{"total":17,"rows":[{"id":"2403.19967","title":"Rewrite the Stars","created":"2024-03-29","cited_by_count":55,"area":null},{"id":"2505.19328","title":"BAH Dataset for Ambivalence/Hesitancy Recognition in Videos for Digital Behavioural Change","created":"2025-05-25","cited_by_count":14,"area":null},{"id":"2603.15818","title":"Conflict-Aware Multimodal Fusion for Ambivalence and Hesitancy Recognition","created":"2026-03-16","cited_by_count":11,"area":null},{"id":"2504.13112","title":"Hadamard product in deep learning: Introduction, Advances and Challenges","created":"2025-04-17","cited_by_count":9,"area":null},{"id":"2402.02754","title":"Focal Modulation Networks for Interpretable Sound Classification","created":"2024-02-05","cited_by_count":8,"area":null},{"id":"2504.10676","title":"H-MoRe: Learning Human-centric Motion Representation for Action Analysis","created":"2025-04-14","cited_by_count":8,"area":null},{"id":"2411.13626","title":"Principles of Visual Tokens for Efficient Video Understanding","created":"2024-11-20","cited_by_count":7,"area":null},{"id":"2411.13683","title":"Extending Video Masked Autoencoders to 128 frames","created":"2024-11-20","cited_by_count":3,"area":null},{"id":"2604.11730","title":"Multimodal Ambivalence/Hesitancy Recognition in Videos for Personalized Digital Health Interventions","created":"2026-04-13","cited_by_count":3,"area":null},{"id":"2503.13724","title":"Towards Scalable Modeling of Compressed Videos for Efficient Action Recognition","created":"2025-03-17","cited_by_count":2,"area":null},{"id":"2507.12426","title":"DVFL-Net: A Lightweight Distilled Video Focal Modulation Network for Spatio-Temporal Action Recognition","created":"2025-07-16","cited_by_count":2,"area":null},{"id":"2503.06317","title":"Accurate and Efficient Two-Stage Gun Detection in Video","created":"2025-03-08","cited_by_count":1,"area":null},{"id":"2604.20760","title":"Exploring High-Order Self-Similarity for Video Understanding","created":"2026-04-22","cited_by_count":1,"area":null},{"id":"2605.06809","title":"LookWhen? Fast Video Recognition by Learning When, Where, and What to Compute","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2604.15141","title":"KVNN: Learnable Multi-Kernel Volterra Neural Networks","created":"2026-04-16","cited_by_count":0,"area":null},{"id":"2604.16240","title":"CollideNet: Hierarchical Multi-scale Video Representation Learning with Disentanglement for Time-To-Collision Forecasting","created":"2026-04-17","cited_by_count":0,"area":null},{"id":"2607.09114","title":"Event Stream based Multi-Modal Video Anomaly Detection: A Benchmark Dataset and Algorithms","created":"2026-07-10","cited_by_count":0,"area":null}],"next_cursor":null}