The DOI matches its Crossref record; 73 of the 76 references it cites were found in a registry or an index.
MovieChat: From Dense Token to Sparse Memory for Long Video Understanding
Open accessAbstract
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. The code, models and data can be found in https://reself.github.io/MovieChat.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“By making plans and structured environment representations the readable and writable core of working memory, agents can maintain goal consistency and revise strategies robustly against perception failures (Song et al., 2023).”
From Memory in the Age of AI Agents (2025) · cites this paper as Song et al., 2023
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset
Carreira, J., & Zisserman, A. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.502 · Cited by 9,570
Human Memory: A Proposed System and its Control Processes
Atkinson, R. C., & Shiffrin, R. M. (1968) · Psychology of Learning and Motivation · doi:10.1016/s0079-7421(08)60422-3 · Cited by 7,216
LLaMA: Open and Efficient Foundation Language Models
Touvron, H., Lavril, T., Izacard, G., Martinet, X., Lachaux, M.-A., Lacroix, T., Rozière, B., Goyal, N., Hambro, E., Azhar, F., et al. (2023) · arXiv · doi:10.48550/arxiv.2302.13971 · Cited by 4,602
ViViT: A Video Vision Transformer
Arnab, A., Dehghani, M., Heigold, G., Sun, C., Lucic, M., & Schmid, C. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00676 · Cited by 2,767
Llama 2: Open Foundation and Fine-Tuned Chat Models
Touvron, H., Martin, L., Stone, K., Albert, P., Almahairi, A., Babaei, Y., Bashlykov, N., Batra, S., Bhargava, P., Bhosale, S., et al. (2023) · arXiv · doi:10.48550/arxiv.2307.09288 · Cited by 2,604
Self-citationLiu, Z., Ning, J., Cao, Y., Wei, Y., Zhang, Z., Lin, S., & Hu, H. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00320 · Cited by 2,294
MSR-VTT: A Large Video Description Dataset for Bridging Video and Language
Xu, J., Mei, T., Yao, T., & Rui, Y. (2016) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2016.571 · Cited by 1,888
Li, J., Li, D., Xiong, C., & Hoi, S. (2022) · arXiv · doi:10.48550/arxiv.2201.12086 · Cited by 1,741
Research works printed but not linked: 10
- 2023, Meet claude
- Awad, 2018, Trecvid 2018: Benchmarking video activity detection, video captioning and matching, video storytelling linking and video search
- 10.1109/ICCV48922.2021.00175 · DOI · Paper page
- Chiang, 2023, Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality.
- Driess, 2023, Palme: An embodied multimodal language model.
- 10.1007/springerreference_9081 · DOI
- 2021, Gpt3.5, 2021.
- 2023, Gpt-4 technical report.
- Su, 2023, Bert position encoding.
- Taori, 2023, Stanford alpaca: An instruction-following llama model
Cited by
Sorted by citations
Multimodal Large Language Models in Health Care: Applications, Challenges, and Future Outlook.
AlSaad, R., Abd-alrazaq, A., Boughorbel, S., Ahmed, A., Renault, M.-A., Damseh, R., & Sheikh, J. (2024) · Journal of medical Internet research · doi:10.2196/59505 · Cited by 349
Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis
Fu, C., Dai, Y., Luo, Y., Li, L., Ren, S., Zhang, R., Wang, Z., Zhou, C., Shen, Y., Zhang, M., et al. (2025) · 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52734.2025.02245 · Cited by 291
LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models
Li, Y., Wang, C., & Jia, J. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72952-2_19 · Cited by 403
TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding
Ren, S., Yao, L., Li, S., Sun, X., & Hou, L. (2024) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52733.2024.01357 · Cited by 277
VideoAgent: Long-Form Video Understanding with Large Language Model as Agent
Wang, X., Zhang, Y., Zohar, O., & Yeung, S. Y. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72989-8_4 · Cited by 196
Self-citation
Metadata
- Authors
- Song, E., Chai, W., Wang, G., Zhang, Y., Zhou, H., Wu, F., Chi, H., Guo, X., Ye, T., Zhang, Y., Lu, Y., Hwang, J.-N., & Wang, G.
- Affiliations
- Zhejiang University (CN)
- University of Washington (US)
- Donghua University (CN)
- Microsoft Research Asia (China) (CN)
- Hong Kong University of Science and Technology (GZ)
- ORCID
- Venue
- 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2024-06-16
- Pages
- 18221-18232
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W4402702917
- Cited by
- 176
- References
- 76
- Citations by year
- 2026: 82 · 2025: 60 · 2024: 32
- FWCI
- 35.92
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- Rare & Special e-Zone (The Hong Kong University of Science and Technology) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Key R&D Program of China (2022ZD0162000)
- National Natural Science Foundation of China (62106219,62206046)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Human Pose and Action Recognition
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Video Analysis and Summarization
- Keywords
- long video understanding, video foundation models, large language models, temporal relations
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
