Building on the advances of language models, Large Multimodal Models (LMMs) have contributed significant improvements in video understanding. While the current video LMMs utilize advanced Large Language Models (LLMs), they rely on either image or video encoders to process visual inputs, each of which has its own limitations. Image encoders excel at capturing rich spatial details from frame sequences but lack explicit temporal context, which can be important in videos with intricate action sequences. On the other hand, video encoders provide temporal context but are often limited by computational constraints that lead to processing only sparse frames at lower resolutions, resulting in reduced contextual and spatial understanding. To this end, we introduce VideoGPT+, which combines the complementary benefits of the image encoder (for detailed spatial understanding) and the video encoder (for global temporal context modeling). The model processes videos by dividing them into smaller segments and applies an adaptive pooling strategy on features extracted by both image and video encoders. Our architecture showcases improved performance across multiple video benchmarks, including VCGBench, MVBench and Zero-shot question-answering. Further, we develop 112K video-instruction set using a novel semi-automatic annotation pipeline which further improves the model performance. Additionally, to comprehensively evaluate video LMMs, we present VCGBench-Diverse, covering 18 broad video categories such as lifestyle, sports, science, gaming, and surveillance videos. This benchmark with 4,354 question-answer pairs evaluates the generalization of existing LMMs on dense video captioning, spatial and temporal understanding, and complex reasoning, ensuring comprehensive assessment across diverse video types and dynamics. Code: https://github.com/mbzuai-oryx/VideoGPT-plus.

翻译：基于语言模型的进展，大型多模态模型（LMMs）在视频理解领域取得了显著提升。当前视频LMMs虽采用先进的大型语言模型（LLMs），但其视觉输入处理仅依赖图像编码器或视频编码器之一，二者均存在固有局限。图像编码器擅长从帧序列中捕捉丰富的空间细节，但缺乏显式的时间上下文，这在包含复杂动作序列的视频中至关重要。另一方面，视频编码器能提供时间上下文，但常受计算资源限制，仅能处理低分辨率下的稀疏帧，导致上下文与空间理解能力下降。为此，我们提出VideoGPT+，它融合了图像编码器（用于精细空间理解）与视频编码器（用于全局时间上下文建模）的互补优势。该模型通过将视频分割为较小片段进行处理，并对两种编码器提取的特征采用自适应池化策略。我们的架构在多个视频基准测试（包括VCGBench、MVBench和零样本问答任务）中均展现出性能提升。此外，我们通过新型半自动标注流程构建了包含112K样本的视频指令集，进一步提升了模型性能。同时，为全面评估视频LMMs，我们提出了VCGBench-Diverse基准，涵盖生活方式、体育、科学、游戏、监控视频等18个广泛视频类别。该基准包含4,354个问答对，从密集视频描述、时空理解及复杂推理等维度评估现有LMMs的泛化能力，确保对不同视频类型与动态场景的综合评估。代码：https://github.com/mbzuai-oryx/VideoGPT-plus。