Pith. sign in

Paper Citation Record · LEDGER

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries

As of 13 August 2026, this Paper Citation Record lists 97 of 97 outbound references and 0 inbound Pith citation observations for arXiv:2412.00639.

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

pith.paper-citation-record.v1
2412.00639 v2

Coverage vector

measured 97 of 97 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-12T05:13:50.370465Z

measured 97 of 97 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-12T06:34:41.77262+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

97 of 97 outbound references displayed

  • verified exact2
  • verified fuzzy42
  • unresolved52
  • parse uncertain0
  • malformed identifier1
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation f99fdae7-f186-4a29-91aa-be9c0d060fd7 · outbound

This paper cites GPT-4 Technical Report.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries GPT-4 Technical Report

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-12T05:13:49.965500Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T05:13:49.965500Z digest=sha256:e2beaea4c7a817f65ba87d05284c850b4536c058f9faaad5688bd15396f9ffff

Observation e51d17be-8da4-4c6d-8303-1c909f63a461 · outbound

This paper cites nocaps: novel object captioning at scale.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries nocaps: novel object captioning at scale

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-12T05:13:49.970814Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T05:13:49.970814Z digest=sha256:f18eaea53d114f30b3045e63e72816ced390ab7c364c934ed68b045af4f3e238

Observation 9c6e25b8-0853-4cc9-ab11-c806ca290241 · outbound

This paper cites Natural language interfaces to databases–an introduction.Natural language engineering, 1(1):29–81, 1995.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Natural language interfaces to databases–an introduction.Natural language engineering, 1(1):29–81, 1995

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-12T05:13:49.975713Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T05:13:49.975713Z digest=sha256:811e4cd301970b4f52e4f02f050e8e0b785edc7657720238f3918872798a734b

Observation e98e2486-026c-446b-ad42-2cedaeb42f24 · outbound

This paper cites Modeling score distributions in information retrieval.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Modeling score distributions in information retrieval

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-12T05:13:49.980207Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T05:13:49.980207Z digest=sha256:007b712a1faaa543a5c30675bf2b76181b2765e0923711e544e0dd841f7bfd37

Observation 77dd7599-b6a6-4079-a710-bd6b4dc900ef · outbound

This paper cites The multiplicative weights update method: a meta-algorithm and applications.Theory of computing, 8(1):121–164, 2012.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries The multiplicative weights update method: a meta-algorithm and applications.Theory of computing, 8(1):121–164, 2012

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-12T05:13:49.985333Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T05:13:49.985333Z digest=sha256:3509c247b4d05fe18d22a3491f451e6b696f90f7664ace906b3f08ab86bc41d4

Observation 57abeed8-565f-4cac-8319-4ce2ace18c6a · outbound

This paper cites Deep neural architecture for multi-modal retrieval based on joint embedding space for text and images.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Deep neural architecture for multi-modal retrieval based on joint embedding space for text and images

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-12T05:13:49.989522Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T05:13:49.989522Z digest=sha256:c3af7e7de4076bab410becd2a67b0d214009c44f6eac4c76a13ebce66dddbe10

Observation 38b437d3-b40d-449c-8940-30c75d535822 · outbound

This paper cites BEiT: BERT Pre-Training of Image Transformers.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries BEiT: BERT Pre-Training of Image Transformers

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-12T05:13:49.994257Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T05:13:49.994257Z digest=sha256:68f909b32435b126e1c85d8d9c94de364f9e42295e83f14907627eb17380e49e

Observation d7091c3c-5543-4e28-8f7c-1df79dc68aa1 · outbound

This paper cites Lof: identifying density-based local outliers.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Lof: identifying density-based local outliers

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-12T05:13:49.999104Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T05:13:49.999104Z digest=sha256:2cdeef4970838f35017ed181ec51c8bfbf66e45670c372df4e0a54a5547113be

Observation f58a3298-5b37-4db0-986e-9fadf93dbe80 · outbound

This paper cites Language Models are Few-Shot Learners.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Language Models are Few-Shot Learners

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-12T05:13:50.003495Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T05:13:50.003495Z digest=sha256:9a70bff60f0084c53f7b3d1b106f4677b2ee9e0ccc2bb3164642c35d8e2db8be

Observation 5699e3d3-aed3-4c48-a0de-80554a1c9d5f · outbound

This paper cites Large-scale content-based audio retrieval from text queries.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Large-scale content-based audio retrieval from text queries

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-12T05:13:50.007478Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T05:13:50.007478Z digest=sha256:eedfb26ade685c21b6b66691c54d384ff9a7c7da721abe4122e02bbab6de9b8f

Observation b9799d22-6efb-4d50-ac87-7651439ed677 · outbound

This paper cites Image search with text feedback by visiolin- guistic attention learning.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Image search with text feedback by visiolin- guistic attention learning

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-12T05:13:50.011482Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T05:13:50.011482Z digest=sha256:ca44dc9b377e6f754f38569775880d630446859a1fb81bf20c0beec9007269da

Observation d96eb973-9567-41a8-9220-cc07cc9dfd36 · outbound

This paper cites Palm: Scaling language modeling with pathways.Journal of Machine Learning Research, 24(240):1– 113, 2023.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Palm: Scaling language modeling with pathways.Journal of Machine Learning Research, 24(240):1– 113, 2023

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-12T05:13:50.014877Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T05:13:50.014877Z digest=sha256:34751cc4ad7cf718e725988776dbbb3d6565f2784a5052bfa0a1666e70b5d6f8

Observation 25a79af1-081f-4524-ad33-22043aa41391 · outbound

This paper cites On the inference of average precision from score distributions.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries On the inference of average precision from score distributions

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-12T05:13:50.018126Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T05:13:50.018126Z digest=sha256:a16e1602a1c3906bafeeb12dcfd9b279bbbe565e9de27513d2ee6a9a0f57a993

Observation aa50658b-cec6-4f16-bc5e-fb550934c407 · outbound

This paper cites Advanced generative ai methods for academic text summarization.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Advanced generative ai methods for academic text summarization

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-12T05:13:50.022300Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T05:13:50.022300Z digest=sha256:398d405019a34e58c08e0492e23a2fca09b7b711fdcd828d3b36ecdbf87ddbd6

Observation 7e8e4b06-79b1-4fd3-b231-6c39bf7d9fbd · outbound

This paper cites BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-12T05:13:50.026286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T05:13:50.026286Z digest=sha256:1f329fe2672a44f83ed678bcd067372ac3446bd7ed9e9e16debbe2cc4c3afb45

Observation f06a8ab1-4cdd-45ea-8006-5100a071ca6d · outbound

This paper cites Chameleon: Foundation models for fairness-aware multi-modal data augmentation to enhance coverage of minorities.Proceedings of the VLDB Endowment, 17(11):3470–3483, 2024.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Chameleon: Foundation models for fairness-aware multi-modal data augmentation to enhance coverage of minorities.Proceedings of the VLDB Endowment, 17(11):3470–3483, 2024

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-12T05:13:50.030109Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T05:13:50.030109Z digest=sha256:77f6428d0301646eddcd46255d666b60c7a539dd9485665c7779375d30815576

Observation d76fb0e0-b9fe-40a3-b236-bf0e5cbaaa33 · outbound

This paper cites Optimal aggregation algorithms for middleware.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Optimal aggregation algorithms for middleware

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-12T05:13:50.033689Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T05:13:50.033689Z digest=sha256:93478786c3b22914244972a79a521d3e7b8a0c7870131c5cfdae2dd7d8753854

Observation 718b4582-6d69-445b-b8fd-71eefe25f421 · outbound

This paper cites Eva: Exploring the limits of masked visual representation learning at scale.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Eva: Exploring the limits of masked visual representation learning at scale

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-12T05:13:50.037369Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T05:13:50.037369Z digest=sha256:943671beb44a825e791669def21bd9121f8686540c4651dfbe48b475a4cc4fcc

Observation 0107312c-94cc-49be-b681-6bd2b300f255 · outbound

This paper cites Learning to rank for content-based image retrieval.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Learning to rank for content-based image retrieval

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-12T05:13:50.042175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T05:13:50.042175Z digest=sha256:6caed4840489418d3f07b924203e6f6747f976e1fb72c93c3b3ff3167661423b

Observation d71f1b6d-420a-43ae-9bb3-e68e77264893 · outbound

This paper cites Tagging personal photos with transfer deep learning.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Tagging personal photos with transfer deep learning

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-12T05:13:50.046114Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T05:13:50.046114Z digest=sha256:20a064fef01494738762873a7b231b49930d71377156e388a795b7d035d76764

Observation 2dd88f8f-409b-42bd-ab01-66df36b47123 · outbound

This paper cites Caltech 256, Apr 2022.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Caltech 256, Apr 2022

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-12T05:13:50.050267Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T05:13:50.050267Z digest=sha256:23d9045fc9ac2d76671428c01b63d773c4b24646996aacab56f4705b8a051862

Observation 4c1834f8-3053-4e0e-9428-7483bf25f9b8 · outbound

This paper cites Lvis: A dataset for large vocabulary instance segmentation.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Lvis: A dataset for large vocabulary instance segmentation

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-12T05:13:50.054344Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T05:13:50.054344Z digest=sha256:7ca5908c7c2ba2d5c849518303f3fb797633ba6ea4e603e4e52e2bcfd8773d31

Observation 7ef73d95-267e-4278-a89d-f361fa874559 · outbound

This paper cites Query-aware locality- sensitive hashing for approximate nearest neighbor search.Proceedings of the VLDB Endow- ment, 9(1):1–12, 2015.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Query-aware locality- sensitive hashing for approximate nearest neighbor search.Proceedings of the VLDB Endow- ment, 9(1):1–12, 2015

Reference 23

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T05:13:51.426992Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T05:13:50.058116Z digest=sha256:939437fa729d6bb792a3ee197dad20a2ffba0b51afb87e1a104b4bf36117c472

Observation 5ab79138-f222-4035-8262-9d528fc8e689 · outbound

This paper cites A Survey on Locality Sensitive Hashing Algorithms and their Applications.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries A Survey on Locality Sensitive Hashing Algorithms and their Applications

Reference 24

Resolution
unresolved
no resolver link, observed 2026-08-12T05:13:50.063085Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T05:13:50.063085Z digest=sha256:b47d52e9f1a928b20031ba1674d88455afb0a50288e4b463be7e6538da30bdce

Observation 057b21af-7de1-4f0d-a017-abce482aa55c · outbound

This paper cites Scaling up visual and vision-language representation learning with noisy text supervision.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Scaling up visual and vision-language representation learning with noisy text supervision

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-12T05:13:50.068261Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T05:13:50.068261Z digest=sha256:ebc35b61aadfd499cbb3157b8f6d3e6257e4b7f41b026762cf9c3fafce1cd599

Observation 71b3d95b-8376-4f19-8b7a-af19db71c69b · outbound

This paper cites Semantically- enhanced kernel canonical correlation analysis: a multi-label cross-modal retrieval.Multimedia Tools and Applications, 78:13169–13188, 2019.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Semantically- enhanced kernel canonical correlation analysis: a multi-label cross-modal retrieval.Multimedia Tools and Applications, 78:13169–13188, 2019

Reference 26

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T05:13:51.405017Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T05:13:50.072300Z digest=sha256:831e5b1446943d18dd633dbb7352c61124545415c511969f822b25239dca22e6

Observation 7cfeaa99-326f-44a0-89d3-9c1bace21c85 · outbound

This paper cites Learning image embeddings using convolutional neural networks for improved multi-modal semantics.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Learning image embeddings using convolutional neural networks for improved multi-modal semantics

Reference 27

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T05:13:51.393184Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T05:13:50.076231Z digest=sha256:1d814e76e14e375b622e56a053a49c47092c941877aa190d1db606b6310a3c29

Observation 7627731e-0837-4092-84c9-3b5c377802e9 · outbound

This paper cites Audio retrieval with natural language queries: A benchmark study.IEEE Transactions on Multimedia, 25:2675–2685, 2022.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Audio retrieval with natural language queries: A benchmark study.IEEE Transactions on Multimedia, 25:2675–2685, 2022

Reference 28

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T05:13:51.380041Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T05:13:50.080367Z digest=sha256:5f97e5b57275429107805b10fc88812a4dbf12a54ffcd64553c9e4047fe308e2

Observation 26bd95fe-75fb-4c16-9fe7-a8e231623295 · outbound

This paper cites V oronoi-based k nearest neighbor search for spatial network databases.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries V oronoi-based k nearest neighbor search for spatial network databases

Reference 29

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T05:13:51.367627Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T05:13:50.084103Z digest=sha256:e91a3234c923875d8f7a6625fcfa9462945e231457c81bbd4b8cadf30d7d6f59

Observation efadf8ee-9373-4aab-9eb4-ea0dabe58245 · outbound

This paper cites Using synthetic data to train neural networks is model-based reasoning.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Using synthetic data to train neural networks is model-based reasoning

Reference 30

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T05:13:51.354808Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T05:13:50.087437Z digest=sha256:a14373a5137619884aac211e7655ec634b70569ff6293e48b07c0cd42a846b48

Observation 23120b54-73f8-44b0-ab94-6be37a37aecb · outbound

This paper cites Retrieval-augmented generation for knowledge-intensive nlp tasks.Advances in Neural Information Processing Systems, 33:9459–9474, 2020.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Retrieval-augmented generation for knowledge-intensive nlp tasks.Advances in Neural Information Processing Systems, 33:9459–9474, 2020

Reference 31

Resolution
unresolved
no resolver link, observed 2026-08-12T05:13:50.090743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T05:13:50.090743Z digest=sha256:2cc1b5d1264c37d3b556983d8abf30fdeff6fa975b2df4905b1f42d5d48a18b9

Observation dfe5ea49-a476-47c5-b6d0-d7a12055019d · outbound

This paper cites Nalir: an interactive natural language interface for querying relational databases.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Nalir: an interactive natural language interface for querying relational databases

Reference 32

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T05:13:51.334767Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T05:13:50.093893Z digest=sha256:6e7678d1b27a28174c0139fe82b1643dd76b5be163ba1cf2d26d2fe1a698cbbd

Observation 9d61d628-9655-41a2-aefa-4af862d6f86e · outbound

This paper cites Cross-Modal Retrieval: A Systematic Review of Methods and Future Directions.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Cross-Modal Retrieval: A Systematic Review of Methods and Future Directions

Reference 33

Resolution
unresolved
no resolver link, observed 2026-08-12T05:13:50.097722Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T05:13:50.097722Z digest=sha256:c422b22bfee803632e72df8adf91e792d0cf399b378f99784cfa2e57f98b7b14

Observation af00dcb5-a91e-4baf-9a45-7cfc1593485e · outbound

This paper cites Can llm already serve as a database interface? a big bench for large-scale database grounded text-to-sqls.Advances in Neural Information Processing Systems, 36, 2024.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Can llm already serve as a database interface? a big bench for large-scale database grounded text-to-sqls.Advances in Neural Information Processing Systems, 36, 2024

Reference 34

Resolution
unresolved
no resolver link, observed 2026-08-12T05:13:50.102370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T05:13:50.102370Z digest=sha256:55fd971191dcd48b97f211afa53b2026714539019da7629f0a41e9de7d3f6ec6

Observation c9e7ea36-267b-4194-8266-cf76d7a315d7 · outbound

This paper cites Blip: Bootstrapping language- image pre-training for unified vision-language understanding and generation.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Blip: Bootstrapping language- image pre-training for unified vision-language understanding and generation

Reference 35

Resolution
unresolved
no resolver link, observed 2026-08-12T05:13:50.107132Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T05:13:50.107132Z digest=sha256:0e485d668a55bcc4d28995d7e625d0ef0b2ec594af498ee572abfba9e977e05c

Observation ff316476-a5d9-4045-8dec-cc3680aa0697 · outbound

This paper cites W2vv++ fully deep learning for ad-hoc video search.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries W2vv++ fully deep learning for ad-hoc video search

Reference 36

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T05:13:51.307829Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T05:13:50.111597Z digest=sha256:87a1a77e2fab53def433f647452fa80193da1d4b6d28be916ef8c91a9daf1804

Observation d148382c-1d54-40ea-a187-a6f4d78989a5 · outbound

This paper cites Using LLM to select the right SQL Query from candidates.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Using LLM to select the right SQL Query from candidates

Reference 37

Resolution
unresolved
no resolver link, observed 2026-08-12T05:13:50.115582Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T05:13:50.115582Z digest=sha256:78d03e07bfd6a492a96194983938d4bb7e49d2de841eddeab7e44b0e8a1e3e46

Observation ab32334b-ac08-4efe-8dc3-960373323dfa · outbound

This paper cites Microsoft coco: Common objects in context.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Microsoft coco: Common objects in context

Reference 38

Resolution
unresolved
no resolver link, observed 2026-08-12T05:13:50.120227Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T05:13:50.120227Z digest=sha256:1061178dc545396d4c8b349cb550253d903a8565983991021908a1f670b77108

Observation 7cfe3bf3-6fc9-447c-9ad6-f3a732555d2a · outbound

This paper cites Learning a recurrent residual fusion network for multimodal matching.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Learning a recurrent residual fusion network for multimodal matching

Reference 39

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T05:13:51.286492Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T05:13:50.124266Z digest=sha256:a610caa159b2da9fe6b5ac73e8a4aacfcdac363bcbf7cb6ac03bd33d7ff346a9

Observation 8ea95b71-15e6-45ac-a3b7-82a473567ab1 · outbound

This paper cites CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval

Reference 40

Resolution
unresolved
no resolver link, observed 2026-08-12T05:13:50.127973Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T05:13:50.127973Z digest=sha256:cd05eced215215ac9844dfdd296b3a40db163461ac424b4b1845bc9b6751a97d

Observation 57654ad3-a586-499e-a59b-dd6b3e777317 · outbound

This paper cites Mention Extraction and Linking for SQL Query Generation.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Mention Extraction and Linking for SQL Query Generation

Reference 41

Resolution
verified exact
local_arxiv, observed 2026-08-12T05:13:50.610579Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T05:13:50.132060Z digest=sha256:74f79db173bbaf62573bb2508d38a4c0fec3652c9602b5010189eefd53e56f32

Observation 5e18f7a1-3d24-4eb2-9cbe-11042471f245 · outbound

This paper cites an unresolved cited work.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Unresolved cited work

Reference 42

Resolution
unresolved
no resolver link, observed 2026-08-12T05:13:50.136325Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T05:13:50.136325Z digest=sha256:c50d75acd39acb35b189766d820989978b3e08d5c5c065cee8ff5e6383d5cd4c

Observation db902d1f-3118-49e3-a51a-c31594583ccd · outbound

This paper cites Query and keyframe representations for ad-hoc video search.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Query and keyframe representations for ad-hoc video search

Reference 43

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T05:13:51.266562Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T05:13:50.140509Z digest=sha256:5d568819c02297d4aabf418702a1f017eaa2462438a51837ec876756296becf0

Observation 7c41e9e1-57db-4adc-b5b1-021c1eaa0eff · outbound

This paper cites Senticap: Generating image descriptions with sentiments.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Senticap: Generating image descriptions with sentiments

Reference 44

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T05:13:51.255683Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T05:13:50.145103Z digest=sha256:65a1ff1f106e5c9fb4b27caa842549df1144f7891ced7046a9a9f51384a60eb6

Observation ff1e7170-ea61-4235-a9e6-9c45797df9b7 · outbound

This paper cites UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction

Reference 45

Resolution
unresolved
no resolver link, observed 2026-08-12T05:13:50.148488Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T05:13:50.148488Z digest=sha256:2c1dfccbf343c658ea83299fcbd81483dc70ce4e89971b01203297716178386e

Observation ecda0958-9b0d-49f1-be43-696cf7c7ba9f · outbound

This paper cites Howto100m: Learning a text-video embedding by watching hundred million narrated video clips.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Howto100m: Learning a text-video embedding by watching hundred million narrated video clips

Reference 46

Resolution
unresolved
no resolver link, observed 2026-08-12T05:13:50.152020Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T05:13:50.152020Z digest=sha256:99afdaf9a1afa2bbd676f355ca3f09c9a547c18fd47180b41b24bd01b1ab5924

Observation 94cff172-0fa1-4c28-a93c-0cf7b0ab55b7 · outbound

This paper cites Learning joint embedding with multimodal cues for cross-modal video-text retrieval.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Learning joint embedding with multimodal cues for cross-modal video-text retrieval

Reference 47

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T05:13:51.235852Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T05:13:50.155828Z digest=sha256:acd85ba4d3a293b6b6a77a75b25789dd9f238ccaf8383ba7a69a6a3d043fd6b5

Observation dc25b34f-f0c4-442e-93e0-9ddf0eb5f190 · outbound

This paper cites Seesaw: interactive ad-hoc search over image databases.Proceedings of the ACM on Management of Data, 1(4):1–26, 2023.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Seesaw: interactive ad-hoc search over image databases.Proceedings of the ACM on Management of Data, 1(4):1–26, 2023

Reference 48

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T05:13:51.223632Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T05:13:50.159210Z digest=sha256:6488fbceef6751812a816e022eb0ba084f543dd61f17b76522d15573b2885983

Observation c156cb2f-7059-4f42-833b-4e051564955c · outbound

This paper cites Randomized algorithms.ACM Computing Surveys (CSUR), 28(1):33–37, 1996.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Randomized algorithms.ACM Computing Surveys (CSUR), 28(1):33–37, 1996

Reference 49

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T05:13:51.211325Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T05:13:50.163528Z digest=sha256:80a5170a2f61713a815da6666b1defb446690bfc720099d529b6622fc5a53353

Observation a85a2efa-8d1f-4bf8-832f-8fc776477ff0 · outbound

This paper cites Learning and transferring mid- level image representations using convolutional neural networks.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Learning and transferring mid- level image representations using convolutional neural networks

Reference 50

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T05:13:51.199007Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T05:13:50.168245Z digest=sha256:4de068f1097ebc7d199d5aa998054f7043388a829a1d89a276f7ec145f905156

Observation 003ebfd0-88fd-46a8-bcf7-baee9dbb1710 · outbound

This paper cites DINOv2: Learning Robust Visual Features without Supervision.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries DINOv2: Learning Robust Visual Features without Supervision

Reference 51

Resolution
unresolved
no resolver link, observed 2026-08-12T05:13:50.173310Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T05:13:50.173310Z digest=sha256:328eaba597c70ae621e2046bd92e55741b2c214105ffcf8dfb82dd3cedd61ccf

Observation 0b3b9726-b634-41f3-9cdf-7f5366ec2e90 · outbound

This paper cites Composing object relations and attributes for image-text matching.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Composing object relations and attributes for image-text matching

Reference 52

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T05:13:51.185285Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T05:13:50.178729Z digest=sha256:1d755e50ef35af7061a52363f65e5e8925c92e4924b3ec06dfb7d4bd342f019f

Observation 8dbc31df-52b8-4149-8ac7-4d1693105ac0 · outbound

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

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Learning transferable visual models from natural language supervision

Reference 53

Resolution
unresolved
no resolver link, observed 2026-08-12T05:13:50.182720Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T05:13:50.182720Z digest=sha256:88a580cd2bb94dbfa0ebec42286fff28277fc346be22c5441a2d02775e2012ff

Observation d0493ea1-7e87-439a-836f-6e106a6499a1 · outbound

This paper cites Hierarchical Text-Conditional Image Generation with CLIP Latents.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Hierarchical Text-Conditional Image Generation with CLIP Latents

Reference 54

Resolution
unresolved
no resolver link, observed 2026-08-12T05:13:50.186761Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T05:13:50.186761Z digest=sha256:7bc74c3f15878c31439ed06f9e9e0b0aceb6dd366b45d946be71c0a9e18d788d

Observation 132c63d3-4d6b-47d1-b15f-b618eacbc94f · outbound

This paper cites A new approach to cross-modal multimedia retrieval.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries A new approach to cross-modal multimedia retrieval

Reference 55

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T05:13:51.165166Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T05:13:50.190887Z digest=sha256:09fdf02936fbf2f9a0d0873a8343e5be904aef86a14b3a9eb334a27dcedf2004

Observation 5cf954cf-f3db-4a44-9348-a400436f5255 · outbound

This paper cites Cola: A benchmark for compositional text-to-image retrieval.Advances in Neural Information Processing Systems, 36:46433–46445, 2023.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Cola: A benchmark for compositional text-to-image retrieval.Advances in Neural Information Processing Systems, 36:46433–46445, 2023

Reference 56

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T05:13:51.152604Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T05:13:50.194703Z digest=sha256:ee300523f8529fc65f24aae35c7582f388a472992942df64c6257ec0c79398eb

Observation 54fef369-921b-4784-a006-efc7a17d144f · outbound

This paper cites High- resolution image synthesis with latent diffusion models.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries High- resolution image synthesis with latent diffusion models

Reference 57

Resolution
unresolved
no resolver link, observed 2026-08-12T05:13:50.198754Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T05:13:50.198754Z digest=sha256:c38be7f15bbae7006931c3f92db73ff736e3282d69dbdd39f003218c5e976706

Observation 61cb84e6-2eee-4f48-923f-686523a3c392 · outbound

This paper cites Multi-modal joint embedding for fashion product retrieval.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Multi-modal joint embedding for fashion product retrieval

Reference 58

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T05:13:51.132046Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T05:13:50.202732Z digest=sha256:cc639825fee54f80a37433dc93b4f3ac6e2e1da9331185b7a0989a0f5a16b77b

Observation 6a89fbc5-22b2-48e6-9840-fa3f50d72edd · outbound

This paper cites Coverage-based data-centric approaches for responsible and trustworthy ai.IEEE Data Eng.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Coverage-based data-centric approaches for responsible and trustworthy ai.IEEE Data Eng

Reference 59

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T05:13:51.118412Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T05:13:50.206934Z digest=sha256:1083dd22ae5cc1201cbd00eefefab15d51ac04e51782778bf4387b6db185d0da

Observation 1628244f-5705-4288-81be-a87172f5b3de · outbound

This paper cites Flava: A foundational language and vision alignment model.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Flava: A foundational language and vision alignment model

Reference 60

Resolution
unresolved
no resolver link, observed 2026-08-12T05:13:50.211066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T05:13:50.211066Z digest=sha256:0fa144e6596d7745ef3b3113ea2762d43a04e8760e8e46afbcab283922dc90f4

Observation ba62b6fc-fc0c-49de-be79-5ba96d9504f1 · outbound

This paper cites Data Augmentation Using GANs.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Data Augmentation Using GANs

Reference 61

Resolution
unresolved
no resolver link, observed 2026-08-12T05:13:50.215362Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T05:13:50.215362Z digest=sha256:4c410a06c2f0b71f6d8fb5d5a627d92634c4c2cbaef2916825624badf2b43cf2

Observation 3834c631-7f7f-478e-8e31-5ffc135ace34 · outbound

This paper cites Interacting- enhancing feature transformer for cross-modal remote-sensing image and text retrieval.IEEE Transactions on Geoscience and Remote Sensing, 61:1–15, 2023.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Interacting- enhancing feature transformer for cross-modal remote-sensing image and text retrieval.IEEE Transactions on Geoscience and Remote Sensing, 61:1–15, 2023

Reference 62

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T05:13:51.095571Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T05:13:50.219014Z digest=sha256:ce978fa5f2183b93b68555707d7e36777168092206ba06e0f02096e7ee6ec082

Observation dbbc7171-f808-47df-a0ad-6c6c07c49433 · outbound

This paper cites Winoground: Probing vision and language models for visio-linguistic compositionality.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Winoground: Probing vision and language models for visio-linguistic compositionality

Reference 63

Resolution
unresolved
no resolver link, observed 2026-08-12T05:13:50.222876Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T05:13:50.222876Z digest=sha256:d5c0b54f1541ce0d6d3e1b4cf549aa3e60924e5a7c3162dc7693be8f672df3f8

Observation 840cb99b-1bc7-408b-a4ef-c713959af5d5 · outbound

This paper cites Learning Language-Visual Embedding for Movie Understanding with Natural-Language.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Learning Language-Visual Embedding for Movie Understanding with Natural-Language

Reference 64

Resolution
unresolved
no resolver link, observed 2026-08-12T05:13:50.226247Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T05:13:50.226247Z digest=sha256:d6cad73ab5635fb71df7dbbe53146ad1fd0b3f4f6da9838440c0350f63f837da

Observation bd8c26fd-7865-4ca7-b5de-0ed6363d70a5 · outbound

This paper cites Training deep networks with synthetic data: Bridging the reality gap by domain randomization.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Training deep networks with synthetic data: Bridging the reality gap by domain randomization

Reference 65

Resolution
unresolved
no resolver link, observed 2026-08-12T05:13:50.230613Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T05:13:50.230613Z digest=sha256:3b87d2f05564c7e3499f0b6df892b8d2b886df4b5c2056f85641aaecd955e145

Observation 4db8cbd5-d230-464c-93f7-9d1c5948e843 · outbound

This paper cites Codexdb: Synthesizing code for query processing from natural language instructions using gpt-3 codex.Proceedings of the VLDB Endowment, 15(11):2921–2928, 2022.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Codexdb: Synthesizing code for query processing from natural language instructions using gpt-3 codex.Proceedings of the VLDB Endowment, 15(11):2921–2928, 2022

Reference 66

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T05:13:51.062904Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T05:13:50.234987Z digest=sha256:181baabc4ad1feb9c14b02430bbf060da5397ecc082748b4d05ab096b0b10777

Observation 2a11ac16-5a54-40f7-9e4b-2cf2103b15fd · outbound

This paper cites Demonstrating gpt-db: Generating query-specific and customizable code for sql processing with gpt-4.Proceedings of the VLDB Endowment, 16(12):4098–4101, 2023.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Demonstrating gpt-db: Generating query-specific and customizable code for sql processing with gpt-4.Proceedings of the VLDB Endowment, 16(12):4098–4101, 2023

Reference 67

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T05:13:51.048698Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T05:13:50.239658Z digest=sha256:a036fa66ffda80de2819f7a05b5da2768693d26c241fe47a7a3a4cbb07d43f3c

Observation 56c70c32-b6a1-4f4a-8a01-6f232292a81d · outbound

This paper cites Diffusion Models for Tabular Data Imputation and Synthetic Data Generation.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Diffusion Models for Tabular Data Imputation and Synthetic Data Generation

Reference 68

Resolution
unresolved
no resolver link, observed 2026-08-12T05:13:50.244361Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T05:13:50.244361Z digest=sha256:b0a066a005c65617e1c42d56bd27817743fd26d7ae34eb4335d61fd0c3706e38

Observation 8817a9e3-cdea-4f7b-90ae-a7f896f402ed · outbound

This paper cites Image-text cross- modal retrieval via modality-specific feature learning.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Image-text cross- modal retrieval via modality-specific feature learning

Reference 69

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T05:13:51.036041Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T05:13:50.248854Z digest=sha256:01a3f73fc3d2833e1e7c53c5e6b611ad574a65b25c6a22f484ed9cfa00dd4264

Observation f3330211-bd5e-4242-952e-72fab252c0f0 · outbound

This paper cites Cluster-sensitive structured correlation analysis for web cross-modal retrieval.Neurocomputing, 168:747–760, 2015.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Cluster-sensitive structured correlation analysis for web cross-modal retrieval.Neurocomputing, 168:747–760, 2015

Reference 70

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T05:13:51.022253Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T05:13:50.252920Z digest=sha256:b3f88aefc60e9b78f312acad98d423948b93f9602fa9e7ddfaaca8025709bc67

Observation b7c8f82b-1492-498a-bb58-b6a967587808 · outbound

This paper cites Cross- modal retrieval: a systematic review of methods and future directions.Proceedings of the IEEE, 2025.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Cross- modal retrieval: a systematic review of methods and future directions.Proceedings of the IEEE, 2025

Reference 71

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T05:13:51.008442Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T05:13:50.257618Z digest=sha256:da8119d17526f344a82a660367747fa94816cdacb9c1c2ac84acaa529efb9e73

Observation d018c000-e9ef-46fc-a56f-9e8fa842977a · outbound

This paper cites Minilm: Deep self-attention distillation for task-agnostic compression of pre-trained transformers.Advances in neural information processing systems, 33:5776–5788, 2020.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Minilm: Deep self-attention distillation for task-agnostic compression of pre-trained transformers.Advances in neural information processing systems, 33:5776–5788, 2020

Reference 72

Resolution
unresolved
no resolver link, observed 2026-08-12T05:13:50.262678Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T05:13:50.262678Z digest=sha256:8836a6f1c81ab51bfe4c664f6d193ef6dd8415be52f503dc18b47f52ba74aed0

Observation 003373c8-4e1d-4e0e-9d04-f9b2e30ebb8b · outbound

This paper cites Convnext v2: Co-designing and scaling convnets with masked autoencoders.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Convnext v2: Co-designing and scaling convnets with masked autoencoders

Reference 73

Resolution
unresolved
no resolver link, observed 2026-08-12T05:13:50.266174Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T05:13:50.266174Z digest=sha256:2b29aa8aa5cfbce6aa66ad9bac27af658bc11efd3582b38d47ab51886449f6a4

Observation 306cb27b-073f-4b70-928f-6cc02880127b · outbound

This paper cites Improving text-audio retrieval by text-aware attention pooling and prior matrix revised loss.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Improving text-audio retrieval by text-aware attention pooling and prior matrix revised loss

Reference 74

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T05:13:50.976466Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T05:13:50.269491Z digest=sha256:ebfdbd153146a67dff37ac5ded2bf7797726b135aa1a50a40591996b3b225588

Observation d162a88a-9f7a-42dc-b04d-459d9d2dc2c2 · outbound

This paper cites Regnet: self-regulated network for image classification.IEEE Transactions on Neural Networks and Learning Systems, 34(11):9562–9567, 2022.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Regnet: self-regulated network for image classification.IEEE Transactions on Neural Networks and Learning Systems, 34(11):9562–9567, 2022

Reference 75

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T05:13:50.962144Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T05:13:50.273139Z digest=sha256:2e3c37407b2c3969c83ed522a065ccf9ee966fc5267ecd567491aca605878811

Observation 78bd2647-525b-4f47-aab9-15c6ed938557 · outbound

This paper cites Re- thinking label-wise cross-modal retrieval from a semantic sharing perspective.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Re- thinking label-wise cross-modal retrieval from a semantic sharing perspective

Reference 76

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T05:13:50.948591Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T05:13:50.277165Z digest=sha256:e38336c77d3a5c40128ca92e36814733a538d5212cac4903bbfb7bef702064af

Observation 8bb25eb5-e961-4073-bc13-0960d3a6882b · outbound

This paper cites Saliencycut: Augmenting plausible anomalies for anomaly detection.Pattern Recognition, 153:110508, 2024.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Saliencycut: Augmenting plausible anomalies for anomaly detection.Pattern Recognition, 153:110508, 2024

Reference 77

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T05:13:50.935283Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T05:13:50.281012Z digest=sha256:2f12826280757edc5a59d6497ae9fbbd7f8c6908b21732f15fa119ef46eb4b44

Observation 5db307f8-62f4-4c37-abaa-198e90b28e8b · outbound

This paper cites Data structures and algorithms for nearest neighbor search in general metric spaces.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Data structures and algorithms for nearest neighbor search in general metric spaces

Reference 78

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T05:13:50.921375Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T05:13:50.285560Z digest=sha256:e2159216cb8d61fa25c815cd052f8e2e93cab10bf396d315f6d93919b439d2fa

Observation c626ba84-4d8a-4ea7-9a66-335e54ffb417 · outbound

This paper cites Bdd100k: A diverse driving dataset for heterogeneous mul- titask learning.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Bdd100k: A diverse driving dataset for heterogeneous mul- titask learning

Reference 79

Resolution
unresolved
no resolver link, observed 2026-08-12T05:13:50.290261Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T05:13:50.290261Z digest=sha256:c809583e9516a5d0b249234d86030743042a9f52e11ac780ba3e817c14ca7b60

Observation 093a73e4-9905-4024-9955-534654d2cf36 · outbound

This paper cites Text-to-image Diffusion Models in Generative AI: A Survey.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Text-to-image Diffusion Models in Generative AI: A Survey

Reference 80

Resolution
unresolved
no resolver link, observed 2026-08-12T05:13:50.294956Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T05:13:50.294956Z digest=sha256:18a23717f3bca9ea655631b2768a14eebc42930465668403bf02127bc36aac91

Observation 3abe202b-f128-409b-bc8c-49c9827b9d5d · outbound

This paper cites Interactive retrieval based on faceted feedback.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Interactive retrieval based on faceted feedback

Reference 81

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T05:13:50.898139Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T05:13:50.299464Z digest=sha256:917143f344ef70ce8ff146c9e3506dfc2d97a8e097ea11a30b3ca5186fa11ac0

Observation a90a289f-4419-4615-b211-270d0e889d74 · outbound

This paper cites Editing-Based SQL Query Generation for Cross-Domain Context-Dependent Questions.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Editing-Based SQL Query Generation for Cross-Domain Context-Dependent Questions

Reference 82

Resolution
unresolved
no resolver link, observed 2026-08-12T05:13:50.303657Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T05:13:50.303657Z digest=sha256:2877f265f7e9d4369658b7fd08cc8f338aacd3c642d77904b97ebd5a765c107d

Observation b712a92d-adc2-4146-be6d-90990570a4cd · outbound

This paper cites Recognize anything: A strong image tagging model.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Recognize anything: A strong image tagging model

Reference 83

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T05:13:50.885946Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T05:13:50.308737Z digest=sha256:dbd7cc1d909326eaf371958507fd46475d61c81f42d14b805b38a3ce0c4b0f7c

Observation fc589fc1-19d9-4da2-bf5c-ca6cce20f353 · outbound

This paper cites Relevance feedback in image retrieval: A comprehen- sive review.Multimedia systems, 8:536–544, 2003.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Relevance feedback in image retrieval: A comprehen- sive review.Multimedia systems, 8:536–544, 2003

Reference 84

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T05:13:50.872818Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T05:13:50.312134Z digest=sha256:8c1888e28ec3c942631a723cd4935aaff51631c70b080cdb655a0eabdfbc592b

Observation dc3c0932-c0c9-4094-a893-baaac7a13db1 · outbound

This paper cites complex.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries complex

Reference 85

Resolution
verified exact
raw_fallback, observed 2026-08-12T05:13:50.487397Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T05:13:50.315751Z digest=sha256:b62082442df1d558ff03c073f5da2ae7ffe131c32d1e8535a569d719776464ea

Observation 4707a352-3bb5-4c85-84f4-3cab6ec2a4dd · outbound

This paper cites hard categories.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries hard categories

Reference 86

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T05:13:50.861769Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T05:13:50.320991Z digest=sha256:11fe652b68d61a4249347c25894ed2c362b5493ce3624afb08e6bc3baf709d1d

Observation 6f59687e-ec73-4c55-b87b-0b3e615186a7 · outbound

This paper cites However, while CLIP (in our clip-vit-base-patch32 variant) uses a Vision Transformer for image encoding, ALIGN typically uses a CNN image encoder along with a Transformer for text.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries However, while CLIP (in our clip-vit-base-patch32 variant) uses a Vision Transformer for image encoding, ALIGN typically uses a CNN image encoder along with a Transformer for text

Reference 87

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T05:13:50.850455Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T05:13:50.325178Z digest=sha256:a1f3a0dfd708dd7c031a8e35752e5d1f00edb2b328c753f244c844717a528aa9

Observation 44862ebd-8d22-4ba6-b439-a2e7fadbccf4 · outbound

This paper cites an unresolved cited work.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Unresolved cited work

Reference 88

Resolution
unresolved
raw_fallback, observed 2026-08-12T05:13:50.839036Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T05:13:50.329599Z digest=sha256:06b1acfaf22ad14efdeff945a1437a5d9a5fe8dcbdef5a9e5edb4a19901b32d2

Observation e2dd76e6-d762-4d52-97ba-25e3efecd724 · outbound

This paper cites The generated captions are then transformed into embeddings with MiniLM [72]30, a robust text encoder widely adopted in industrial applications.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries The generated captions are then transformed into embeddings with MiniLM [72]30, a robust text encoder widely adopted in industrial applications

Reference 89

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T05:13:50.827473Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T05:13:50.333937Z digest=sha256:d8c9b4b7acbf8b1dfc3a6fe2bcb8d3b50549eb4a967cfb843bd61f5f84429c28

Observation f09832f3-108a-4da3-ac67-d4bbe1e21ff6 · outbound

This paper cites Its diverse object classes make it a useful benchmark for assessing the robustness of detection and retrieval models.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Its diverse object classes make it a useful benchmark for assessing the robustness of detection and retrieval models

Reference 90

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T05:13:50.815240Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T05:13:50.338469Z digest=sha256:91f234863ed44e40d0df3c354c94617d3324f87c11c07e6ca5120482f67edf19

Observation 08f3106d-0611-4934-8d62-bee28d29f3eb · outbound

This paper cites Its comprehensive annotations and varied scene compositions provide a challenging testbed.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Its comprehensive annotations and varied scene compositions provide a challenging testbed

Reference 91

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T05:13:50.802825Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T05:13:50.344014Z digest=sha256:6a2563b4f2cd5bd82dbe8a2b51094e3cb4f21d1357faa37a3948523a80b27168

Observation c9a1bc4f-db46-46be-8cbc-9beef33b8461 · outbound

This paper cites Its focus on rare and fine-grained objects is critical for evaluating retrieval performance on less frequent classes.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Its focus on rare and fine-grained objects is critical for evaluating retrieval performance on less frequent classes

Reference 92

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T05:13:50.789721Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T05:13:50.348906Z digest=sha256:f7fd2db11deee44cd42c35d25442d6aef7c96069dfa498bde305effe8347d5b7

Observation fc3f5d7f-ec0d-42ed-8161-fe631ca9a18a · outbound

This paper cites an unresolved cited work.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Unresolved cited work

Reference 93

Resolution
unresolved
raw_fallback, observed 2026-08-12T05:13:50.775213Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T05:13:50.353749Z digest=sha256:384f0797f457873d7ce537b1a4f5480cfe3ba45a077138e3acdd0eed8121883c

Observation 2e1f6167-9cf9-404f-8ea5-aa75c944c7d0 · outbound

This paper cites an unresolved cited work.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Unresolved cited work

Reference 94

Resolution
unresolved
raw_fallback, observed 2026-08-12T05:13:50.761918Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T05:13:50.357814Z digest=sha256:52ea26ecfa6bbb1e6ed5b08b09b57059d594ab77e846d3173c08b910d15fc539

Observation 28c9aa30-21d8-41f9-bcda-a99997e02d9c · outbound

This paper cites This dataset challenges models to accurately map nuanced language to the corresponding image, serving as a stringent test of fine-grained retrieval performance.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries This dataset challenges models to accurately map nuanced language to the corresponding image, serving as a stringent test of fine-grained retrieval performance

Reference 95

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T05:13:50.750959Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T05:13:50.362288Z digest=sha256:83f23d383cb2c5a81164d9a656607f5067f758d1c1b6a1f1f0cbade6f0b6323d

Observation 7e9add9b-2666-45da-902b-a29577210573 · outbound

This paper cites It is crucial for evaluating a model’s ability to handle zero-shot retrieval on images containing objects not commonly found in standard captioning datasets.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries It is crucial for evaluating a model’s ability to handle zero-shot retrieval on images containing objects not commonly found in standard captioning datasets

Reference 96

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T05:13:50.739954Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T05:13:50.366427Z digest=sha256:6e2e0e720772d710881724f4f48d3927869db2a74f90e006ae5eedd1d4219013

Observation 6b6530b0-6158-4239-81cb-78b93666f499 · outbound

This paper cites Left is better,.

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries Left is better,

Reference 97

Resolution
malformed identifier
raw_fallback, observed 2026-08-12T05:13:50.728272Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-08-12T05:13:50.370465Z digest=sha256:ffe9f21eb4efc59f919a5c390ff5835d46bfb23645ba33dcaaeac9d91ae49a96

Pith citing papers

No inbound Pith citation observations are available.