Pith. sign in

REVIEW 12 cited by

MovieChat: From Dense Token to Sparse Memory for Long Video Understanding

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2307.16449 v4 pith:ZUT2E4YM submitted 2023-07-31 cs.CV

Enxin Song , Wenhao Chai , Guanhong Wang , Yucheng Zhang , Haoyang Zhou , Feiyang Wu , Haozhe Chi , Xun Guo
show 5 more authors
Tian Ye Yanting Zhang Yan Lu Jenq-Neng Hwang Gaoang Wang
This is my paper
classification cs.CV
keywords memoryvideolongmoviechatunderstandingchallengesmodelsovercome
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Recently, integrating video foundation models and large language models to build a video understanding system can overcome the limitations of specific pre-defined vision tasks. Yet, existing systems can only handle videos with very few frames. For long videos, the computation complexity, memory cost, and long-term temporal connection impose additional challenges. Taking advantage of the Atkinson-Shiffrin memory model, with tokens in Transformers being employed as the carriers of memory in combination with our specially designed memory mechanism, we propose the MovieChat to overcome these challenges. MovieChat achieves state-of-the-art performance in long video understanding, along with the released MovieChat-1K benchmark with 1K long video and 14K manual annotations for validation of the effectiveness of our method.

Discussion (0). Sign in to comment.

Forward citations

Cited by 12 Pith papers

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

  1. A Benchmark for Omni-Modal Reasoning in Long Videos

    cs.CV 2025-12 reject novelty 7.0 of 10

    A new 45-minute-scale omni-modal video Q&A benchmark and a training-free retrieval-refine agent, whose reported agent score (66.64% in the abstract) is not supported by the paper's own main results (44.66%).

  2. Movie Facts and Fibs (MF$^2$): A Benchmark for Long Movie Understanding

    cs.CV 2025-06 conditional novelty 7.0 of 10

    MF2 evaluates long-movie understanding by asking models to classify fact/fib claim pairs; the best model trails humans by 23.5 points in pairwise accuracy.

  3. Diagnosing Long-Video Quantitative Reasoning in Multimodal LLMs via Enumeration and Counting

    cs.CV 2026-03 accept novelty 6.5 of 10

    EC-Bench finds best MLLMs score 29.98% enumeration F1 and 23.74% counting accuracy on 152 hour-scale videos, with errors driven by instance identification and temporal grounding rather than arithmetic.

  4. What to Keep, What to Forget: A Rate--Distortion View of Memory Compaction in LLMs and Agents

    cs.LG 2026-07 conditional novelty 6.0 of 10

    KV-cache eviction, prompt compression, recurrent state bounding, and agent memory consolidation are unified as one rate-distortion problem with a shared lower bound, shared failure mode, and transferable mechanisms.

  5. DELTAVID: Enhancing Fine-Grained Spatiotemporal Perception with Cross-Video Differences

    cs.CV 2026-06 conditional novelty 6.0 of 10

    Rule-reward training on controllable cross-video differences (Grounding + MCQ) improves Video MLLM local spatiotemporal evidence localization and transfers to general video QA benchmarks.

  6. AuroraLong: Bringing RNNs Back to Efficient Open-Ended Video Understanding

    cs.CV 2025-07 conditional novelty 6.0 of 10

    A 2B-parameter video-language model using an RWKV linear-RNN backbone and sorted token merging achieves competitive long-video QA accuracy with far lower memory cost than transformer-based models.

  7. LLaVA-Scissor: Token Compression with Semantic Connected Components for Video LLMs

    cs.CV 2025-06 conditional novelty 6.0 of 10

    A training-free token compression method using semantic connected components in space and time keeps video understanding accuracy high even when retaining only 5-10% of visual tokens.

  8. EffiVLM-BENCH: A Comprehensive Benchmark for Evaluating Training-Free Acceleration in Large Vision-Language Models

    cs.CL 2025-05 conditional novelty 6.0 of 10

    EffiVLM-Bench is a benchmark study showing token compression is task- and model-dependent, KV cache methods are more loyal, and parameter compression preserves accuracy better at typical ratios.

  9. Less Data, Faster Convergence: Goal-Driven Data Optimization for Multimodal Instruction Tuning

    cs.CV 2026-03 conditional novelty 5.5 of 10

    Goal-driven selection of 1× multimodal instruction subsets reaches a 512k Uni-10x baseline after ~27–35k samples and improves accuracy by up to +3.08 pp under a fixed Qwen3-VL recipe.

  10. Task-Aware KV Compression For Cost-Effective Long Video Understanding

    cs.CV 2025-06 conditional novelty 5.0 of 10

    Video-X2L uses bi-level KV compression with task-aware selective reloading to improve long-video QA accuracy and reduce decode-time memory versus uniform KV compression.

  11. Video-XL-2: Towards Very Long-Video Understanding Through Task-Aware KV Sparsification

    cs.CV 2025-06 conditional novelty 5.0 of 10

    Video-XL-2 cuts long-video inference cost with chunked pre-filling and query-gated dense-or-sparse KV reloading, reporting half the FLOPs and a third less decoding memory at roughly equal benchmark scores.

  12. Infinite Video Understanding

    cs.CV 2025-07 conditional novelty 3.0 of 10

    The paper argues that video understanding research should aim at processing streams of arbitrary, unbounded duration and outlines the challenges, directions, and metrics needed.

Pith tools