.81 (PPLLaVA-7B-dpo)
SOTA
VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding arXiv:2406.09418
Video Question AnsweringonTVBench
Average Accuracy· 2024-06-13
41.7
best: 63.6 (Seed1.5-VL thinking)
VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding arXiv:2406.09418
Video Question AnsweringonMVBench
Avg.· 2024-06-13
58.7
best: 69.3 (LinVT-Qwen2-VL (7B))
VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding arXiv:2406.09418
Video Question AnsweringonMSVD-QA
Accuracy· 2024-06-13
72.4
best: 80.3 (Tarsier (34B))
VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding arXiv:2406.09418
Video Question AnsweringonMSVD-QA
Confidence Score· 2024-06-13
3.6
best: 2.5 (Video LLaMA-7B)
VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding arXiv:2406.09418
Video Question AnsweringonTGIF-QA
Accuracy· 2024-06-13
74.6
best: 82.5 (Tarsier (34B))
VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding arXiv:2406.09418
Video Question AnsweringonTGIF-QA
Confidence Score· 2024-06-13
4.1
best: 2.3 (Video Chat-7B)
VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding arXiv:2406.09418
Video Question AnsweringonMSRVTT-QA
Accuracy· 2024-06-13
60.6
best: 72.4 (Flash-VStream)
VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding arXiv:2406.09418
Video Question AnsweringonMSRVTT-QA
Confidence Score· 2024-06-13
3.6
best: 1.8 (Video LLaMA-7B)
VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding arXiv:2406.09418
Video Question AnsweringonActivityNet-QA
Accuracy· 2024-06-13
50.6
best: 61.6 (Tarsier (34B))
VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding arXiv:2406.09418
Video Question AnsweringonActivityNet-QA
Confidence Score· 2024-06-13
3.6
best: 1.1 (Video LLaMA)
VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding arXiv:2406.09418
Generative Visual Question AnsweringonVideoInstruct
Contextual Understanding· 2024-06-13
3.74
best: 4.21 (PPLLaVA-7B-dpo)
VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding arXiv:2406.09418
Generative Visual Question AnsweringonVideoInstruct
Correctness of Information· 2024-06-13
3.27
best: 3.85 (PPLLaVA-7B-dpo)
VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding arXiv:2406.09418
Generative Visual Question AnsweringonVideoInstruct
Detail Orientation· 2024-06-13
3.18
best: 3.56 (PPLLaVA-7B-dpo)
VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding arXiv:2406.09418
Generative Visual Question AnsweringonVideoInstruct
Temporal Understanding· 2024-06-13
2.83
best: 3.23 (VLM-RLAIF)
VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding arXiv:2406.09418
Generative Visual Question AnsweringonVideoInstruct
mean· 2024-06-13
3.28
best: 3.73 (PPLLaVA-7B-dpo)
VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding arXiv:2406.09418
Generative Visual Question AnsweringonVideoInstruct
gpt-score· 2024-06-13
3.74
best: 4.21 (PPLLaVA-7B)
VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding arXiv:2406.09418
Generative Visual Question AnsweringonVideoInstruct
gpt-score· 2024-06-13
3.27
best: 4.21 (PPLLaVA-7B)
VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding arXiv:2406.09418
Generative Visual Question AnsweringonVideoInstruct
gpt-score· 2024-06-13
3.18
best: 4.21 (PPLLaVA-7B)
VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding arXiv:2406.09418
Generative Visual Question AnsweringonVideoInstruct
gpt-score· 2024-06-13
2.83
best: 4.21 (PPLLaVA-7B)
VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding arXiv:2406.09418
Generative Visual Question AnsweringonVideoInstruct
gpt-score· 2024-06-13
3.39
best: 4.21 (PPLLaVA-7B)
VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding arXiv:2406.09418
Video-based Generative Performance BenchmarkingonVideoInstruct
Contextual Understanding· 2024-06-13
3.74
best: 4.21 (PPLLaVA-7B-dpo)
VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding arXiv:2406.09418
Video-based Generative Performance BenchmarkingonVideoInstruct
Correctness of Information· 2024-06-13
3.27
best: 3.85 (PPLLaVA-7B-dpo)
VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding arXiv:2406.09418
Video-based Generative Performance BenchmarkingonVideoInstruct
Detail Orientation· 2024-06-13
3.18
best: 3.56 (PPLLaVA-7B-dpo)
VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding arXiv:2406.09418
Video-based Generative Performance BenchmarkingonVideoInstruct
Temporal Understanding· 2024-06-13
2.83
best: 3.23 (VLM-RLAIF)
VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding arXiv:2406.09418
Video-based Generative Performance BenchmarkingonVideoInstruct
mean· 2024-06-13
3.28
best: 3.73 (PPLLaVA-7B-dpo)
VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding arXiv:2406.09418
Video-based Generative Performance BenchmarkingonVideoInstruct
gpt-score· 2024-06-13
3.74
best: 4.21 (PPLLaVA-7B)
VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding arXiv:2406.09418
Video-based Generative Performance BenchmarkingonVideoInstruct
gpt-score· 2024-06-13
3.27
best: 4.21 (PPLLaVA-7B)
VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding arXiv:2406.09418
Video-based Generative Performance BenchmarkingonVideoInstruct
gpt-score· 2024-06-13
3.18
best: 4.21 (PPLLaVA-7B)
VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding arXiv:2406.09418
Video-based Generative Performance BenchmarkingonVideoInstruct
gpt-score· 2024-06-13
2.83
best: 4.21 (PPLLaVA-7B)
VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding arXiv:2406.09418
Video-based Generative Performance BenchmarkingonVideoInstruct
gpt-score· 2024-06-13
3.39
best: 4.21 (PPLLaVA-7B)
VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding arXiv:2406.09418

Natural Language Processing19 results

Visual Question Answering (VQA)onVideoInstruct
Consistency· 2024-06-13
3.39
best: 3.81 (PPLLaVA-7B-dpo)
SOTA
VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding arXiv:2406.09418
Question AnsweringonMSVD-QA
Accuracy· 2024-06-13
72.4
best: 80.3 (Tarsier (34B))
VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding arXiv:2406.09418
Question AnsweringonMSVD-QA
Confidence Score· 2024-06-13
3.6
best: 2.5 (Video LLaMA-7B)
VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding arXiv:2406.09418
Question AnsweringonTGIF-QA
Accuracy· 2024-06-13
74.6
best: 82.5 (Tarsier (34B))
VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding arXiv:2406.09418
Question AnsweringonTGIF-QA
Confidence Score· 2024-06-13
4.1
best: 2.3 (Video Chat-7B)
VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding arXiv:2406.09418
Question AnsweringonMSRVTT-QA
Accuracy· 2024-06-13
60.6
best: 72.4 (Flash-VStream)
VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding arXiv:2406.09418
Question AnsweringonMSRVTT-QA
Confidence Score· 2024-06-13
3.6
best: 1.8 (Video LLaMA-7B)
VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding arXiv:2406.09418
Question AnsweringonActivityNet-QA
Accuracy· 2024-06-13
50.6
best: 61.6 (Tarsier (34B))
VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding arXiv:2406.09418
Question AnsweringonActivityNet-QA
Confidence Score· 2024-06-13
3.6
best: 1.1 (Video LLaMA)
VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding arXiv:2406.09418
Visual Question Answering (VQA)onVideoInstruct
Contextual Understanding· 2024-06-13
3.74
best: 4.21 (PPLLaVA-7B-dpo)
VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding arXiv:2406.09418
Visual Question Answering (VQA)onVideoInstruct
Correctness of Information· 2024-06-13
3.27
best: 3.85 (PPLLaVA-7B-dpo)
VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding arXiv:2406.09418
Visual Question Answering (VQA)onVideoInstruct
Detail Orientation· 2024-06-13
3.18
best: 3.56 (PPLLaVA-7B-dpo)
VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding arXiv:2406.09418
Visual Question Answering (VQA)onVideoInstruct
Temporal Understanding· 2024-06-13
2.83
best: 3.23 (VLM-RLAIF)
VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding arXiv:2406.09418
Visual Question Answering (VQA)onVideoInstruct
mean· 2024-06-13
3.28
best: 3.73 (PPLLaVA-7B-dpo)
VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding arXiv:2406.09418
Visual Question Answering (VQA)onVideoInstruct
gpt-score· 2024-06-13
3.74
best: 4.21 (PPLLaVA-7B)
VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding arXiv:2406.09418
Visual Question Answering (VQA)onVideoInstruct
gpt-score· 2024-06-13
3.27
best: 4.21 (PPLLaVA-7B)
VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding arXiv:2406.09418
Visual Question Answering (VQA)onVideoInstruct
gpt-score· 2024-06-13
3.18
best: 4.21 (PPLLaVA-7B)
VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding arXiv:2406.09418
Visual Question Answering (VQA)onVideoInstruct
gpt-score· 2024-06-13
2.83
best: 4.21 (PPLLaVA-7B)
VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding arXiv:2406.09418
Visual Question Answering (VQA)onVideoInstruct
gpt-score· 2024-06-13
3.39
best: 4.21 (PPLLaVA-7B)
VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding arXiv:2406.09418

Computer Vision9 results

VCGBench-DiverseonVideoInstruct
Consistency· 2024-06-13
2.59
SOTA
VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding arXiv:2406.09418
VCGBench-DiverseonVideoInstruct
Contextual Understanding· 2024-06-13
2.81
SOTA
VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding arXiv:2406.09418
VCGBench-DiverseonVideoInstruct
Correctness of Information· 2024-06-13
2.46
SOTA
VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding arXiv:2406.09418
VCGBench-DiverseonVideoInstruct
Dense Captioning· 2024-06-13
1.38
SOTA
VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding arXiv:2406.09418
VCGBench-DiverseonVideoInstruct
Detail Orientation· 2024-06-13
2.73
SOTA
VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding arXiv:2406.09418
VCGBench-DiverseonVideoInstruct
Reasoning· 2024-06-13
3.63
SOTA
VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding arXiv:2406.09418
VCGBench-DiverseonVideoInstruct
Spatial Understanding· 2024-06-13
2.8
SOTA
VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding arXiv:2406.09418
VCGBench-DiverseonVideoInstruct
Temporal Understanding· 2024-06-13
1.78
SOTA
VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding arXiv:2406.09418
VCGBench-DiverseonVideoInstruct
mean· 2024-06-13
2.47
SOTA
VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding arXiv:2406.09418

Other1 result

Video-based Generative Performance Benchmarking (Correctness of Information)onVideoInstruct
gpt-score· 2024-06-13
3.27
best: 3.85 (PPLLaVA-7B)
VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding arXiv:2406.09418