Pith. sign in

REVIEW 1 cited by

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

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2410.11417 v1 pith:Y2JXR346 submitted 2024-10-15 cs.CV cs.MM

classification cs.CVcs.MM
keywords temporalvidcompressmemory-enhancedmodelsvideo-llmsvideosvisualcompression
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

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.

Discussion (0). Sign in to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. ViSAGE: Constructing Self-Correcting Memories for Long-Form Video Understanding

    cs.AI 2026-07 conditional novelty 6.0 of 10

    ViSAGE builds entity-centered, self-correcting memories for long-form video understanding and reports state-of-the-art accuracy on M3-Bench and Video-MME-long.

Pith tools