Papers › Token-Level Contrastive Learning with Modality-Aware Prompting for Multimodal Intent...

Token-Level Contrastive Learning with Modality-Aware Prompting for Multimodal Intent Recognition

22 Dec 2023arXiv:2312.14667archive 2025-07-28

Qianrui Zhou, Hua Xu, Hao Li, Hanlei Zhang, Xiaohan Zhang, Yifan Wang, Kai Gao

Multimodal intent recognition aims to leverage diverse modalities such as expressions, body movements and tone of speech to comprehend user's intent, constituting a critical task for understanding human language and behavior in real-world multimodal scenarios. Nevertheless, the majority of existing methods ignore potential correlations among different modalities and own limitations in effectively learning semantic features from nonverbal modalities. In this paper, we introduce a token-level contrastive learning method with modality-aware prompting (TCL-MAP) to address the above challenges. To establish an optimal multimodal semantic environment for text modality, we develop a modality-aware prompting module (MAP), which effectively aligns and fuses features from text, video and audio modalities with similarity-based modality alignment and cross-modality attention mechanism. Based on the modality-aware prompt and ground truth labels, the proposed token-level contrastive learning framework (TCL) constructs augmented samples and employs NT-Xent loss on the label token. Specifically, TCL capitalizes on the optimal textual semantic insights derived from intent labels to guide the learning processes of other modalities in return. Extensive experiments show that our method achieves remarkable improvements compared to state-of-the-art methods. Additionally, ablation analyses demonstrate the superiority of the modality-aware prompt over the handcrafted prompt, which holds substantial significance for multimodal prompt learning. The codes are released at https://github.com/thuiar/TCL-MAP.

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="2312.14667")

Code

Syntology Ran 5 of 8 code samples harvested from 1 repository linked to this paper; 3 have no recorded run. Of those that ran: 1 ran · honoured contract; 2 ran · our draft was wrong; 1 ran · fixture could not drive it; 1 ran with no contract checked.

By repository: official repository: 8 samples from 1 repository, 5 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

thuiar/TCL-MAP officialmentioned in papermentioned on GitHubpytorchMIT 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

8 samples harvested; 5 ran; 1 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.

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

Licence: 0 of the 8 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 thuiar/TCL-MAP. “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.

Linear thuiar/TCL-MAP/methods/TCL_MAP/SubNets/transformers_encoder/transformer.py official repository ran · our draft was wrong MIT (permissive) · 10865bbb99140edd · report
buffered_future_mask thuiar/TCL-MAP/methods/TCL_MAP/SubNets/transformers_encoder/transformer.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · d13fbe5e7e90947f · report
fill_with_neg_inf thuiar/TCL-MAP/methods/TCL_MAP/SubNets/transformers_encoder/transformer.py official repository ran · honoured contract fingerprinted MIT (permissive) · 8f266b9d616de9b9 · report
make_positions thuiar/TCL-MAP/methods/TCL_MAP/SubNets/transformers_encoder/position_embedding.py official repository ran · fixture could not drive it fingerprinted MIT (permissive) · 21958d540bd87a8c · report
restore_model thuiar/TCL-MAP/utils/functions.py official repository ran MIT (permissive) · c25b59874b2d48aa · report
add_config_param thuiar/TCL-MAP/configs/base.py official repository unverified MIT (permissive) · 1ef6337ae6763042 · report
load_npy thuiar/TCL-MAP/utils/functions.py official repository unverified MIT (permissive) · 8c6bc8fd52264b46 · report
set_output_path thuiar/TCL-MAP/utils/functions.py official repository unverified MIT (permissive) · d152ab9b27609574 · report

Tasks

Contrastive LearningIntent RecognitionMultimodal Intent RecognitionPrompt Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Multimodal Intent Recognition MIntRec TCL-MAP Accuracy (20 classes) 73.62 #2 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.

Methods

Contrastive LearningNT-Xent

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