Emotion Knowledge Enhancement for Vision Large Language Models: A Self-Verification Approach for High-Quality Emotion Instruction Data Generation | Paper Citation Record

Observation fd585619-4881-4431-a9bd-fe730379ea18 · outbound

This paper cites A comprehensive review of facial expression recognition techniques.Multimedia Systems, 29(1):73–103, 2023.

Emotion Knowledge Enhancement for Vision Large Language Models: A Self-Verification Approach for High-Quality Emotion Instruction Data Generation A comprehensive review of facial expression recognition techniques.Multimedia Systems, 29(1):73–103, 2023

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:44:30.448939Z

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 f4c81d0c-efae-426b-84af-0d4c07a6e459 · outbound

This paper cites Llama 3 model card.

Emotion Knowledge Enhancement for Vision Large Language Models: A Self-Verification Approach for High-Quality Emotion Instruction Data Generation Llama 3 model card

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-15T21:44:28.900814Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9b005ec-5505-41f0-9761-d91329bffaf0 · outbound

This paper cites Claude-3.5.

Emotion Knowledge Enhancement for Vision Large Language Models: A Self-Verification Approach for High-Quality Emotion Instruction Data Generation Claude-3.5

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-15T21:44:28.909847Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e518addc-9255-4a91-9ee1-bb992dda0440 · outbound

This paper cites Qwen2.5-VL Technical Report.

Emotion Knowledge Enhancement for Vision Large Language Models: A Self-Verification Approach for High-Quality Emotion Instruction Data Generation Qwen2.5-VL Technical Report

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-15T21:44:28.915865Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation efa85399-bc12-401f-8eb7-10c7d6329949 · outbound

This paper cites Video-based facial micro-expression analysis: A survey of datasets, features and algorithms.IEEE transactions on pattern analysis and machine intelligence, 44(9):5826–5846, 2021.

Emotion Knowledge Enhancement for Vision Large Language Models: A Self-Verification Approach for High-Quality Emotion Instruction Data Generation Video-based facial micro-expression analysis: A survey of datasets, features and algorithms.IEEE transactions on pattern analysis and machine intelligence, 44(9):5826–5846, 2021

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:44:30.393790Z

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 f1a0ea46-782d-486d-9fd2-3cc0bb322616 · outbound

This paper cites Knowledge-driven self-supervised representa- tion learning for facial action unit recognition.

Emotion Knowledge Enhancement for Vision Large Language Models: A Self-Verification Approach for High-Quality Emotion Instruction Data Generation Knowledge-driven self-supervised representa- tion learning for facial action unit recognition

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:44:30.373312Z

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 64dff31f-2c95-413c-bc29-a408f7a74e10 · outbound

This paper cites MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning.

Emotion Knowledge Enhancement for Vision Large Language Models: A Self-Verification Approach for High-Quality Emotion Instruction Data Generation MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-15T21:44:28.941071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6df65fbd-105c-42ed-bcb9-d5ad5940160a · outbound

This paper cites How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites.

Emotion Knowledge Enhancement for Vision Large Language Models: A Self-Verification Approach for High-Quality Emotion Instruction Data Generation How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-15T21:44:28.948070Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c113b1d2-cb90-4053-9e67-7f9642cd5069 · outbound

This paper cites Emotion-LLaMA: Multimodal Emotion Recognition and Reasoning with Instruction Tuning.

Emotion Knowledge Enhancement for Vision Large Language Models: A Self-Verification Approach for High-Quality Emotion Instruction Data Generation Emotion-LLaMA: Multimodal Emotion Recognition and Reasoning with Instruction Tuning

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-15T21:44:28.953395Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6480a781-f225-4d80-bd6a-e0962068275f · outbound

This paper cites Knowledge augmented deep neural networks for joint facial expression and action unit recognition.

Emotion Knowledge Enhancement for Vision Large Language Models: A Self-Verification Approach for High-Quality Emotion Instruction Data Generation Knowledge augmented deep neural networks for joint facial expression and action unit recognition

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:44:30.357090Z

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 0b40f4f7-85c6-414f-93d8-9a224ae0e826 · outbound

This paper cites Knowledge augmented deep neural networks for joint facial expression and action unit recognition.Advances in Neural Information Processing Systems, 33:14338–14349, 2020.

Emotion Knowledge Enhancement for Vision Large Language Models: A Self-Verification Approach for High-Quality Emotion Instruction Data Generation Knowledge augmented deep neural networks for joint facial expression and action unit recognition.Advances in Neural Information Processing Systems, 33:14338–14349, 2020

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:44:30.338683Z

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 70b427b1-5d35-4377-8650-259d7ecd28e4 · outbound

This paper cites Decomposition of uncertainty in bayesian deep learning for efficient and risk-sensitive learning.

Emotion Knowledge Enhancement for Vision Large Language Models: A Self-Verification Approach for High-Quality Emotion Instruction Data Generation Decomposition of uncertainty in bayesian deep learning for efficient and risk-sensitive learning

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:44:30.319853Z

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 ad635b35-ec6a-4bfd-963f-c24dba3eaed2 · outbound

This paper cites Consulting Psychologists Press, 1978.

Emotion Knowledge Enhancement for Vision Large Language Models: A Self-Verification Approach for High-Quality Emotion Instruction Data Generation Consulting Psychologists Press, 1978

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:44:30.302560Z

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 e0164aa9-a2d8-4f3b-8ba0-e1a5767d1518 · outbound

This paper cites Universals and cultural differences in the judgments of facial expressions of emotion.Journal of personality and social psychology, 53(4):712, 1987.

Emotion Knowledge Enhancement for Vision Large Language Models: A Self-Verification Approach for High-Quality Emotion Instruction Data Generation Universals and cultural differences in the judgments of facial expressions of emotion.Journal of personality and social psychology, 53(4):712, 1987

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:44:30.284906Z

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 75196822-5c1b-464b-9ded-20435cad4d14 · outbound

This paper cites Oxford University Press, USA, 1997.

Emotion Knowledge Enhancement for Vision Large Language Models: A Self-Verification Approach for High-Quality Emotion Instruction Data Generation Oxford University Press, USA, 1997

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:44:30.267463Z

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 14a49383-e8f3-456d-8012-77ed47e06e97 · outbound

This paper cites Selfme: Self-supervised motion learning for micro-expression recognition.

Emotion Knowledge Enhancement for Vision Large Language Models: A Self-Verification Approach for High-Quality Emotion Instruction Data Generation Selfme: Self-supervised motion learning for micro-expression recognition

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:44:30.249255Z

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 3da9ee51-14c9-4a74-bb20-d6377e3075db · outbound

This paper cites StimuVAR: Spatiotemporal Stimuli-aware Video Affective Reasoning with Multimodal Large Language Models.

Emotion Knowledge Enhancement for Vision Large Language Models: A Self-Verification Approach for High-Quality Emotion Instruction Data Generation StimuVAR: Spatiotemporal Stimuli-aware Video Affective Reasoning with Multimodal Large Language Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-15T21:44:29.001846Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a11e821-1bf5-4677-beb8-bdae00a73d9f · outbound

This paper cites Opera: Alleviating hallucination in multi-modal large language models via over-trust penalty and retrospection- allocation.

Emotion Knowledge Enhancement for Vision Large Language Models: A Self-Verification Approach for High-Quality Emotion Instruction Data Generation Opera: Alleviating hallucination in multi-modal large language models via over-trust penalty and retrospection- allocation

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:44:30.225745Z

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 57c4d9c6-abde-4ca6-a54f-8f3c02e4eb99 · outbound

This paper cites Disentangling identity and pose for facial ex- pression recognition.IEEE Transactions on Affective Computing, 13(4):1868–1878, 2022.

Emotion Knowledge Enhancement for Vision Large Language Models: A Self-Verification Approach for High-Quality Emotion Instruction Data Generation Disentangling identity and pose for facial ex- pression recognition.IEEE Transactions on Affective Computing, 13(4):1868–1878, 2022

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:44:30.205050Z

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 745b3899-9528-4f52-b83f-f36bb18e897b · outbound

This paper cites Scaling Laws for Neural Language Models.

Emotion Knowledge Enhancement for Vision Large Language Models: A Self-Verification Approach for High-Quality Emotion Instruction Data Generation Scaling Laws for Neural Language Models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-15T21:44:29.020890Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4dbe5b7c-5255-4780-858c-4b1e63e723ed · outbound

This paper cites What uncertainties do we need in bayesian deep learning for computer vision?Advances in neural information processing systems, 30, 2017.

Emotion Knowledge Enhancement for Vision Large Language Models: A Self-Verification Approach for High-Quality Emotion Instruction Data Generation What uncertainties do we need in bayesian deep learning for computer vision?Advances in neural information processing systems, 30, 2017

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-15T21:44:29.027335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 14e3cbe0-f036-49c6-9812-b2f827fa4ebe · outbound

This paper cites Expression, Affect, Action Unit Recognition: Aff-Wild2, Multi-Task Learning and ArcFace.

Emotion Knowledge Enhancement for Vision Large Language Models: A Self-Verification Approach for High-Quality Emotion Instruction Data Generation Expression, Affect, Action Unit Recognition: Aff-Wild2, Multi-Task Learning and ArcFace

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-15T21:44:29.032686Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e131d91b-6d0a-42ba-9509-7a97a75e051a · outbound

This paper cites LLaVA-OneVision: Easy Visual Task Transfer.

Emotion Knowledge Enhancement for Vision Large Language Models: A Self-Verification Approach for High-Quality Emotion Instruction Data Generation LLaVA-OneVision: Easy Visual Task Transfer

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-15T21:44:29.038401Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9df44d5-067c-460b-a979-2be5b9b89ed7 · outbound

This paper cites LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models.

Emotion Knowledge Enhancement for Vision Large Language Models: A Self-Verification Approach for High-Quality Emotion Instruction Data Generation LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-15T21:44:29.051757Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7e0f455-66ff-43f4-b495-efc396b13ea6 · outbound

This paper cites Deep facial expression recognition: A survey.IEEE transactions on affective computing, 13(3):1195–1215, 2020.

Emotion Knowledge Enhancement for Vision Large Language Models: A Self-Verification Approach for High-Quality Emotion Instruction Data Generation Deep facial expression recognition: A survey.IEEE transactions on affective computing, 13(3):1195–1215, 2020

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:44:30.168425Z

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 fc6dc9f8-2aa3-4003-a90e-44dd3b59918c · outbound

This paper cites Reliable crowdsourcing and deep locality-preserving learning for expression recognition in the wild.

Emotion Knowledge Enhancement for Vision Large Language Models: A Self-Verification Approach for High-Quality Emotion Instruction Data Generation Reliable crowdsourcing and deep locality-preserving learning for expression recognition in the wild

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-15T21:44:29.062498Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9be963ef-447c-4508-bf1d-b1e0c7f15dce · outbound

This paper cites AffectGPT: Dataset and Framework for Explainable Multimodal Emotion Recognition.

Emotion Knowledge Enhancement for Vision Large Language Models: A Self-Verification Approach for High-Quality Emotion Instruction Data Generation AffectGPT: Dataset and Framework for Explainable Multimodal Emotion Recognition

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-15T21:44:29.077312Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98a81cd0-be0a-462b-ab95-3b99c413f73b · outbound

This paper cites Gpt-4v with emotion: A zero-shot benchmark for generalized emotion recognition.Information Fusion, 108:102367, 2024.

Emotion Knowledge Enhancement for Vision Large Language Models: A Self-Verification Approach for High-Quality Emotion Instruction Data Generation Gpt-4v with emotion: A zero-shot benchmark for generalized emotion recognition.Information Fusion, 108:102367, 2024

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:44:30.132961Z

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 a712980b-a266-4421-a2fc-2ed05ad21a9f · outbound

This paper cites Video-LLaVA: Learning United Visual Representation by Alignment Before Projection.

Emotion Knowledge Enhancement for Vision Large Language Models: A Self-Verification Approach for High-Quality Emotion Instruction Data Generation Video-LLaVA: Learning United Visual Representation by Alignment Before Projection

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-15T21:44:29.089156Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dbf13a1f-c0d8-4dbe-b698-d95295c02381 · outbound

This paper cites an unresolved cited work.

Emotion Knowledge Enhancement for Vision Large Language Models: A Self-Verification Approach for High-Quality Emotion Instruction Data Generation Unresolved cited work

Reference 31

Resolution: unresolved; raw_fallback, observed 2026-08-15T21:44:30.113934Z

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 51b2a338-d5b0-4a45-bdc6-eebed7f88f3c · outbound

This paper cites Improved baselines with visual instruction tuning.

Emotion Knowledge Enhancement for Vision Large Language Models: A Self-Verification Approach for High-Quality Emotion Instruction Data Generation Improved baselines with visual instruction tuning

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-15T21:44:29.099555Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e3975bf9-e31e-4837-b8cf-bd9194cfc3c3 · outbound

This paper cites Visual instruction tuning.Advances in neural information processing systems, 36, 2024.

Emotion Knowledge Enhancement for Vision Large Language Models: A Self-Verification Approach for High-Quality Emotion Instruction Data Generation Visual instruction tuning.Advances in neural information processing systems, 36, 2024

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-15T21:44:29.105455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bcefcfd6-9b7b-433c-84e8-a4efc059aea2 · outbound

This paper cites Facial expressions elicit multiplexed perceptions of emotion categories and dimensions.Current Biology, 32(1):200–209, 2022.

Emotion Knowledge Enhancement for Vision Large Language Models: A Self-Verification Approach for High-Quality Emotion Instruction Data Generation Facial expressions elicit multiplexed perceptions of emotion categories and dimensions.Current Biology, 32(1):200–209, 2022

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:44:30.047620Z

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 77c80aab-deea-4ab0-b651-fb41d2a2aedb · outbound

This paper cites Mafw: A large-scale, multi-modal, compound affective database for dynamic facial expression recognition in the wild.

Emotion Knowledge Enhancement for Vision Large Language Models: A Self-Verification Approach for High-Quality Emotion Instruction Data Generation Mafw: A large-scale, multi-modal, compound affective database for dynamic facial expression recognition in the wild

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-15T21:44:29.121054Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 125f7e72-fa0f-4036-9d25-3013e45fa241 · outbound

This paper cites an unresolved cited work.

Emotion Knowledge Enhancement for Vision Large Language Models: A Self-Verification Approach for High-Quality Emotion Instruction Data Generation Unresolved cited work

Reference 36

Resolution: unresolved; raw_fallback, observed 2026-08-15T21:44:30.018532Z

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 79a82334-a25c-44e0-b9bd-6e1dac34184c · outbound

This paper cites Disfa: A spontaneous facial action intensity database.IEEE Transactions on Affective Computing, 4(2):151–160, 2013.

Emotion Knowledge Enhancement for Vision Large Language Models: A Self-Verification Approach for High-Quality Emotion Instruction Data Generation Disfa: A spontaneous facial action intensity database.IEEE Transactions on Affective Computing, 4(2):151–160, 2013

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:44:29.996354Z

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 8054be0b-be9f-4196-a4e4-dd3a699d5405 · outbound

This paper cites Affectnet: A database for facial expression, valence, and arousal computing in the wild.IEEE Transactions on Affective Computing, 10(1):18–31, 2017.

Emotion Knowledge Enhancement for Vision Large Language Models: A Self-Verification Approach for High-Quality Emotion Instruction Data Generation Affectnet: A database for facial expression, valence, and arousal computing in the wild.IEEE Transactions on Affective Computing, 10(1):18–31, 2017

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:44:29.976436Z

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 979104c4-dc8e-4e2f-90d1-45aeafc68fa1 · outbound

This paper cites Multi-label co- regularization for semi-supervised facial action unit recognition.

Emotion Knowledge Enhancement for Vision Large Language Models: A Self-Verification Approach for High-Quality Emotion Instruction Data Generation Multi-label co- regularization for semi-supervised facial action unit recognition

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:44:29.955566Z

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 5901f188-0ce3-4085-9712-84e3446d8ec2 · outbound

This paper cites an unresolved cited work.

Emotion Knowledge Enhancement for Vision Large Language Models: A Self-Verification Approach for High-Quality Emotion Instruction Data Generation Unresolved cited work

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-15T21:44:29.152898Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2eda21f1-d106-4c47-ab59-be000aac1d17 · outbound

This paper cites Hello gpt-4o.

Emotion Knowledge Enhancement for Vision Large Language Models: A Self-Verification Approach for High-Quality Emotion Instruction Data Generation Hello gpt-4o

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-15T21:44:29.158753Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a10c2b5b-932d-419c-b748-35c1eab6f891 · outbound

This paper cites A unified and interpretable emotion representation and expression generation.

Emotion Knowledge Enhancement for Vision Large Language Models: A Self-Verification Approach for High-Quality Emotion Instruction Data Generation A unified and interpretable emotion representation and expression generation

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:44:29.908899Z

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 d5cd58f2-4a73-469d-982c-3bc941549031 · outbound

This paper cites A circumplex model of affect.Journal of personality and social psychology, 39(6):1161, 1980.

Emotion Knowledge Enhancement for Vision Large Language Models: A Self-Verification Approach for High-Quality Emotion Instruction Data Generation A circumplex model of affect.Journal of personality and social psychology, 39(6):1161, 1980

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-15T21:44:29.178279Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation edb27f16-0e2b-4d94-a18e-edc32ab125a2 · outbound

This paper cites Uncertain graph neural networks for facial action unit detection.Proceedings of the AAAI Conference on Artificial Intelligence, 35(7):5993–6001, 2021.

Emotion Knowledge Enhancement for Vision Large Language Models: A Self-Verification Approach for High-Quality Emotion Instruction Data Generation Uncertain graph neural networks for facial action unit detection.Proceedings of the AAAI Conference on Artificial Intelligence, 35(7):5993–6001, 2021

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:44:29.875105Z

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 a8f47576-8091-4484-9c08-adbeb174d240 · outbound

This paper cites Hybrid message passing with performance-driven structures for facial action unit detection.

Emotion Knowledge Enhancement for Vision Large Language Models: A Self-Verification Approach for High-Quality Emotion Instruction Data Generation Hybrid message passing with performance-driven structures for facial action unit detection

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:44:29.854631Z

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 d3416001-0052-425e-a3a4-23903835f89c · outbound

This paper cites Gemini: A Family of Highly Capable Multimodal Models.

Emotion Knowledge Enhancement for Vision Large Language Models: A Self-Verification Approach for High-Quality Emotion Instruction Data Generation Gemini: A Family of Highly Capable Multimodal Models

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-15T21:44:29.199625Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3fe20492-2509-484f-9a1b-b6ab00c93242 · outbound

This paper cites Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context.

Emotion Knowledge Enhancement for Vision Large Language Models: A Self-Verification Approach for High-Quality Emotion Instruction Data Generation Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-15T21:44:29.207681Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3aae1250-6c06-48f5-b557-3bba229d829b · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

Emotion Knowledge Enhancement for Vision Large Language Models: A Self-Verification Approach for High-Quality Emotion Instruction Data Generation LLaMA: Open and Efficient Foundation Language Models

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-15T21:44:29.212990Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0dd3b1f7-89e4-4717-a477-52605470f60e · outbound

This paper cites Rethinking the learning paradigm for dynamic facial expression recognition.

Emotion Knowledge Enhancement for Vision Large Language Models: A Self-Verification Approach for High-Quality Emotion Instruction Data Generation Rethinking the learning paradigm for dynamic facial expression recognition

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:44:29.831395Z

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 35934a95-d9e1-42a0-a6dc-1c0ce49d7288 · outbound

This paper cites Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution.

Emotion Knowledge Enhancement for Vision Large Language Models: A Self-Verification Approach for High-Quality Emotion Instruction Data Generation Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-15T21:44:29.223723Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de36e934-6782-42fa-9aee-d879762dbda5 · outbound

This paper cites Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization.

Emotion Knowledge Enhancement for Vision Large Language Models: A Self-Verification Approach for High-Quality Emotion Instruction Data Generation Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-15T21:44:29.233811Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f76c93ae-0f6e-42bc-ae1f-c6ae17b41707 · outbound

This paper cites Emovit: Revolutionizing emotion insights with visual instruction tuning.

Emotion Knowledge Enhancement for Vision Large Language Models: A Self-Verification Approach for High-Quality Emotion Instruction Data Generation Emovit: Revolutionizing emotion insights with visual instruction tuning

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-15T21:44:29.240611Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad5c8d31-a12a-4c95-bd8f-62e135eaece9 · outbound

This paper cites Qwen2 Technical Report.

Emotion Knowledge Enhancement for Vision Large Language Models: A Self-Verification Approach for High-Quality Emotion Instruction Data Generation Qwen2 Technical Report

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-15T21:44:29.247106Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c69de7ab-bd21-4e78-969f-d0d6795b13a4 · outbound

This paper cites Robust emotion recognition in context debiasing.

Emotion Knowledge Enhancement for Vision Large Language Models: A Self-Verification Approach for High-Quality Emotion Instruction Data Generation Robust emotion recognition in context debiasing

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:44:29.793904Z

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 492de562-dca7-4574-bf19-7a55fa8adf0d · outbound

This paper cites MiniCPM-V: A GPT-4V Level MLLM on Your Phone.

Emotion Knowledge Enhancement for Vision Large Language Models: A Self-Verification Approach for High-Quality Emotion Instruction Data Generation MiniCPM-V: A GPT-4V Level MLLM on Your Phone

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-15T21:44:29.262550Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aebe6239-57eb-4344-ada0-bd843454f20a · outbound

This paper cites Sigmoid loss for language image pre-training.

Emotion Knowledge Enhancement for Vision Large Language Models: A Self-Verification Approach for High-Quality Emotion Instruction Data Generation Sigmoid loss for language image pre-training

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-15T21:44:29.276459Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c66b5d0a-dbb2-4932-9697-f7fb8ebd4415 · outbound

This paper cites A high-resolution spontaneous 3d dynamic facial expression database.

Emotion Knowledge Enhancement for Vision Large Language Models: A Self-Verification Approach for High-Quality Emotion Instruction Data Generation A high-resolution spontaneous 3d dynamic facial expression database

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:44:29.761442Z

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 45d9dd06-f5d7-46be-809d-79e895bd6a15 · outbound

This paper cites Bp4d-spontaneous: a high-resolution spontaneous 3d dynamic facial expression database.Image and Vision Computing, 32(10):692–706, 2014.

Emotion Knowledge Enhancement for Vision Large Language Models: A Self-Verification Approach for High-Quality Emotion Instruction Data Generation Bp4d-spontaneous: a high-resolution spontaneous 3d dynamic facial expression database.Image and Vision Computing, 32(10):692–706, 2014

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-15T21:44:29.290214Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d99c2338-975d-412d-81a8-97d9fad1dd0c · outbound

This paper cites Khfa: Knowledge-driven hierarchical feature alignment framework for subject- invariant facial action unit detection.IEEE Transactions on Instrumentation and Measurement, 2024.

Emotion Knowledge Enhancement for Vision Large Language Models: A Self-Verification Approach for High-Quality Emotion Instruction Data Generation Khfa: Knowledge-driven hierarchical feature alignment framework for subject- invariant facial action unit detection.IEEE Transactions on Instrumentation and Measurement, 2024

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T21:44:29.730776Z

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.

Coverage vector

Reference resolution

Outbound references

Pith citing papers