Papers › MoTE: Reconciling Generalization with Specialization for Visual-Language to Video...

MoTE: Reconciling Generalization with Specialization for Visual-Language to Video Knowledge Transfer

14 Oct 2024arXiv:2410.10589archive 2025-07-28

Minghao Zhu, Zhengpu Wang, Mengxian Hu, Ronghao Dang, Xiao Lin, Xun Zhou, Chengju Liu, Qijun Chen

Transferring visual-language knowledge from large-scale foundation models for video recognition has proved to be effective. To bridge the domain gap, additional parametric modules are added to capture the temporal information. However, zero-shot generalization diminishes with the increase in the number of specialized parameters, making existing works a trade-off between zero-shot and close-set performance. In this paper, we present MoTE, a novel framework that enables generalization and specialization to be balanced in one unified model. Our approach tunes a mixture of temporal experts to learn multiple task views with various degrees of data fitting. To maximally preserve the knowledge of each expert, we propose \emph{Weight Merging Regularization}, which regularizes the merging process of experts in weight space. Additionally with temporal feature modulation to regularize the contribution of temporal feature during test. We achieve a sound balance between zero-shot and close-set video recognition tasks and obtain state-of-the-art or competitive results on various datasets, including Kinetics-400 \& 600, UCF, and HMDB. Code is available at \url{https://github.com/ZMHH-H/MoTE}.

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="2410.10589")

Code

Syntology Ran 8 of 12 code samples harvested from 1 repository linked to this paper; 4 have no recorded run. Of those that ran: 3 ran · our draft was wrong; 1 ran · fixture could not drive it; 4 ran with no contract checked.

By repository: official repository: 12 samples from 1 repository, 8 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

zmhh-h/mote officialmentioned in papermentioned on GitHubpytorchApache-2.0 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

12 samples harvested; 8 ran; 0 honoured the contract we drafted; 4 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.

3ran · our draft was wrong
1ran · fixture could not drive it
4ran
4unverified

Licence: 0 of the 12 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 zmhh-h/mote. “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.

MoTE zmhh-h/mote/modules/video_clip.py official repository ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 5040c36396284f29 · report
QuickGELU zmhh-h/mote/modules/video_clip.py official repository ran · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive) · 8c5c4de012c0aab9 · report
basic_clean ZMHH-H/MoTE/clip/simple_tokenizer.py official repository ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 98f385d847636a3e · report
drop_path ZMHH-H/MoTE/clip/model.py official repository ran · fixture could not drive it fingerprinted Apache-2.0 (permissive) · 3ac6b7d76e8e3584 · report
get_pairs ZMHH-H/MoTE/clip/simple_tokenizer.py official repository ran · our draft was wrong Apache-2.0 (permissive) · d919ae32e5e4e616 · report
multiple_samples_collate ZMHH-H/MoTE/utils/Augmentation.py official repository ran Apache-2.0 (permissive) · 4927733091f71100 · report
setup_logger ZMHH-H/MoTE/utils/logger.py official repository ran Apache-2.0 (permissive) · 92035acbaccac625 · report
whitespace_clean ZMHH-H/MoTE/clip/simple_tokenizer.py official repository ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 9542161e9640b858 · report
build_model ZMHH-H/MoTE/clip/model.py official repository unverified Apache-2.0 (permissive) · 5d969c3a44340f51 · report
get_augmentation ZMHH-H/MoTE/utils/Augmentation.py official repository unverified Apache-2.0 (permissive) · 2e5fc9f7692cae58 · report
load ZMHH-H/MoTE/clip/clip.py official repository unverified Apache-2.0 (permissive) · a34ba2785e08acbd · report
train_augmentation ZMHH-H/MoTE/utils/Augmentation.py official repository unverified Apache-2.0 (permissive) · 8bd3efba1612299f · report

Tasks

Transfer LearningVideo RecognitionZero-shot Generalization

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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