{"total":29,"rows":[{"id":"2105.08276","title":"NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions","created":"2021-05-18","cited_by_count":744,"area":null},{"id":"2308.09126","title":"EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding","created":"2023-08-17","cited_by_count":680,"area":null},{"id":"2109.06835","title":"The Perils of Using Mechanical Turk to Evaluate Open-Ended Text Generation","created":"2021-09-14","cited_by_count":97,"area":null},{"id":"2203.01225","title":"Video Question Answering: Datasets, Algorithms and Challenges","created":"2022-03-02","cited_by_count":84,"area":null},{"id":"2209.03299","title":"Multimodal learning with graphs","created":"2022-09-07","cited_by_count":54,"area":null},{"id":"2112.05230","title":"Injecting Semantic Concepts into End-to-End Image Captioning","created":"2021-12-09","cited_by_count":41,"area":null},{"id":"2202.09195","title":"A Review on Methods and Applications in Multimodal Deep Learning","created":"2022-02-18","cited_by_count":29,"area":null},{"id":"2303.14655","title":"GOAL: A Challenging Knowledge-grounded Video Captioning Benchmark for Real-time Soccer Commentary Generation","created":"2023-03-26","cited_by_count":28,"area":null},{"id":"2105.11087","title":"Recent Advances and Trends in Multimodal Deep Learning: A Review","created":"2021-05-24","cited_by_count":26,"area":null},{"id":"2306.00424","title":"End-to-end Knowledge Retrieval with Multi-modal Queries","created":"2023-06-01","cited_by_count":23,"area":null},{"id":"2303.15616","title":"Fine-grained Audible Video Description","created":"2023-03-27","cited_by_count":18,"area":null},{"id":"2104.05981","title":"CLEVR_HYP: A Challenge Dataset and Baselines for Visual Question Answering with Hypothetical Actions over Images","created":"2021-04-13","cited_by_count":14,"area":null},{"id":"2211.03779","title":"CRIPP-VQA: Counterfactual Reasoning about Implicit Physical Properties via Video Question Answering","created":"2022-11-07","cited_by_count":13,"area":null},{"id":"2406.06499","title":"NarrativeBridge: Enhancing Video Captioning with Causal-Temporal Narrative","created":"2024-06-10","cited_by_count":10,"area":null},{"id":"2506.09445","title":"TOGA: Temporally Grounded Open-Ended Video QA with Weak Supervision","created":"2025-06-11","cited_by_count":8,"area":null},{"id":"2109.02747","title":"WhyAct: Identifying Action Reasons in Lifestyle Vlogs","created":"2021-09-06","cited_by_count":6,"area":null},{"id":"2410.08860","title":"Audio Description Generation in the Era of LLMs and VLMs: A Review of Transferable Generative AI Technologies","created":"2024-10-11","cited_by_count":5,"area":null},{"id":"2107.10300","title":"iReason: Multimodal Commonsense Reasoning using Videos and Natural Language with Interpretability","created":"2021-06-25","cited_by_count":4,"area":null},{"id":"2108.02365","title":"Hybrid Reasoning Network for Video-based Commonsense Captioning","created":"2021-08-05","cited_by_count":4,"area":null},{"id":"2312.17429","title":"Commonsense for Zero-Shot Natural Language Video Localization","created":"2023-12-29","cited_by_count":4,"area":null},{"id":"2506.07811","title":"Looking Beyond Visible Cues: Implicit Video Question Answering via Dual-Clue Reasoning","created":"2025-06-09","cited_by_count":3,"area":null},{"id":"2105.12392","title":"Unsupervised Pronoun Resolution via Masked Noun-Phrase Prediction","created":"2021-05-26","cited_by_count":2,"area":null},{"id":"2112.14815","title":"Materialized Knowledge Bases from Commonsense Transformers","created":"2021-12-29","cited_by_count":2,"area":null},{"id":"2203.16682","title":"To Find Waldo You Need Contextual Cues: Debiasing Who's Waldo","created":"2022-03-30","cited_by_count":2,"area":null},{"id":"2401.13888","title":"Knowledge Guided Entity-aware Video Captioning and A Basketball Benchmark","created":"2024-01-25","cited_by_count":2,"area":null},{"id":"2511.03757","title":"Laugh, Relate, Engage: Stylized Comment Generation for Short Videos","created":"2025-11-05","cited_by_count":1,"area":null},{"id":"2605.14607","title":"ViMU: Benchmarking Video Metaphorical Understanding","created":"2026-05-14","cited_by_count":1,"area":null},{"id":"2204.13548","title":"Tragedy Plus Time: Capturing Unintended Human Activities from Weakly-labeled Videos","created":"2022-04-28","cited_by_count":0,"area":null},{"id":"2407.20257","title":"Causal Understanding For Video Question Answering","created":"2024-07-23","cited_by_count":0,"area":null}],"next_cursor":null}