Paper Citation Record · LEDGER

Joint Generalized Cosine Similarity: A Novel Method for N-Modal Semantic Alignment Based on Contrastive Learning

As of 16 August 2026, this Paper Citation Record lists 41 of 41 outbound references and 0 inbound Pith citation observations for arXiv:2505.03532.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2505.03532 v1

Coverage vector

measured 41 of 41 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T23:55:36.165878Z

measured 41 of 41 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-16T06:30:59.297886+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: cited_works

Reference resolution

41 of 41 outbound references displayed

verified exact3
verified fuzzy17
unresolved21
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 14081640-e9e1-4943-805d-f85a73827acc · outbound

This paper cites Multi-modal sentiment analysis based on image and text fusion based on cross-attention mechanism,.

Joint Generalized Cosine Similarity: A Novel Method for N-Modal Semantic Alignment Based on Contrastive Learning Multi-modal sentiment analysis based on image and text fusion based on cross-attention mechanism,

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:55:36.601052Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation c539aff7-0d8b-41a2-93a4-a0c0f7c32a69 · outbound

This paper cites An image-text sentiment analysis method using multi-channel multi-modal joint learning,.

Joint Generalized Cosine Similarity: A Novel Method for N-Modal Semantic Alignment Based on Contrastive Learning An image-text sentiment analysis method using multi-channel multi-modal joint learning,

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:55:36.588713Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 937aee48-f130-49a7-8348-69486911e7e8 · outbound

This paper cites Unified cross-modal attention: robust audio-visual speech recognition and beyond,.

Joint Generalized Cosine Similarity: A Novel Method for N-Modal Semantic Alignment Based on Contrastive Learning Unified cross-modal attention: robust audio-visual speech recognition and beyond,

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:55:36.576863Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 5acbf293-6235-4e7c-b581-afe03d619700 · outbound

This paper cites Catnet: Cross-modal fusion for audio–visual speech recognition,.

Joint Generalized Cosine Similarity: A Novel Method for N-Modal Semantic Alignment Based on Contrastive Learning Catnet: Cross-modal fusion for audio–visual speech recognition,

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:55:36.564311Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation b629805d-56e1-4a80-9687-38f41422a240 · outbound

This paper cites Medm2g: Unifying medical multi-modal generation via cross-guided diffusion with visual invariant,.

Joint Generalized Cosine Similarity: A Novel Method for N-Modal Semantic Alignment Based on Contrastive Learning Medm2g: Unifying medical multi-modal generation via cross-guided diffusion with visual invariant,

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:55:36.553267Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 6dac3c44-6c0a-40cb-886c-2001a8207085 · outbound

This paper cites A comprehensive review on synergy of multi-modal data and ai technologies in medical diagnosis,.

Joint Generalized Cosine Similarity: A Novel Method for N-Modal Semantic Alignment Based on Contrastive Learning A comprehensive review on synergy of multi-modal data and ai technologies in medical diagnosis,

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:55:36.541170Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation ab5d0953-ae96-403a-a3b1-2556b9ae33fd · outbound

This paper cites M3D: Advancing 3D Medical Image Analysis with Multi-Modal Large Language Models.

Joint Generalized Cosine Similarity: A Novel Method for N-Modal Semantic Alignment Based on Contrastive Learning M3D: Advancing 3D Medical Image Analysis with Multi-Modal Large Language Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-15T23:55:36.037745Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d334e03-3da7-4afb-ab47-1dfa19d7f495 · outbound

This paper cites A review on methods and applications in multimodal deep learning,.

Joint Generalized Cosine Similarity: A Novel Method for N-Modal Semantic Alignment Based on Contrastive Learning A review on methods and applications in multimodal deep learning,

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-15T23:55:36.041730Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8594c819-3016-41d2-8104-157845f29ee7 · outbound

This paper cites Bimac: Bidirectional multimodal alignment in contrastive learning,.

Joint Generalized Cosine Similarity: A Novel Method for N-Modal Semantic Alignment Based on Contrastive Learning Bimac: Bidirectional multimodal alignment in contrastive learning,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:55:36.524692Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 37edc611-6285-4ffb-8ee1-af4b04a3ad1d · outbound

This paper cites What to align in multimodal contrastive learning?.

Joint Generalized Cosine Similarity: A Novel Method for N-Modal Semantic Alignment Based on Contrastive Learning What to align in multimodal contrastive learning?

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-15T23:55:36.048970Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bec2b03c-b48a-4cc0-a6fc-e85f870415c9 · outbound

This paper cites Variance Alignment Score: A Simple But Tough-to-Beat Data Selection Method for Multimodal Contrastive Learning.

Joint Generalized Cosine Similarity: A Novel Method for N-Modal Semantic Alignment Based on Contrastive Learning Variance Alignment Score: A Simple But Tough-to-Beat Data Selection Method for Multimodal Contrastive Learning

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-15T23:55:36.052892Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 32f3971f-3f12-484b-8d94-8aa3b7dda540 · outbound

This paper cites ContrastAlign: Toward Robust BEV Feature Alignment via Contrastive Learning for Multi-Modal 3D Object Detection.

Joint Generalized Cosine Similarity: A Novel Method for N-Modal Semantic Alignment Based on Contrastive Learning ContrastAlign: Toward Robust BEV Feature Alignment via Contrastive Learning for Multi-Modal 3D Object Detection

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-15T23:55:36.057355Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5eb80b7e-98ce-41b1-8645-940ba052b907 · outbound

This paper cites Mm-fi: Multi-modal non-intrusive 4d human dataset for versatile wireless sensing,.

Joint Generalized Cosine Similarity: A Novel Method for N-Modal Semantic Alignment Based on Contrastive Learning Mm-fi: Multi-modal non-intrusive 4d human dataset for versatile wireless sensing,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:55:36.514243Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation ced00b38-dcd9-4bca-b7b8-4cc257ff7e38 · outbound

This paper cites M5product: Self-harmonized contrastive learning for e-commercial multi-modal pretraining,.

Joint Generalized Cosine Similarity: A Novel Method for N-Modal Semantic Alignment Based on Contrastive Learning M5product: Self-harmonized contrastive learning for e-commercial multi-modal pretraining,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:55:36.502514Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation ad377fc2-899b-40f1-8deb-6d38a25d77f0 · outbound

This paper cites Humman: Multi-modal 4d human dataset for versatile sensing and modeling,.

Joint Generalized Cosine Similarity: A Novel Method for N-Modal Semantic Alignment Based on Contrastive Learning Humman: Multi-modal 4d human dataset for versatile sensing and modeling,

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-15T23:55:36.068734Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aeb73310-18a3-4bf4-8532-2d37fae37aa8 · outbound

This paper cites MedTrinity-25M: A Large-scale Multimodal Dataset with Multigranular Annotations for Medicine.

Joint Generalized Cosine Similarity: A Novel Method for N-Modal Semantic Alignment Based on Contrastive Learning MedTrinity-25M: A Large-scale Multimodal Dataset with Multigranular Annotations for Medicine

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-15T23:55:36.072451Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 86f0b9cd-c5ae-4771-ba03-bc3037a479ed · outbound

This paper cites Mmearth: Exploring multi-modal pretext tasks for geospatial representation learning,.

Joint Generalized Cosine Similarity: A Novel Method for N-Modal Semantic Alignment Based on Contrastive Learning Mmearth: Exploring multi-modal pretext tasks for geospatial representation learning,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:55:36.480900Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation e7841f29-3a69-420b-960a-cd75f4bf0b07 · outbound

This paper cites Gen-jema: enhanced explainability using generative joint embedding multimodal alignment for monitoring directed energy deposition,.

Joint Generalized Cosine Similarity: A Novel Method for N-Modal Semantic Alignment Based on Contrastive Learning Gen-jema: enhanced explainability using generative joint embedding multimodal alignment for monitoring directed energy deposition,

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:55:36.469463Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation dee8e2ef-d54c-464f-999c-e23516a90bc1 · outbound

This paper cites VSE++: Improving Visual-Semantic Embeddings with Hard Negatives.

Joint Generalized Cosine Similarity: A Novel Method for N-Modal Semantic Alignment Based on Contrastive Learning VSE++: Improving Visual-Semantic Embeddings with Hard Negatives

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-15T23:55:36.084315Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd15a8e2-13f2-4142-aabf-ec3a5d1aeed7 · outbound

This paper cites Learning transferable visual models from natural language supervision,.

Joint Generalized Cosine Similarity: A Novel Method for N-Modal Semantic Alignment Based on Contrastive Learning Learning transferable visual models from natural language supervision,

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-15T23:55:36.088328Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9fea8b21-ec6a-4bf3-82d0-d9c93c73a826 · outbound

This paper cites EVA-CLIP: Improved Training Techniques for CLIP at Scale.

Joint Generalized Cosine Similarity: A Novel Method for N-Modal Semantic Alignment Based on Contrastive Learning EVA-CLIP: Improved Training Techniques for CLIP at Scale

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-15T23:55:36.092557Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 901a4998-b132-4eb7-883a-6969306f333c · outbound

This paper cites Long-clip: Unlocking the long-text capability of clip,.

Joint Generalized Cosine Similarity: A Novel Method for N-Modal Semantic Alignment Based on Contrastive Learning Long-clip: Unlocking the long-text capability of clip,

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:55:36.451399Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 5e9672a0-0374-48cb-9090-2fcc25f007b9 · outbound

This paper cites Oscar: Object-semantics aligned pre-training for vision-language tasks,.

Joint Generalized Cosine Similarity: A Novel Method for N-Modal Semantic Alignment Based on Contrastive Learning Oscar: Object-semantics aligned pre-training for vision-language tasks,

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-15T23:55:36.101520Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e80dfd1e-b755-4f0f-9391-968f5aefb1e4 · outbound

This paper cites an unresolved cited work.

Joint Generalized Cosine Similarity: A Novel Method for N-Modal Semantic Alignment Based on Contrastive Learning Unresolved cited work

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-15T23:55:36.105031Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9bf4f69-3e32-41f9-87c4-9775749634de · outbound

This paper cites Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks,.

Joint Generalized Cosine Similarity: A Novel Method for N-Modal Semantic Alignment Based on Contrastive Learning Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks,

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-15T23:55:36.108657Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2cd4083b-1755-4dea-8837-bee177d955f8 · outbound

This paper cites Vilt: Vision-and-language transformer without convolution or region supervision,.

Joint Generalized Cosine Similarity: A Novel Method for N-Modal Semantic Alignment Based on Contrastive Learning Vilt: Vision-and-language transformer without convolution or region supervision,

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-15T23:55:36.112140Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 610dcb60-3981-4fde-bab7-1b05757e23af · outbound

This paper cites Multimodal Contrastive Learning via Uni-Modal Coding and Cross-Modal Prediction for Multimodal Sentiment Analysis.

Joint Generalized Cosine Similarity: A Novel Method for N-Modal Semantic Alignment Based on Contrastive Learning Multimodal Contrastive Learning via Uni-Modal Coding and Cross-Modal Prediction for Multimodal Sentiment Analysis

Reference 27

Resolution: verified exact; local_arxiv, observed 2026-08-15T23:55:36.254812Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 909ffdcf-b3f5-4a6f-979f-6d94dceebb5b · outbound

This paper cites Triplet-based deep hashing network for cross-modal retrieval,.

Joint Generalized Cosine Similarity: A Novel Method for N-Modal Semantic Alignment Based on Contrastive Learning Triplet-based deep hashing network for cross-modal retrieval,

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-15T23:55:36.119217Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c182d9f-6b53-4afe-bd1d-58b6a1771d38 · outbound

This paper cites Representation Learning with Contrastive Predictive Coding.

Joint Generalized Cosine Similarity: A Novel Method for N-Modal Semantic Alignment Based on Contrastive Learning Representation Learning with Contrastive Predictive Coding

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-15T23:55:36.122734Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db29472c-a514-4904-b37b-c95eaf9e8553 · outbound

This paper cites Momentum contrast for unsupervised visual representation learning,.

Joint Generalized Cosine Similarity: A Novel Method for N-Modal Semantic Alignment Based on Contrastive Learning Momentum contrast for unsupervised visual representation learning,

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-15T23:55:36.126704Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e065964a-8911-4cf1-a49f-0d4ecbebf13c · outbound

This paper cites A simple framework for contrastive learning of visual representations,.

Joint Generalized Cosine Similarity: A Novel Method for N-Modal Semantic Alignment Based on Contrastive Learning A simple framework for contrastive learning of visual representations,

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-15T23:55:36.130177Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce602085-9f28-4166-9104-5a890999973c · outbound

This paper cites Semantic alignment network for multi-modal emotion recognition,.

Joint Generalized Cosine Similarity: A Novel Method for N-Modal Semantic Alignment Based on Contrastive Learning Semantic alignment network for multi-modal emotion recognition,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:55:36.394462Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 17c6e5a0-2e34-434c-a601-366e8d5a9101 · outbound

This paper cites X2CT-CLIP: Enable Multi-Abnormality Detection in Computed Tomography from Chest Radiography via Tri-Modal Contrastive Learning.

Joint Generalized Cosine Similarity: A Novel Method for N-Modal Semantic Alignment Based on Contrastive Learning X2CT-CLIP: Enable Multi-Abnormality Detection in Computed Tomography from Chest Radiography via Tri-Modal Contrastive Learning

Reference 33

Resolution: verified exact; local_arxiv, observed 2026-08-15T23:55:36.229441Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 5a554f16-9df2-4cc5-933c-bfb189655317 · outbound

This paper cites Hybrid contrastive learning of tri-modal representation for multimodal sentiment analysis,.

Joint Generalized Cosine Similarity: A Novel Method for N-Modal Semantic Alignment Based on Contrastive Learning Hybrid contrastive learning of tri-modal representation for multimodal sentiment analysis,

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:55:36.383475Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 3f811589-2d18-403e-8eb0-6b8f4293c78b · outbound

This paper cites Tri-clt: Learning tri-modal representations with contrastive learning and transformer for multimodal sentiment recognition,.

Joint Generalized Cosine Similarity: A Novel Method for N-Modal Semantic Alignment Based on Contrastive Learning Tri-clt: Learning tri-modal representations with contrastive learning and transformer for multimodal sentiment recognition,

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:55:36.371975Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 4adb5ec0-242d-4a3e-ac49-6a58e46eddd5 · outbound

This paper cites Tricolo: Trimodal contrastive loss for text to shape retrieval,.

Joint Generalized Cosine Similarity: A Novel Method for N-Modal Semantic Alignment Based on Contrastive Learning Tricolo: Trimodal contrastive loss for text to shape retrieval,

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-15T23:55:36.147885Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b0e7563e-585c-48a2-96fc-43dbc5b165cb · outbound

This paper cites Con- trastive learning of medical visual representations from paired images and text,.

Joint Generalized Cosine Similarity: A Novel Method for N-Modal Semantic Alignment Based on Contrastive Learning Con- trastive learning of medical visual representations from paired images and text,

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:55:36.354735Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 07abb902-4f2e-4c84-86ee-3faa6b2846b9 · outbound

This paper cites Triangular Contrastive Learning on Molecular Graphs.

Joint Generalized Cosine Similarity: A Novel Method for N-Modal Semantic Alignment Based on Contrastive Learning Triangular Contrastive Learning on Molecular Graphs

Reference 38

Resolution: verified exact; local_arxiv, observed 2026-08-15T23:55:36.213401Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 99309edd-4bda-4b15-902f-389e59377faf · outbound

This paper cites Seven- point checklist and skin lesion classification using multitask multimodal neural nets,.

Joint Generalized Cosine Similarity: A Novel Method for N-Modal Semantic Alignment Based on Contrastive Learning Seven- point checklist and skin lesion classification using multitask multimodal neural nets,

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T23:55:36.343361Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 4b765122-8914-4382-a16f-e8a15d054808 · outbound

This paper cites Adam: A Method for Stochastic Optimization.

Joint Generalized Cosine Similarity: A Novel Method for N-Modal Semantic Alignment Based on Contrastive Learning Adam: A Method for Stochastic Optimization

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-15T23:55:36.162324Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8daefaee-402c-4f33-90f4-f2bead281722 · outbound

This paper cites Focal loss for dense object detection,.

Joint Generalized Cosine Similarity: A Novel Method for N-Modal Semantic Alignment Based on Contrastive Learning Focal loss for dense object detection,

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-15T23:55:36.165878Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.