{"total":36,"rows":[{"id":"2206.08916","title":"Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks","created":"2022-06-17","cited_by_count":421,"area":null},{"id":"2210.03347","title":"Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding","created":"2022-10-07","cited_by_count":366,"area":null},{"id":"2209.13064","title":"EPIC-KITCHENS VISOR Benchmark: VIdeo Segmentations and Object Relations","created":"2022-09-26","cited_by_count":140,"area":null},{"id":"2309.01327","title":"Can I Trust Your Answer? Visually Grounded Video Question Answering","created":"2023-09-04","cited_by_count":135,"area":null},{"id":"2308.07123","title":"An Outlook into the Future of Egocentric Vision","created":"2023-08-14","cited_by_count":84,"area":null},{"id":"2412.20206","title":"Toward Visual Grounding: A Survey","created":"2024-12-28","cited_by_count":52,"area":null},{"id":"2311.00308","title":"From Image to Language: A Critical Analysis of Visual Question Answering (VQA) Approaches, Challenges, and Opportunities","created":"2023-11-01","cited_by_count":25,"area":null},{"id":"2403.05435","title":"OmniCount: Multi-label Object Counting with Semantic-Geometric Priors","created":"2024-03-08","cited_by_count":16,"area":null},{"id":"2308.11662","title":"VQA Therapy: Exploring Answer Differences by Visually Grounding Answers","created":"2023-08-21","cited_by_count":14,"area":null},{"id":"2207.11810","title":"VizWiz-FewShot: Locating Objects in Images Taken by People With Visual Impairments","created":"2022-07-24","cited_by_count":11,"area":null},{"id":"2309.16511","title":"Toloka Visual Question Answering Benchmark","created":"2023-09-28","cited_by_count":10,"area":null},{"id":"2411.00394","title":"Right this way: Can VLMs Guide Us to See More to Answer Questions?","created":"2024-11-01","cited_by_count":10,"area":null},{"id":"2306.05240","title":"Dealing with Semantic Underspecification in Multimodal NLP","created":"2023-06-08","cited_by_count":9,"area":null},{"id":"2304.14623","title":"Quality-agnostic Image Captioning to Safely Assist People with Vision Impairment","created":"2023-04-28","cited_by_count":8,"area":null},{"id":"2309.11593","title":"Sentence Attention Blocks for Answer Grounding","created":"2023-09-20","cited_by_count":8,"area":null},{"id":"2501.02201","title":"Acknowledging Focus Ambiguity in Visual Questions","created":"2025-01-04","cited_by_count":8,"area":null},{"id":"2301.05323","title":"Salient Object Detection for Images Taken by People With Vision Impairments","created":"2023-01-12","cited_by_count":7,"area":null},{"id":"2406.18253","title":"On the Role of Visual Grounding in VQA","created":"2024-06-26","cited_by_count":5,"area":null},{"id":"2407.18243","title":"BIV-Priv-Seg: Locating Private Content in Images Taken by People With Visual Impairments","created":"2024-07-25","cited_by_count":5,"area":null},{"id":"2409.14319","title":"Scene-Text Grounding for Text-Based Video Question Answering","created":"2024-09-22","cited_by_count":5,"area":null},{"id":"2303.05068","title":"Toward Unsupervised Realistic Visual Question Answering","created":"2023-03-09","cited_by_count":4,"area":null},{"id":"2309.03726","title":"Interpretable Visual Question Answering via Reasoning Supervision","created":"2023-09-07","cited_by_count":4,"area":null},{"id":"2601.08155","title":"Instance-Aligned Captions for Explainable Video Anomaly Detection","created":"2026-01-13","cited_by_count":4,"area":null},{"id":"2307.14142","title":"LOIS: Looking Out of Instance Semantics for Visual Question Answering","created":"2023-07-26","cited_by_count":3,"area":null},{"id":"2305.03971","title":"Adaptive loose optimization for robust question answering","created":"2023-05-06","cited_by_count":2,"area":null},{"id":"2309.01955","title":"A Survey on Interpretable Cross-modal Reasoning","created":"2023-09-05","cited_by_count":2,"area":null},{"id":"2402.03896","title":"Multimodal Rationales for Explainable Visual Question Answering","created":"2024-02-06","cited_by_count":2,"area":null},{"id":"2410.18109","title":"NaVIP: An Image-Centric Indoor Navigation Solution for Visually Impaired People","created":"2024-10-08","cited_by_count":2,"area":null},{"id":"2207.05703","title":"Tell Me the Evidence? Dual Visual-Linguistic Interaction for Answer Grounding","created":"2022-06-21","cited_by_count":1,"area":null},{"id":"2410.22648","title":"SimpsonsVQA: Enhancing Inquiry-Based Learning with a Tailored Dataset","created":"2024-10-30","cited_by_count":1,"area":null},{"id":"2303.02601","title":"Knowledge-Based Counterfactual Queries for Visual Question Answering","created":"2023-03-05","cited_by_count":0,"area":null},{"id":"2509.18177","title":"A Framework for Generating Artificial Datasets to Validate Absolute and Relative Position Concepts","created":"2025-09-17","cited_by_count":0,"area":null},{"id":"2512.10102","title":"Hierarchical Instance Tracking to Balance Privacy Preservation with Accessible Information","created":"2025-12-10","cited_by_count":0,"area":null},{"id":"2606.09181","title":"Counterfactual Reasoning for Fine-Grained Evidence Disentanglement in VideoQA","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2607.23921","title":"DDVT: Dynamic Dual-level Vision Transformer Fusion Network for Answer Grounding in Visual Question Answering","created":"2026-07-27","cited_by_count":0,"area":null},{"id":"2609.20574","title":"DocAttriBench: Benchmarking Answer Grounding in Document Visual Question Answering","created":"2026-09-17","cited_by_count":0,"area":null}],"next_cursor":null}