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/Chat-UniVi

Chat-UniVi

Reported on 35 benchmarks across 7 tasks · 1 paper · 29 SOTA

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

Reasoning24 results

Generative Visual Question AnsweringonVideoInstruct
Consistency· 2023-11-14
2.81
best: 3.81 (PPLLaVA-7B-dpo)
SOTA
Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding arXiv:2311.08046
Generative Visual Question AnsweringonVideoInstruct
Contextual Understanding· 2023-11-14
3.46
best: 4.21 (PPLLaVA-7B-dpo)
SOTA
Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding arXiv:2311.08046
Generative Visual Question AnsweringonVideoInstruct
Correctness of Information· 2023-11-14
2.89
best: 3.85 (PPLLaVA-7B-dpo)
SOTA
Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding arXiv:2311.08046
Generative Visual Question AnsweringonVideoInstruct
Detail Orientation· 2023-11-14
2.91
best: 3.56 (PPLLaVA-7B-dpo)
SOTA
Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding arXiv:2311.08046
Generative Visual Question AnsweringonVideoInstruct
Temporal Understanding· 2023-11-14
2.39
best: 3.23 (VLM-RLAIF)
SOTA
Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding arXiv:2311.08046
Generative Visual Question AnsweringonVideoInstruct
mean· 2023-11-14
2.99
best: 3.73 (PPLLaVA-7B-dpo)
SOTA
Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding arXiv:2311.08046
Generative Visual Question AnsweringonVideoInstruct
gpt-score· 2023-11-14
3.46
best: 4.21 (PPLLaVA-7B)
SOTA
Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding arXiv:2311.08046
Video-based Generative Performance BenchmarkingonVideoInstruct
Consistency· 2023-11-14
2.81
best: 3.81 (PPLLaVA-7B-dpo)
SOTA
Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding arXiv:2311.08046
Video-based Generative Performance BenchmarkingonVideoInstruct
Contextual Understanding· 2023-11-14
3.46
best: 4.21 (PPLLaVA-7B-dpo)
SOTA
Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding arXiv:2311.08046
Video-based Generative Performance BenchmarkingonVideoInstruct
Correctness of Information· 2023-11-14
2.89
best: 3.85 (PPLLaVA-7B-dpo)
SOTA
Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding arXiv:2311.08046
Video-based Generative Performance BenchmarkingonVideoInstruct
Detail Orientation· 2023-11-14
2.91
best: 3.56 (PPLLaVA-7B-dpo)
SOTA
Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding arXiv:2311.08046
Video-based Generative Performance BenchmarkingonVideoInstruct
Temporal Understanding· 2023-11-14
2.39
best: 3.23 (VLM-RLAIF)
SOTA
Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding arXiv:2311.08046
Video-based Generative Performance BenchmarkingonVideoInstruct
mean· 2023-11-14
2.99
best: 3.73 (PPLLaVA-7B-dpo)
SOTA
Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding arXiv:2311.08046
Video-based Generative Performance BenchmarkingonVideoInstruct
gpt-score· 2023-11-14
3.46
best: 4.21 (PPLLaVA-7B)
SOTA
Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding arXiv:2311.08046
Video Question AnsweringonActivityNet-QA
Accuracy· 2023-11-14
46.1
best: 61.6 (Tarsier (34B))
Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding arXiv:2311.08046
Video Question AnsweringonActivityNet-QA
Confidence Score· 2023-11-14
3.3
best: 1.1 (Video LLaMA)
Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding arXiv:2311.08046
Generative Visual Question AnsweringonVideoInstruct
gpt-score· 2023-11-14
2.89
best: 4.21 (PPLLaVA-7B)
Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding arXiv:2311.08046
Generative Visual Question AnsweringonVideoInstruct
gpt-score· 2023-11-14
2.91
best: 4.21 (PPLLaVA-7B)
Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding arXiv:2311.08046
Generative Visual Question AnsweringonVideoInstruct
gpt-score· 2023-11-14
2.39
best: 4.21 (PPLLaVA-7B)
Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding arXiv:2311.08046
Generative Visual Question AnsweringonVideoInstruct
gpt-score· 2023-11-14
2.81
best: 4.21 (PPLLaVA-7B)
Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding arXiv:2311.08046
Video-based Generative Performance BenchmarkingonVideoInstruct
gpt-score· 2023-11-14
2.89
best: 4.21 (PPLLaVA-7B)
Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding arXiv:2311.08046
Video-based Generative Performance BenchmarkingonVideoInstruct
gpt-score· 2023-11-14
2.91
best: 4.21 (PPLLaVA-7B)
Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding arXiv:2311.08046
Video-based Generative Performance BenchmarkingonVideoInstruct
gpt-score· 2023-11-14
2.39
best: 4.21 (PPLLaVA-7B)
Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding arXiv:2311.08046
Video-based Generative Performance BenchmarkingonVideoInstruct
gpt-score· 2023-11-14
2.81
best: 4.21 (PPLLaVA-7B)
Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding arXiv:2311.08046

Natural Language Processing13 results

Visual Question Answering (VQA)onVideoInstruct
Consistency· 2023-11-14
2.81
best: 3.81 (PPLLaVA-7B-dpo)
SOTA
Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding arXiv:2311.08046
Visual Question Answering (VQA)onVideoInstruct
Contextual Understanding· 2023-11-14
3.46
best: 4.21 (PPLLaVA-7B-dpo)
SOTA
Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding arXiv:2311.08046
Visual Question Answering (VQA)onVideoInstruct
Correctness of Information· 2023-11-14
2.89
best: 3.85 (PPLLaVA-7B-dpo)
SOTA
Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding arXiv:2311.08046
Visual Question Answering (VQA)onVideoInstruct
Detail Orientation· 2023-11-14
2.91
best: 3.56 (PPLLaVA-7B-dpo)
SOTA
Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding arXiv:2311.08046
Visual Question Answering (VQA)onVideoInstruct
Temporal Understanding· 2023-11-14
2.39
best: 3.23 (VLM-RLAIF)
SOTA
Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding arXiv:2311.08046
Visual Question Answering (VQA)onVideoInstruct
mean· 2023-11-14
2.99
best: 3.73 (PPLLaVA-7B-dpo)
SOTA
Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding arXiv:2311.08046
Visual Question Answering (VQA)onVideoInstruct
gpt-score· 2023-11-14
3.46
best: 4.21 (PPLLaVA-7B)
SOTA
Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding arXiv:2311.08046
Question AnsweringonActivityNet-QA
Accuracy· 2023-11-14
46.1
best: 61.6 (Tarsier (34B))
Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding arXiv:2311.08046
Question AnsweringonActivityNet-QA
Confidence Score· 2023-11-14
3.3
best: 1.1 (Video LLaMA)
Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding arXiv:2311.08046
Visual Question Answering (VQA)onVideoInstruct
gpt-score· 2023-11-14
2.89
best: 4.21 (PPLLaVA-7B)
Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding arXiv:2311.08046
Visual Question Answering (VQA)onVideoInstruct
gpt-score· 2023-11-14
2.91
best: 4.21 (PPLLaVA-7B)
Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding arXiv:2311.08046
Visual Question Answering (VQA)onVideoInstruct
gpt-score· 2023-11-14
2.39
best: 4.21 (PPLLaVA-7B)
Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding arXiv:2311.08046
Visual Question Answering (VQA)onVideoInstruct
gpt-score· 2023-11-14
2.81
best: 4.21 (PPLLaVA-7B)
Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding arXiv:2311.08046

Computer Vision9 results

VCGBench-DiverseonVideoInstruct
Consistency· 2023-11-14
2.36
best: 2.59 (VideoGPT+)
SOTA
Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding arXiv:2311.08046
VCGBench-DiverseonVideoInstruct
Contextual Understanding· 2023-11-14
2.66
best: 2.81 (VideoGPT+)
SOTA
Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding arXiv:2311.08046
VCGBench-DiverseonVideoInstruct
Correctness of Information· 2023-11-14
2.29
best: 2.46 (VideoGPT+)
SOTA
Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding arXiv:2311.08046
VCGBench-DiverseonVideoInstruct
Dense Captioning· 2023-11-14
1.33
best: 1.38 (VideoGPT+)
SOTA
Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding arXiv:2311.08046
VCGBench-DiverseonVideoInstruct
Spatial Understanding· 2023-11-14
2.36
best: 2.8 (VideoGPT+)
SOTA
Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding arXiv:2311.08046
VCGBench-DiverseonVideoInstruct
Temporal Understanding· 2023-11-14
1.56
best: 1.78 (VideoGPT+)
SOTA
Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding arXiv:2311.08046
VCGBench-DiverseonVideoInstruct
mean· 2023-11-14
2.29
best: 2.47 (VideoGPT+)
SOTA
Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding arXiv:2311.08046
VCGBench-DiverseonVideoInstruct
Detail Orientation· 2023-11-14
2.56
best: 2.73 (VideoGPT+)
Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding arXiv:2311.08046
VCGBench-DiverseonVideoInstruct
Reasoning· 2023-11-14
3.59
best: 3.63 (VideoGPT+)
Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding arXiv:2311.08046

Other1 result

Video-based Generative Performance Benchmarking (Correctness of Information)onVideoInstruct
gpt-score· 2023-11-14
2.89
best: 3.85 (PPLLaVA-7B)
SOTA
Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding arXiv:2311.08046