ResNetVLLM -- Multi-modal Vision LLM for the Video Understanding Task
It addresses video understanding for AI applications, but appears incremental as it builds on existing cross-modal and zero-shot approaches.
The paper tackles zero-shot video understanding by introducing ResNetVLLM, a cross-modal framework that integrates a ResNet-based visual encoder with a Large Language Model, achieving state-of-the-art performance on benchmarks like MSRVTT-QA and ActivityNet-QA.
In this paper, we introduce ResNetVLLM (ResNet Vision LLM), a novel cross-modal framework for zero-shot video understanding that integrates a ResNet-based visual encoder with a Large Language Model (LLM. ResNetVLLM addresses the challenges associated with zero-shot video models by avoiding reliance on pre-trained video understanding models and instead employing a non-pretrained ResNet to extract visual features. This design ensures the model learns visual and semantic representations within a unified architecture, enhancing its ability to generate accurate and contextually relevant textual descriptions from video inputs. Our experimental results demonstrate that ResNetVLLM achieves state-of-the-art performance in zero-shot video understanding (ZSVU) on several benchmarks, including MSRVTT-QA, MSVD-QA, TGIF-QA FrameQA, and ActivityNet-QA.