VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding

Benchmark Model Rank Results
vcgbench-diverse-on-videoinstructVideoGPT+#1mean: 2.47Correctness of Information: 2.46Detail Orientation: 2.73…
video-based-generative-performance-benchmarking-detail-orientation-on-videoinstructVideoGPT+#3gpt-score: 3.18
video-based-generative-performance-benchmarking-temporal-understanding-on-videoinstructVideoGPT+#3gpt-score: 2.83
video-based-generative-performance-benchmarking-consistency-on-videoinstructVideoGPT+#4gpt-score: 3.39
video-based-generative-performance-benchmarking-contextual-understanding-on-videoinstructVideoGPT+#6gpt-score: 3.74
video-based-generative-performance-benchmarking-correctness-of-information-on-videoinstructVideoGPT+#6gpt-score: 3.27
video-based-generative-performance-benchmarking-on-videoinstructVideoGPT+#7mean: 3.28Correctness of Information: 3.27Detail Orientation: 3.18…
zeroshot-video-question-answer-on-tgif-qaVideoGPT+#8Accuracy: 74.6Confidence Score: 4.1
zeroshot-video-question-answer-on-activitynet-qaVideoGPT+#11Accuracy: 50.6Confidence Score: 3.6
zeroshot-video-question-answer-on-msrvtt-qaVideoGPT+#12Accuracy: 60.6Confidence Score: 3.6
zeroshot-video-question-answer-on-msvd-qaVideoGPT+#15Accuracy: 72.4Confidence Score: 3.6
video-question-answering-on-tvbenchVideoGPT+#18Average Accuracy: 41.7
video-question-answering-on-mvbenchVideoGPT+#74Avg.: 58.7