sutdcv / SUTD-TrafficQA Star 45 Code Issues Pull requests [CVPR2021] SUTD-TrafficQA: A Question Answering Benchmark and an Efficient Network for Video Reasoning over Traffic Events paper annotations dataset vqa cvpr video-qa vqa-dataset traffic-events multimodal multimodal-deep-learning cvpr2021 video-reasoning Updated Dec 13, 2022 JavaScript
scofield7419 / Video-of-Thought Star 10 Code Issues Pull requests Codes for ICML 2024 paper: "Video-of-Thought: Step-by-Step Video Reasoning from Perception to Cognition" video video-reasoning chain-of-thought multimodal-large-language-models chain-of-thought-reasoning video-model Updated Jun 24, 2024