Papers › Text-Video Retrieval with Disentangled Conceptualization and Set-to-Set Alignment

Text-Video Retrieval with Disentangled Conceptualization and Set-to-Set Alignment

20 May 2023arXiv:2305.12218archive 2025-07-28

Peng Jin, Hao Li, Zesen Cheng, Jinfa Huang, Zhennan Wang, Li Yuan, Chang Liu, Jie Chen

Text-video retrieval is a challenging cross-modal task, which aims to align visual entities with natural language descriptions. Current methods either fail to leverage the local details or are computationally expensive. What's worse, they fail to leverage the heterogeneous concepts in data. In this paper, we propose the Disentangled Conceptualization and Set-to-set Alignment (DiCoSA) to simulate the conceptualizing and reasoning process of human beings. For disentangled conceptualization, we divide the coarse feature into multiple latent factors related to semantic concepts. For set-to-set alignment, where a set of visual concepts correspond to a set of textual concepts, we propose an adaptive pooling method to aggregate semantic concepts to address the partial matching. In particular, since we encode concepts independently in only a few dimensions, DiCoSA is superior at efficiency and granularity, ensuring fine-grained interactions using a similar computational complexity as coarse-grained alignment. Extensive experiments on five datasets, including MSR-VTT, LSMDC, MSVD, ActivityNet, and DiDeMo, demonstrate that our method outperforms the existing state-of-the-art methods.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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="2305.12218")

Code

Syntology Ran 9 of 23 code samples harvested from 3 repositories linked to this paper; 14 have no recorded run. Of those that ran: 2 ran · honoured contract; 6 ran · our draft was wrong; 1 ran · fixture could not drive it.

By repository: official repository: 16 samples from 1 repository, 7 ran; community (archive-listed): 7 samples from 2 repositories, 2 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

jpthu17/dicosa officialmentioned in papermentioned on GitHubpytorchApache-2.0 report
jpthu17/HBI mentioned on GitHubpytorch report
jpthu17/diffusionret mentioned on GitHubpytorchApache-2.0 report
jpthu17/emcl mentioned on GitHubpytorch 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

23 samples harvested; 9 ran; 2 honoured the contract we drafted; 14 have no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

2ran · honoured contract
6ran · our draft was wrong
1ran · fixture could not drive it
14unverified

Licence: 0 of the 23 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 3 repositories linked to this paper, official or community; each sample names its own and says which. “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.

swish jpthu17/DiCoSA/tvr/models/until_module.py official repository ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 0f786c407fb1ee4c · report
basic_clean jpthu17/DiCoSA/tvr/models/tokenization_clip.py official repository ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 98f385d847636a3e · report
euclidean_dist jpthu17/DiCoSA/tvr/models/until_module.py official repository ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · e54804982d1e6d22 · report
gelu jpthu17/DiCoSA/tvr/models/until_module.py official repository ran · honoured contract fingerprinted Apache-2.0 (permissive) · 50e1ffed03f484ec · report
get_pairs jpthu17/DiCoSA/tvr/models/tokenization_clip.py official repository ran · our draft was wrong Apache-2.0 (permissive) · d919ae32e5e4e616 · report
warmup_linear jpthu17/DiCoSA/tvr/models/optimization.py official repository ran · honoured contract fingerprinted Apache-2.0 (permissive) · e0960afdb0d64aa7 · report
whitespace_clean jpthu17/DiCoSA/tvr/models/tokenization_clip.py official repository ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 9542161e9640b858 · report
dataloader_msrvtt_test jpthu17/DiCoSA/tvr/dataloaders/data_dataloaders.py official repository unverified Apache-2.0 (permissive) · b6070984a76e9bf3 · report
dataloader_msrvtt_train jpthu17/DiCoSA/tvr/dataloaders/data_dataloaders.py official repository unverified Apache-2.0 (permissive) · 780f499e676f8267 · report
dataloader_msrvtt_train_test jpthu17/DiCoSA/tvr/dataloaders/data_dataloaders.py official repository unverified Apache-2.0 (permissive) · 70d56cc28b0d7a14 · report
get_args jpthu17/DiCoSA/main_retrieval.py official repository unverified Apache-2.0 (permissive) · 91e7fe98724c5bad · report
load_stopwords jpthu17/DiCoSA/tvr/dataloaders/dataloader_activitynet_retrieval.py official repository unverified Apache-2.0 (permissive) · d227e7f9a9ea755e · report
remove_stopwords jpthu17/DiCoSA/tvr/dataloaders/dataloader_activitynet_retrieval.py official repository unverified Apache-2.0 (permissive) · 1d11677b554a969d · report
set_seed_logger jpthu17/DiCoSA/main_retrieval.py official repository unverified Apache-2.0 (permissive) · 8952edef143f2747 · report
warmup_constant jpthu17/DiCoSA/tvr/models/optimization.py official repository unverified Apache-2.0 (permissive) · 59e4e730a9dc5dc6 · report
warmup_cosine jpthu17/DiCoSA/tvr/models/optimization.py official repository unverified Apache-2.0 (permissive) · 20b3d25ba1b796e5 · report
merge_tokens jpthu17/HBI/HBI/models/cluster.py community (archive-listed) ran · fixture could not drive it Apache-2.0 (permissive) · 0e49170b7c8f60fd · report
url_to_filename jpthu17/diffusionret/DiffusionRet/models/file_utils.py community (archive-listed) ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · af64ec220e8bcdbc · report
CTM jpthu17/HBI/HBI/models/cluster.py community (archive-listed) unverified Apache-2.0 (permissive) · 8bc3e8d24dc52e8b · report
TokenConv jpthu17/HBI/HBI/models/cluster.py community (archive-listed) unverified Apache-2.0 (permissive) · 8b50e3e4f063bce8 · report
cached_path jpthu17/diffusionret/DiffusionRet/models/file_utils.py community (archive-listed) unverified Apache-2.0 (permissive) · 349d780dd4a89a37 · report
dataloader_activity_train jpthu17/diffusionret/DiffusionRet/dataloaders/data_dataloaders.py community (archive-listed) unverified Apache-2.0 (permissive) · ab028ff1220c10c1 · report
filename_to_url jpthu17/diffusionret/DiffusionRet/models/file_utils.py community (archive-listed) unverified Apache-2.0 (permissive) · db0ac56aaf6e35e6 · report

Tasks

RetrievalVideo Retrieval

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

ALIGNfail

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