{"total":27,"rows":[{"id":"2405.09711","title":"STAR: A Benchmark for Situated Reasoning in Real-World Videos","created":"2024-05-15","cited_by_count":213,"area":null},{"id":"2304.06708","title":"Verbs in Action: Improving verb understanding in video-language models","created":"2023-04-13","cited_by_count":76,"area":null},{"id":"2301.02074","title":"Test of Time: Instilling Video-Language Models with a Sense of Time","created":"2023-01-05","cited_by_count":51,"area":null},{"id":"2103.16848","title":"Embracing Uncertainty: Decoupling and De-bias for Robust Temporal Grounding","created":"2021-03-31","cited_by_count":29,"area":null},{"id":"2306.07515","title":"A Survey on Video Moment Localization","created":"2023-06-13","cited_by_count":18,"area":null},{"id":"2206.07690","title":"ELUDE: Generating interpretable explanations via a decomposition into labelled and unlabelled features","created":"2022-06-15","cited_by_count":10,"area":null},{"id":"2207.05054","title":"Demystifying Unsupervised Semantic Correspondence Estimation","created":"2022-07-11","cited_by_count":10,"area":null},{"id":"2112.12175","title":"Recur, Attend or Convolve? On Whether Temporal Modeling Matters for Cross-Domain Robustness in Action Recognition","created":"2021-12-22","cited_by_count":7,"area":null},{"id":"2109.02747","title":"WhyAct: Identifying Action Reasons in Lifestyle Vlogs","created":"2021-09-06","cited_by_count":6,"area":null},{"id":"2108.11149","title":"A Unified Taxonomy and Multimodal Dataset for Events in Invasion Games","created":"2021-08-25","cited_by_count":4,"area":null},{"id":"2104.07135","title":"Adaptive Intermediate Representations for Video Understanding","created":"2021-04-14","cited_by_count":3,"area":null},{"id":"2210.15187","title":"Learning Joint Representation of Human Motion and Language","created":"2022-10-27","cited_by_count":3,"area":null},{"id":"2308.11249","title":"Video BagNet: short temporal receptive fields increase robustness in long-term action recognition","created":"2023-08-22","cited_by_count":2,"area":null},{"id":"2201.06444","title":"Black-box Error Diagnosis in Deep Neural Networks for Computer Vision: a Survey of Tools","created":"2022-01-17","cited_by_count":1,"area":null},{"id":"2202.08138","title":"When Did It Happen? Duration-informed Temporal Localization of Narrated Actions in Vlogs","created":"2022-02-16","cited_by_count":1,"area":null},{"id":"2204.11929","title":"Temporal Relevance Analysis for Video Action Models","created":"2022-04-25","cited_by_count":1,"area":null},{"id":"2205.00694","title":"A Multi-stage deep architecture for summary generation of soccer videos","created":"2022-05-02","cited_by_count":1,"area":null},{"id":"2211.00549","title":"No-audio speaking status detection in crowded settings via visual pose-based filtering and wearable acceleration","created":"2022-11-01","cited_by_count":1,"area":null},{"id":"2311.18064","title":"GELDA: A generative language annotation framework to reveal visual biases in datasets","created":"2023-11-29","cited_by_count":1,"area":null},{"id":"2610.00064","title":"Reachability Is Not Generalization: Understanding Verb--Noun Decomposition in Assembly Action Recognition","created":"2026-09-04","cited_by_count":1,"area":null},{"id":"2101.01073","title":"Anomaly Recognition from surveillance videos using 3D Convolutional Neural Networks","created":"2021-01-04","cited_by_count":0,"area":null},{"id":"2107.12744","title":"Real-Time Activity Recognition and Intention Recognition Using a Vision-based Embedded System","created":"2021-07-27","cited_by_count":0,"area":null},{"id":"2203.16062","title":"AxIoU: An Axiomatically Justified Measure for Video Moment Retrieval","created":"2022-03-30","cited_by_count":0,"area":null},{"id":"2208.10077","title":"Identifying Auxiliary or Adversarial Tasks Using Necessary Condition Analysis for Adversarial Multi-task Video Understanding","created":"2022-08-22","cited_by_count":0,"area":null},{"id":"2309.06219","title":"Human Action Co-occurrence in Lifestyle Vlogs using Graph Link Prediction","created":"2023-09-12","cited_by_count":0,"area":null},{"id":"2310.10586","title":"VidCoM: Fast Video Comprehension through Large Language Models with Multimodal Tools","created":"2023-10-16","cited_by_count":0,"area":null},{"id":"2405.08695","title":"The impact of Compositionality in Zero-shot Multi-label action recognition for Object-based tasks","created":"2024-05-14","cited_by_count":0,"area":null}],"next_cursor":null}