The DOI matches its Crossref record; 44 of the 45 references it cites were found in a registry or an index.
VizWiz Grand Challenge: Answering Visual Questions from Blind People
Open accessAbstract
The study of algorithms to automatically answer visual questions currently is motivated by visual question answering (VQA) datasets constructed in artificial VQA settings. We propose VizWiz, the first goal-oriented VQA dataset arising from a natural VQA setting. VizWiz consists of over 31,000 visual questions originating from blind people who each took a picture using a mobile phone and recorded a spoken question about it, together with 10 crowdsourced answers per visual question. VizWiz differs from the many existing VQA datasets because (1) images are captured by blind photographers and so are often poor quality, (2) questions are spoken and so are more conversational, and (3) often visual questions cannot be answered. Evaluation of modern algorithms for answering visual questions and deciding if a visual question is answerable reveals that VizWiz is a challenging dataset. We introduce this dataset to encourage a larger community to develop more generalized algorithms that can assist blind people.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Prior work reported over 40% disagreement between crowdworkers and in-house experts on whether a photo contained privacy or quality issues [36]”
From Disability-First AI Dataset Annotation: Co-designing Stuttered Speech Annotation Guidelines with People Who Stutter (2026) · cites this paper as [36]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Although academic scholars and industry corporations have emphasized the pressing need for more disability-centered datasets [20, 38, 55, 79, 97, 111, 124]”
From "It's trained by non-disabled people": Evaluating How Image Quality Affects Product Captioning with Vision-Language Models (2026) · cites this paper as [55]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“While prior efforts of disabilityfirst datasets often focus on the data collection process [36, 47, 63, 68, 88, 98], our study represents an important step in centering disabled people and their expertise throughout the AI development pipeline.”
From Disability-First AI Dataset Annotation: Co-designing Stuttered Speech Annotation Guidelines with People Who Stutter (2026) · cites this paper as [36]
The cited source says what the claim attributes to it.
In the citing paper
“From analyzing VizWiz images, Gurari et al. [55] found that blind users often struggle to take high-quality photographs, and many visual questions go unanswered because images fail to capture the relevant objects [55].”
From "It's trained by non-disabled people": Evaluating How Image Quality Affects Product Captioning with Vision-Language Models (2026) · cites this paper as [55]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333 · cited 2×
“Following prior work [14], we first computed the average image from all images in VizWiz.”
BackgroundMethodMicrosoft COCO: Common Objects in Context
Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., & Zitnick, C. L. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10602-1_48 · Cited by 45,460 · cited 4×
“0: Real [7] MSCOCO [25] Crowd workers (AMT) Typed Visual Madlibs [43] MSCOCO [25] Automatically generated (templates) ——– FM-IQA [16] MSCOCO [25] Crowd workers (Baidu) Typed KB-VQA [40] MSCOCO [25] In-house participants Typed COCO-QA [32] MSCOCO [25] Automatically generated (captions) ——– VQA v2.”
BackgroundMethodInfluentialImageNet Large Scale Visual Recognition Challenge
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0816-y · Cited by 39,380
BLEU: a method for automatic evaluation of machine translation
Papineni, K., Roukos, S., Ward, T., & Zhu, W.-J. (2001) · Proceedings of the 40th Annual Meeting on Association for Computational Linguistics - ACL '02 · doi:10.3115/1073083.1073135 · Cited by 21,344 · cited 2×
“We employ five metrics commonly used for evaluating VQA and image description algorithms: Accuracy [7], CIDEr [38], BLEU4 [29], and ME-”
MethodIndoor segmentation and support inference from rgbd images
Silberman, N., Hoiem, D., Kohli, P., & Fergus, R. (2012) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-33715-4_54 · Cited by 5,760 · cited 1×
“DAQUAR [28] NYU Depth V2 [34] Automatically generated (templates) ——– VQA v1.”
MethodVisual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations
Krishna, R., Zhu, Y., Groth, O., Johnson, J., Hata, K., Kravitz, J., Chen, S., Kalantidis, Y., Li, L.-J., Shamma, D. A., et al. (2017) · International Journal of Computer Vision · doi:10.1007/s11263-016-0981-7 · Cited by 5,107
Deep visual-semantic alignments for generating image descriptions
Karpathy, A., & Fei-Fei, L. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298932 · Cited by 4,902
CIDEr: Consensus-based image description evaluation
Vedantam, R., Zitnick, C. L., & Parikh, D. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7299087 · Cited by 4,845 · cited 2×
“We employ five metrics commonly used for evaluating VQA and image description algorithms: Accuracy [7], CIDEr [38], BLEU4 [29], and ME-”
MethodVQA: Visual Question Answering
Antol, S., Agrawal, A., Lu, J., Mitchell, M., Batra, D., Zitnick, C. L., & Parikh, D. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.279 · Cited by 4,487
Bleu: a method for automatic evaluation of machine translation
Papineni, K. (2024) · doi:10.57702/ljteqmrb · Cited by 3,668
Flagged first, then by citations
1 of the 45 references couldn’t be matched to a known paper.
Research works printed but not linked: 3
- mahendru, 2017, The promise of premise Harnessing question premises in visual question answering
- anderson, 2017, Bottom-up and top-down attention for image captioning and visual question answering
- 0, Be My Eyes
Cited by
Sorted by citations
Items 501–600 of 629
A Comprehensive Review and Open Challenges on Visual Question Answering Models
Shaik, F. A., Koshti, D., Gupta, A., Kalla, M., & Sharma, A. (2023) · Aibi revista de investigación administración e ingeniería · doi:10.15649/2346030x.3370
Visual Question Answering – VizWiz Challenge
Ranković, T., Janković, E., & Сливка, Ј. (2024) · Lecture notes in networks and systems · doi:10.1007/978-3-031-50755-7_32
SkillCLIP: Skill Aware Modality Fusion Visual Question Answering (Student Abstract)
Naik, A., Butala, Y., Vaikunthan, N., & Kapoor, R. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i21.30486
“However, progress on the accessibility-focused VizWiz VQA dataset (Gurari et al. 2018) has proven particularly difficult (Cao et al. 2022).”
BackgroundTian, Y., Liu, Z., Zou, Q., & Chen, G. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-2390-4_9 · Cited by 1
Visual Question Answering based Educational Tool for Medical Students using Cross-ViT
Somvanshi, M. S. (2024) · International Journal for Research in Applied Science and Engineering Technology · doi:10.22214/ijraset.2024.62677
S$$^3$$: A Simple Strong Sample-Effective Multimodal Dialog System
Rykov, E., Malkershin, E., & Panchenko, A. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-70239-6_17
Customizable and Programmable Deep Learning
Pal, R., Kar, S., & Sekh, A. A. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-78107-0_7
Analyzing Difficulties of Visual Questions Using Entropy Values of Answer Predictions
Yadav, M. G., Nennuri, R., Deepthi, N. L., Harshitha, K. S., & Vinay, A. N. (2024) · Lecture notes in networks and systems · doi:10.1007/978-981-97-8666-4_40
Deep learning-based visual question answering: Survey
Mohammed, N. F., & Ali, I. H. (2025) · AIP conference proceedings · doi:10.1063/5.0258482
MixSense : Mixture of Vision Sense
Lin, J., Wang, Z., Qiu, Q., Chen, J., Ge, Z., Jin, W., Yan, Y., & Yu, L. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10889214
“To verify whether MixSense maintains its original vanilla capabilities while improving performance on specific tasks, we evaluate MixSense on several VQA benchmarks: VQAv2 [26], GQA [27], VizWiz [28], SQA-IMG [29], and TextVQA [30], and compared it with the baseline model LLaVA-1.”
Graph Convolutional Networks with Fine-Tuned Word Representations for Visual Question Answering
Owusu, J. W., Zakari, R. Y., Qin, K., & He, T. (2024) · IEEE Smart World Congress (SWC) · doi:10.1109/swc62898.2024.00214
“Representative datasets for this domain include VizWiz [18].”
Ab-Vqa: An Abductive Reasoning Framework for Mitigating Bias in Visual Question AnsweringPreprint
Lu, Q., & Chen, S. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5234373
On replacing humans with human simulators in human-in-the-loop systems built to interact with humans
Huang, S.-H., & Huang, T.-H. (2025) · Elsevier eBooks · doi:10.1016/b978-0-44-340553-2.00017-4
Refining visual token sequence for efficient image captioning
Xian, T., Zhou, Z., Zhou, W., & Zhang, Z. (2025) · Neural Networks · doi:10.1016/j.neunet.2025.107759
A Multi-Modal Attentive Framework That Can Interpret Text (MMAT)
Kumari, V., Gupta, S., Sharma, Y., & Goel, L. (2025) · IEEE Access · doi:10.1109/access.2025.3586900 · Cited by 1
“The present VQA models fail to reason on text present in the images, which is crucial for assisting the visually impaired, according to the VizWiz study [7].”
Zheng, S., & Zhao, L. (2025) · International Conference on Neural Networks, Information and Communication Engineering (NNICE) · doi:10.1109/nnice64954.2025.11064513
“Currently, Medical VQA has found extensive applications in radiology field [13], pathology field [14] and the field of assistive technology for individuals with visual impairments [15].”
Self-Improved Visual Preference Alignment by Iteratively Generating Holistic WinnerPreprint
Feng, Z., Chen, K., Zhang, J., Yang, J., & Song, M. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5352865
Enhancing Visual Question Answering Via Clustered In-Context Sequence Configuration
He, Z., Pan, Y., Li, H., Ma, F., Peng, Y., Wu, S., & Sun, X. (2025) · Proceedings - International Conference on Image Processing · doi:10.1109/icip55913.2025.11084650
Visual Prompting Through Image Mines
Shah, K., Snehan, J., Bhutani, G., Singh, K. V., & Singh, S. (2025) · Proceedings - International Conference on Image Processing · doi:10.1109/icip55913.2025.11084631
Enhancing Smart Vision Glasses with Multimodal Language Models: A Voice Guided Approach
Lambor, S. M., Lale, Y., Kota, A., Kulkarni, P., & Patil, M. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-5607-3_35
The System of Visual Question Answering: Based on The Architectural Perspective
Wan, K. (2025) · ITM Web of Conferences · doi:10.1051/itmconf/20257804005
ICT-QA: Question Answering Over Multi-Modal Contexts Including Image, Chart, and Text Modalities
Jang, Y., Kong, H., Kim, G., Lee, Y., Choi, J., & Bae, K. (2025) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw67362.2025.00019
QID: Efficient Query-Informed ViTs in Data-Scarce Regimes for OCR-Free Visual Document Understanding
Le, B. M., Xu, S., Fu, J., Huang, Z., Li, M., Guo, Y., Li, H., Ramasinghe, S., & Wang, B. K. (2025) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw67362.2025.00014
AB-VQA: An Abductive Reasoning Framework for Mitigating Bias in Visual Question AnsweringPreprint
Lu, Q., & Chen, S. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5492131
Leveraging Multimodal Vision-Language Models for the Visually Impaired
Desai, D., Mehra, A., & G, A. M. (2025) · International Conference on Intelligent Technologies (CONIT) · doi:10.1109/conit65521.2025.11167288
“This dataset has inspired research on scene recognition and visual question answering specifically tailored to address accessibility needs [1].”
ML-Based Systems for Identifying Hate Memes on Social Media
Tamilkodi, R., Pravallika, S., Kumar, P., Bhargav, M., Anvesh, G. L. V., & Premraj, S. (2025) · Algorithms for intelligent systems · doi:10.1007/978-981-96-7059-8_8
Jiang, S., Zhang, Y., Zhou, C., Jin, Y., & Liu, Z. (2025) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-032-00274-7_17
Crop-and-Prompt: Multi-Grained Prompting for Fine-Grained Visual-Language Understanding
Zang, Z., & Wang, H. (2025) · International Conference on Artificial Intelligence, Big Data and Algorithms (CAIBDA) · doi:10.1109/caibda65784.2025.11182630
Zeidieh, A., & Seo, J. (2025) · International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS) · doi:10.1145/3663547.3749833
MRBench: A Multi-Image Reasoning Benchmark with Adaptive Knowledge Retrieval
Huang, W., Chen, X., Zhang, Q., Wan, T., Liu, Z., & Zhang, L. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3755442
“Multimodal large language models (MLLMs) exhibit strong capabilities in both text comprehension and image recognition, achieving impressive results on a range of image-text tasks [19, 23, 26, 33, 35].”
Jiang, P., Li, H., Zhao, L., Chao, F., Yan, K., Ding, S., & Ji, R. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3755792 · Cited by 4
“Meanwhile, efficiency analysis is performed to demonstrate the acceleration effect of our method.”
Towards High Robust Vision-Language Large Models: Benchmark and Method
Zhao, M., Liu, Y., He, W., Yu, B., Mi, Y., & Zhou, S. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3758234
“To this end, we consider a total of 13 benchmarks, including VQAv2 [13], GQA [21], VisWiz [16], SciQA [37], TextVQA [41], POPE [30], MME [11], MM-Bench [36], SEED-Bench [24], MM-Vet [50], AMBER [43], Prompt-augmented CIEM (CIEM-Aug), and our benchmark RBench.”
InfluentialHow Vision-Language Tasks Benefit From Large Pre-Trained Models: A Survey
Qi, Y., Hong-xi, L., Song, Y., Wu, X., & Luo, J. (2025) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2025.3632653 · Cited by 5
Self-citationNoh, S. H., & Cho, J. W. (2025) · Mathematics · doi:10.3390/math13223656
Oo, K. N. (2025) · International Conference on Advanced Information Technologies (ICAIT) · doi:10.1109/icait68809.2025.11236732
“• VizWiz Captions subset [15] – a reduced 1,000-image subset drawn from VizWiz, containing images from visually impaired users, included to evaluate robustness under noisy, real-world inputs.”
Bi-directional Semantic Alignment for Large Vision Language Model Training via Echo-Former
Wang, Y., Liu, Q., Li, Z., Wang, S., Guo, S., & Wei, Z. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-3346-6_6
A Survey on Visual Token Compression for Efficient Vision-Language Models
Cao, W., Feng, Z., Sun, F., Liu, D., Xie, Y., & Li, Z. (2025) · International Conference on Advanced Algorithms and Neural Networks (AANN) · doi:10.1109/aann66429.2025.11257670
“The tasks included are VQAv2 [27] , GQA [28] , VizWiz [29] , SQA [30] , TextVQA [31] , POPE [32] , MMVet [33] , MMBench [34] , MME [35] , and SEED [36] .”
Characterizing Cross-Contamination on Multitask Multimodal Large Language Models
Ibañez-Lissen, L., González‐Manzano, L., Fuentes, J. M. D., & García-Alfaro, J. (2025) · Information Systems Frontiers · doi:10.1007/s10796-025-10656-5
NeSyVQA: Neurosymbolic Visual Question Answering With Knowledge-Enriched Scene Graphs
Khan, M. J., Breslin, J. G., & Curry, E. (2025) · IEEE Access · doi:10.1109/access.2025.3645220 · Cited by 1
VisionAidQA: Advancing Visual Question Answering for the Visually Impaired
Pal, R., Kar, S., Prasad, D. K., & Sekh, A. A. (2026) · ACM Computing Surveys · doi:10.1145/3788861
“2 State-of-the-art VQA VQA requires a deep understanding of visual and textual modalities.”
Visual Question Answering for Intelligent Communication Systems: A Systematic Review
Güllü, M., & Barışçı, N. (2026) · IEEE Access · doi:10.1109/access.2026.3654676 · Cited by 3
“These capabilities offer a wide range of applications, from real-time support systems for visually impaired individuals [116] to improving e-commerce experiences [117] and automated content generation in media and marketing [118].”
Manifold-Guided Geometric Enhancement for Reliable Multimodal Interaction in Consumer Electronics
Xu, X., Pan, Y., Zhang, X., Chen, X., & Tsang, K.-F. (2026) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2026.3655466
“3) Real-World and Domain-Specific Generalization: We additionally evaluate on ScienceQA [40] and VizWiz [41].”
BLaVe-CoT: Consistency-Aware Visual Question Answering for Blind and Low Vision Users
Cheng, W., & Ruan, Z. (2025) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc58881.2025.11343278
“To better capture visual problems in real-world settings, the VizWiz dataset [6] was introduced as the first VQA dataset that reflects the genuine needs of blind users, with questions based on their visual perceptions.”
Multi-Perspective Visual Contrastive Decoding for Reliable Assistance
Pan, B., Shi, H., & Gao, X. (2026) · ACM Transactions on Internet of Things · doi:10.1145/3785360
“— VizWiz Caption [16]: A groundbreaking dataset specifically designed to address real-world visual assistance needs of blind individuals.”
Patching the visual ability of large multimodal models by collaborating with small models
Liang, H., Zhang, X., Kan, M., Shan, S., & Xilin, C. (2026) · Frontiers of Computer Science · doi:10.1007/s11704-025-41126-5
CommuteQA: Visual Question Answering for Bus Transport
Shaikh, A. D., Garg, P., Ramesh, M., Kashyap, R., Mutharaju, R., & Shah, R. R. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-15134-6_2
Upadhyay, S., & Tripathy, S. S. (2025) · IEEE Applied Signal Processing Conference (ASPCON) · doi:10.1109/aspcon66877.2025.11389244
“Approximately 28% of VizWiz data are deemed answerable by crowd workers [12].”
Evaluating Variance in Visual Question Answering Benchmarks
Nikitha, S. R. (2025) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw69036.2025.00442 · Cited by 2
Quadtree Partitioning-based Visual Token Pruning for MLLMs Considering Information Density
Wei, Y., Liu, J., Zhao, S., Chen, Z., Zeng, W., & Jin, X. Y. (2025) · IEEE International Conference on Visual Communications and Image Processing (VCIP) · doi:10.1109/vcip67698.2025.11396917
“To validate the effectiveness of QPID, we conduct evaluations on 6 widely adopted multimodal benchmarks: Sci-enceQA (SciQA) [35], TextVQA (VQA T ) [36], POPE [37], VizWiz [38], MME [39], Seed-Bench-image [40].”
VisionAlt-Score: Large-Scale Automated Quality Grading of Web alt Text Attributes
Al-Khalifa, H. S. (2025) · International Conference on ICT & Accessibility (ICTA) · doi:10.1109/icta-atsn68371.2025.11398192
Sota, S., Moraje, S., Deshpande, S. R., Golatkar, S., Chourey, L., Sawant, V., & Tawde, P. (2025) · IEEE International Conference for Women in Computing (InCoWoCo) · doi:10.1109/incowoco68239.2025.11406218
“This simplification can result in the loss of crucial scientific detail [14], [15], [17], [21].”
Zhan, Q., Chen, W., & Zhao, S. (2025) · International Conference on Virtual Reality and Visualization · doi:10.1109/icvrv67992.2025.00022
“…multi-modal benchmarks spanning 4 critical task domains: image captioning(Flickr30K [22]), general visual question answering (GQA [23], VizWiz [24]), text-based visual question answering (ScienceQA [25], TextVQA [12], ChartQA [26], DocVQA [13]), and multi-modal reasoning (POPE [27], MME [28],…”
SHC: Deeply Activating Human-Like Cognitive Ability for Visual Question Answering
Wang, F., Wang, Z., An, G., Lang, C., & Wu, D. O. (2026) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2026.3673273
“We selected several representative benchmarks: VQA-v2, GQA, ScienceQA [94], Text-VQA [95] and VizWiz [89], as well as multiple multimodal evaluation benchmarks, including MMB [96], MME [97], MM-Vet [98], MMMU [99] and POPE [100].”
AI Vision Assistance for Visually Impaired Individuals
Samuel Raj, E., Thamizharasan, M., & Saraswathi., T. (2026) · International Conference on Communication, Computing and Electronics Systems (ICCCES) · doi:10.1109/iccces62661.2026.11436220
“[5] VQA dataset collected from blind users (VizWiz)”
Photo Captioning for Assisting Blind and Visually Impaired People Using Gated Attention
Pavithra, K., Praveena, K., Padmavathy, S., Ishwarya, A., & Velmurugan, M. (2026) · International Conference on Computing, Communication, Control and Cyber-Physical Systems (I5CPS) · doi:10.1109/i5cps67958.2026.11452630
“Gurari et al. presented VizWiz, a visual question answering task and dataset for blind or low vision users, highlighting special requirements and system design challenges in developing assistive vision technology [9].”
Multi-modal representation learning towards visual reasoning
Ben-younes, H. (2019) · theses.fr (ABES) · doi:10.70675/d69497cfzf0c3z418ezaa6azbfef68416b7b
Visual and Textual Common Semantic Spaces for the Analysis of Multimodal Content
Beltrán, L. V. B. (2021) · theses.fr (ABES) · doi:10.70675/a19cbe0dz6c94z4ff6zb70ez024fd8546d17
Lightweight Visual Question Answering system for assistive vision on edge device
Upadhyay, S., Panda, S., & Tripathy, S. S. (2026) · Image and Vision Computing · doi:10.1016/j.imavis.2026.105962
Deep Multimodal Learning for Vision and Language Processing
Cadène, R. (2020) · theses.fr (ABES) · doi:10.70675/674b1e7aza957z4fc5za03czde9aab142a84 · Cited by 1
Répondre aux questions visuelles à propos d'entités nommées
Lerner, P. J. (2023) · theses.fr (ABES) · doi:10.70675/78c96766zfc95z4da8zb67aze67555da6c75
Foundation Vision-Language models
Laurençon, H. (2025) · theses.fr (ABES) · doi:10.70675/ec0311a0zb6a4z4249zb9fbz01bf51a02c7c
Integrating Language and Vision Models for Real-Time Assistance for the Visually Impaired
Angadi, A. V., Koppal, A. N., Atrey, A. S., Surya, C. R. S., & Mamatha, H. R. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-14757-8_27
India, G., Grayson, M., Morrison, C. P., Massiceti, D., Robinson, S., Pearson, J. S., & Jones, M. (2026) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3791099
“In particular, systems trained on data collected by sighted individuals frequently under-perform for blind or have low vision users, whose image data often includes challenges like low lighting, motion blur, and partially framed objects [16, 20, 32, 33, 50].”
InfluentialInformation Router for Mitigating Modality Dominance in Vision-Language Models
Kim, S., Prabhushankar, M., & AlRegib, G. (2026) · Proceedings - International Conference on Image Processing · doi:10.1109/icip61757.2026.11630349
Li, Y., Wu, T., Gao, J., Zhu, W., & Ouyang, W. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11462821
VisualPrism: Disperse-and-Focus Token Compression
He, R. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11464486
Zhang, J., Chen, J. Y., Guo, X., Tong, X., & Huang, D. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11460568
ZIP Your Data: Length-Adaptive Visual Token Optimization for Efficient Multi-Modal Training
Sun, N., Wu, F., Zhang, Y., Chen, S., Tao, X., & Yang, F. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11461954
ECM: Enhancing Compressibility of Quantized Vision Encoder and LLM for Large Vision-Language Models
Wang, W., Mao, Y., Tang, D., Guan, N., & Xue, C. J. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11460785
Bai, Y., Bai, S., 冉健莉, Su, T., & Bai, Z. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11463161
Hu, R., Guan, R., Di, Y., Bao, J., & Liu, Y. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11462754
“Experiments are conducted on 10,000 images from the tellingQA sub-set of Visual7W [6] and VizWiz-VQA-G [24] (hereafter “VizWiz”), where VizWiz segmentation masks are converted to bounding boxes for consistency.”
Preserving Knowledge in Large Language Models Via Model-Agnostic Intrinsic Generative Replay
Zhang, Z., Sun, Y., Zhao, T., Sha, L., Xu, R., Lee, K., & Yin, J. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11464789
Zhang, Y., Li, H., Liu, J., & Yue, X. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.00132
“The MLLM evaluation involves 6 VQA tasks (GQA [39], VQAv2 [29], OKVQA [69], TextVQA (TVQA) [83], ScienceQA (SQA) [67] and Vizwiz [31]), 2 image captioning tasks (Nocaps [1] and Flickr30K [75]), and 4 multimodal benchmarks (MME [22], MM Bench (MMB) [64], MMVet [105] and SEED [46]).”
Learning Beyond Still Frames: Scaling Vision-Language Models with Video
Zhang, Y., Jing, H., Liu, J., & Yue, X. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.02082
“The MLLM evaluation involves 6 VQA tasks (GQA [31], VQAv2 [24], OKVQA [52], TextVQA (TVQA) [62], ScienceQA (SQA) [48] and Vizwiz [25]), 2 image captioning tasks (Nocaps [1] and Flickr30K [58]), and 4 multimodal benchmarks (MME [21], MM Bench (MMB) [47], MMVet [77] and SEED [37]).”
OURO: A Self-Bootstrapped Framework for Enhancing Multimodal Scene Understanding
Xu, T. L., Chen, G. L., Li, Y., Xi, Y., Mu, Z., Wang, R., Zhang, T., Gao, H., & Chen, F. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01695
“For General VQA, we make use of VQAv2 [20], OKVQA [44], GQA [26], ScienceQA [42], and VizWiz [24], collectively adding up to 306k samples.”
Advancing Multimodal LLMs by Large-Scale 3D Visual Instruction Dataset Generation
Liu, H., Zeng, X., Song, Y., Chen, A. Y. C., Xia, L., Verma, S., Dayal, S., Sun, M., Kuo, C.-H., & Aliaga, D. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00570
“…dozens of datasets, focusing on different areas, are combined to enable the comprehensive abilities of MLLMs. Datasets include image captioning [38, 72, 73], visual reasoning [28, 39], general VQA data [19, 41, 67] on knowledge grounding [44, 46], image understanding [15], and OCR [48, 56].”
Bridging the Domain Gap in Small Multimodal Models: A Dual-level Alignment Perspective
Dayal, A., Divya, P., Tiwari, N., Cenkeramaddi, L. R., Mohan, C. K., & Kumar, A. S. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00797
“The Domain pairs ‘(S, H)’ and ‘(I, S)’ show the highest MMD values across both modalities, indicating stronger distribution shifts.”
Ilham, M. H. M., Dhar, S., Joy, M. J. H., & Azhar, T. (2025) · International Conference on Computer and Information Technology (ICCIT) · doi:10.1109/iccit68739.2025.11490380
“In this light, the VizWiz-VQA dataset was proposed in [4], featuring real-world images and questions sourced from blind users of the VizWiz mobile application [2].”
Aljedaani, W., Alsulaymi, R., Alqahtani, G., & Feng, Y. (2026) · International Web for All Conference (W4A) · doi:10.1145/3800424.3800454
“• VizWiz: We specifically included this dataset because it features images taken by BLV users, often containing real-world flaws like blur or bad framing [38].”
Chen, Z., Wang, W., Zhu, J., Wang, X., Liu, Y., Liu, Z. T., Luo, G., Sun, P., Su, W., Tian, H., et al. (2026) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2026.3702168
Benchmarking Local Vision-Language Models on an Edge Device for the Visually Impaired
Sarwar, F., Raja, B. A., Ibrahim, M., Zeb, A., Khan, U. S., & Asad, U. (2026) · International Conference on Robotics and Automation in Industry (ICRAI) · doi:10.1109/icrai70912.2026.11551964
“…images and questions created by blind or visually impaired (hereafter abbreviated as VI) individuals for evaluating frameworks of assistive devices for their use, subsequently proposing the first Visual Question Answering (VQA) dataset containing images and questions from VI individuals [12].”
InfluentialSHARP: Semantic Head-Aware Representation Pruning for Efficient MLLMs
Ma, H. F., Guo, M., Xiao, L., Zheng, Q., & Huang, Q. (2026) · International Conference on Multimedia Retrieval · doi:10.1145/3805622.3810733
“We evaluate our method in seven prominent multimodal benchmarks, including MME[9], POPE[16], SQA[20], VizWiz[12], GQA[13], MMBench[19] and TextVQA[22].”
Efficient Token Compression for the Understanding and Generation Unified MLLMs
Lin, J., Liu, J., Zhao, S., & Jin, X. (2026) · IEEE International Symposium on Circuits and Systems proceedings · doi:10.1109/iscas66217.2026.11562456
“We evaluate our models on ten widely-used vision–language benchmarks: AI2D [21], ChartQA [22], DocVQA [23], In-foVQA [24], MMBench-EN [25], OK-VQA [26], TextVQA [27], VizWiz-VQA [28], and VQAv2 [29].”
Spectral Evolution-Guided Token Pruning in Multimodal Large Language Models
Chen, B., Cai, Y., Luo, Y., Zhang, Y., Yin, J., & Chen, Z. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37517-9_13
ViKSeR: Visual Knowledge-Driven Self-Reinforcing Reasoning Framework
Wang, C., Zhang, C., Tian, Y., Zhou, Y., & Peng, Y. (2026) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2026.3707187
“Datasets: To evaluate the reasoning abilities of V I KS E R, we utilize widely-used datasets for visual reasoning tasks, including VQAv2 [44], A-OKVQA [45], VizWiz [46], e-SNLI-VE [36], COLA [5], and CREPE [47].”
Loughrey, D. G., Brosens, C., Moiselle, R., Shterionov, D., Vandeghinste, V., Way, A., & Leeson, L. M. (2026) · AI and Ethics · doi:10.1007/s43681-026-01230-z · Cited by 1
“Such a framework should not merely conform to existing regulations but should actively guide the development of AI [84].”
Combating Textual Noise and Redundancy: Entropy-Aware Dense Visual Token Pruning
Wang, X., Yang, X., & Shen, W. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37026-6_31
Find what you missed: Causal recovery for visual tokens in vision-language models
Qian, T., Wang, Q., Gao, S., & Yu, H. (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2026.116589
Localized Benchmark Evaluation of Vision-Language Models for Visually Impaired Assistance v1.0
Hussain, S., Tasmia, Faiza, P. A., Sami, S., & Khan, M. A. (2026) · International Conference on Computing, Mathematics and Engineering Technologies (iCoMET) · doi:10.1109/icomet69771.2026.11591816
“Nevertheless, even the most advanced systems show limitations in spatial grounding, localization accuracy, and in safety-critical perception, which remain crucial for visually impaired users who rely on precise and actionable descriptions [12].”
VisSemRender: Scaling Multi-Modal Contexts via Visual Token Compression and Semantic Color Encoding
Fang, P., Huang, W., Hu, Z., Wu, Y., Yin, Y., Zhan, N., Ren, J., He, Z., & Chen, R. (2026) · Communications in computer and information science · doi:10.1007/978-981-92-3560-5_32
Semantic-Guided Visual Byte-Pair Encoding for Unified Autoregressive Multimodal Modeling
Liu, K., Dong, W., Gao, L., & Mao, Q. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-3429-5_11
Götzelmann, T., Sommer, S., & Karg, P. (2026) · Electronics · doi:10.3390/electronics15143223
“The VizWiz project [48] collected a large number of visual questions along with their answers.”
Look Less, Think Faster: Joint Token-Compute Adaptation for Multimodal LLMs
Wang, P., Wang, Z., Lee, J., Xu, Z., Xu, R., Bagchi, S., Li, Y., & Chaterji, S. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37359-5_12 · Cited by 1
SiGMA: Sign-Guided Merging and Adaptation for Multimodal Continual Instruction Tuning
Park, K., & Kim, G. D. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37624-4_3
REVERIE+: Generalized Reflective Instruction Tuning for Hallucination Mitigation in Advanced VLMs
Bi, M., Zhang, J., Wang, X., Jiang, X., Lu, Y., Wang, P., & Zheng, F. (2026) · International Journal of Computer Vision · doi:10.1007/s11263-026-02945-6
“…2023), Geometry3K (Lu et al., 2021), IconQA (Lu et al., 2021), Raven (Zhang et al., 2019)); (iii) General VQA (Visual7W (Zhu et al., 2016), VizWiz (Gurari et al., 2018), VSR (Liu et al., 2023a)); (iv) Document/Chart/Screen (DVQA (Kafle et al., 2018), RoBUT-WTQ (Zhao et al.,…”
AQuant: Repurposing CODEC for VLM Acceleration via Adaptive Quantization
Song, Z., Qi, C., Weng, J., Liang, X., & Guan, H. (2026) · Proceedings - International Symposium on Computer Architecture/Proceedings · doi:10.1109/isca66397.2026.00106
“Note that the AQuant algorithm does not require retraining, making our approach highly deployable without the need for extensive reconfiguration.”
TRTF: A Two-Stage Robust Training Framework for Visual Question Answering
Yu, L., & Xu, J. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-31438-3_43
TruthLens: Object Hallucination Detection via Self-evaluating Truthfulness Scores in LVLMs
Wu, Y., Lai, R., Lu, X., Chen, Q., Zhou, Z., Zhuang, J., Yu, W., & Wang, R. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37490-5_30
Sheelavant, S., Narasimhan, A., & Hegde, A. G. (2026) · Springer eBooks · doi:10.1007/978-3-032-26901-0_10
ID-Pruner: Disentangling Importance and Diversity for Training-Free Visual Token Pruning
Ji, J., Li, G., & Afghah, F. (2026) · Proceedings - International Conference on Image Processing · doi:10.1109/icip61757.2026.11630377
Metadata
- Authors
- Gurari, D., Li, Q., Stangl, A. J., Guo, A., Lin, C., Grauman, K., Luo, J., & Bigham, J. P.
- Affiliations
- The University of Texas at Austin (US)
- University of Science and Technology of China (CN)
- University of Colorado Boulder (US)
- Carnegie Mellon University (US)
- University of Rochester (US)
- Venue
- 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
- Publisher
- IEEE
- Published
- 2018-06
- Pages
- 3608-3617
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W2788643321
- Cited by
- 621
- References
- 45
- Citations by year
- 2026: 92 · 2025: 133 · 2024: 108 · 2023: 65 · 2022: 56 · 2021: 66 · 2020: 55 · 2019: 29 · 2018: 17
- FWCI
- 12.58
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Science Foundation (1704309, 1514118, 1755593)
- Microsoft Research
- Baidu
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image Retrieval and Classification Techniques
- Keywords
- visual question answering, blind people, assistive technology, low-quality images, answerability
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
