Papers › MovieChat+: Question-aware Sparse Memory for Long Video Question Answering

MovieChat+: Question-aware Sparse Memory for Long Video Question Answering

26 Apr 2024arXiv:2404.17176archive 2025-07-28

Enxin Song, Wenhao Chai, Tian Ye, Jenq-Neng Hwang, Xi Li, Gaoang Wang

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 methods either employ complex spatial-temporal modules or rely heavily on additional perception models to extract temporal features for video understanding, and they only perform well on short videos. For long videos, the computational complexity and memory costs associated with long-term temporal connections are significantly increased, posing 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 MovieChat to overcome these challenges. We lift pre-trained multi-modal large language models for understanding long videos without incorporating additional trainable temporal modules, employing a zero-shot approach. MovieChat achieves state-of-the-art performance in long video understanding, along with the released MovieChat-1K benchmark with 1K long video, 2K temporal grounding labels, and 14K manual annotations for validation of the effectiveness of our method. The code along with the dataset can be accessed via the following https://github.com/rese1f/MovieChat.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2404.17176")

Code

Syntology Ran 11 of 14 code samples harvested from 1 repository linked to this paper; 3 have no recorded run. Of those that ran: 2 ran · honoured contract; 1 ran · violated contract; 1 ran · our draft was wrong; 2 ran · fixture could not drive it; 5 ran with no contract checked.

By repository: official repository: 14 samples from 1 repository, 11 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

rese1f/MovieChat officialmentioned in papermentioned on GitHubpytorchBSD-3-Clause report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

14 samples harvested; 11 ran; 2 honoured the contract we drafted; 3 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

2ran · honoured contract
1ran · violated contract
1ran · our draft was wrong
2ran · fixture could not drive it
5ran
3unverified

Licence: 0 of the 14 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from rese1f/MovieChat. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

apply_rotary_pos_emb rese1f/MovieChat/MovieChat/models/modeling_llama.py official repository ran · fixture could not drive it BSD-3-Clause (permissive) · 9b4dff79d5e6102c · report
bipartite_soft_matching rese1f/MovieChat/MovieChat/models/eva_vit_with_tome.py official repository ran BSD-3-Clause (permissive) · 54a7a818ecf43861 · report
cast_if_src_dtype rese1f/MovieChat/MovieChat/models/helpers.py official repository ran · fixture could not drive it BSD-3-Clause (permissive) · 751b1c8ccbe160c4 · report
disabled_train rese1f/MovieChat/MovieChat/models/blip2.py official repository ran · violated contract BSD-3-Clause (permissive) · 4cb732f513d69dfd · report
do_nothing rese1f/MovieChat/MovieChat/models/eva_vit_with_tome.py official repository ran · honoured contract fingerprinted BSD-3-Clause (permissive) · 969e8250d805a154 · report
get_clip_timepoints rese1f/MovieChat/MovieChat/models/process_video_data.py official repository ran BSD-3-Clause (permissive) · 432c312da80537d6 · report
get_sinusoid_encoding_table rese1f/MovieChat/MovieChat/models/multimodal_preprocessors.py official repository ran · honoured contract fingerprinted BSD-3-Clause (permissive) · 35a743e50e17e66d · report
kth_bipartite_soft_matching rese1f/MovieChat/MovieChat/models/eva_vit_with_tome.py official repository ran BSD-3-Clause (permissive) · 6bf3a1372bad1076 · report
load_and_transform_vision_data rese1f/MovieChat/MovieChat/models/process_video_data.py official repository ran BSD-3-Clause (permissive) · e1e69d9ba9ffcb24 · report
rotate_half rese1f/MovieChat/MovieChat/models/modeling_llama.py official repository ran · our draft was wrong fingerprinted BSD-3-Clause (permissive) · b99eea6376d1e212 · report
tile rese1f/MovieChat/MovieChat/models/base_model.py official repository ran fingerprinted BSD-3-Clause (permissive) · cb33571427334815 · report
all_gather_with_grad rese1f/MovieChat/MovieChat/models/base_model.py official repository unverified BSD-3-Clause (permissive) · 0ec9fc2025c16f65 · report
interpolate_pos_encoding rese1f/MovieChat/MovieChat/models/multimodal_preprocessors.py official repository unverified BSD-3-Clause (permissive) · 71227efe6a7df1d2 · report
interpolate_pos_encoding_2d rese1f/MovieChat/MovieChat/models/multimodal_preprocessors.py official repository unverified BSD-3-Clause (permissive) · ddd2e52e6b0956b5 · report

Tasks

2kQuestion AnsweringVideo Question AnsweringVideo Understanding

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Question Answering NExT-QA (Open-ended VideoQA) MovieChat+ Accuracy 54.8 #4 of 6 Archive leaderboard report
Question Answering NExT-QA (Open-ended VideoQA) MovieChat+ Confidence Score 3.0 #4 of 6 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections