CVMMOct 15, 2024

VidCompress: Memory-Enhanced Temporal Compression for Video Understanding in Large Language Models

arXiv:2410.11417v15 citationsh-index: 12
Originality Incremental advance
AI Analysis

This addresses video understanding challenges in multimodal large language models, offering an incremental improvement over prior methods.

The paper tackles the problem of insufficient temporal-spatial interaction and limited visual token capacity in Video-LLMs for video understanding by proposing VidCompress, a memory-enhanced temporal compression method, which significantly outperforms existing models on VideoQA datasets and benchmarks.

Video-based multimodal large language models (Video-LLMs) possess significant potential for video understanding tasks. However, most Video-LLMs treat videos as a sequential set of individual frames, which results in insufficient temporal-spatial interaction that hinders fine-grained comprehension and difficulty in processing longer videos due to limited visual token capacity. To address these challenges, we propose VidCompress, a novel Video-LLM featuring memory-enhanced temporal compression. VidCompress employs a dual-compressor approach: a memory-enhanced compressor captures both short-term and long-term temporal relationships in videos and compresses the visual tokens using a multiscale transformer with a memory-cache mechanism, while a text-perceived compressor generates condensed visual tokens by utilizing Q-Former and integrating temporal contexts into query embeddings with cross attention. Experiments on several VideoQA datasets and comprehensive benchmarks demonstrate that VidCompress efficiently models complex temporal-spatial relations and significantly outperforms existing Video-LLMs.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes