{"total":21,"rows":[{"id":"2305.03907","title":"Listen to Look into the Future: Audio-Visual Egocentric Gaze Anticipation","created":"2023-05-06","cited_by_count":20,"area":null},{"id":"2108.10696","title":"Spatio-Temporal Self-Attention Network for Video Saliency Prediction","created":"2021-08-24","cited_by_count":19,"area":null},{"id":"2303.06357","title":"CASP-Net: Rethinking Video Saliency Prediction from an Audio-VisualConsistency Perceptual Perspective","created":"2023-03-11","cited_by_count":15,"area":null},{"id":"2403.01226","title":"DiffSal: Joint Audio and Video Learning for Diffusion Saliency Prediction","created":"2024-03-02","cited_by_count":13,"area":null},{"id":"2404.03097","title":"SalFoM: Dynamic Saliency Prediction with Video Foundation Models","created":"2024-04-03","cited_by_count":10,"area":null},{"id":"2301.04619","title":"TinyHD: Efficient Video Saliency Prediction with Heterogeneous Decoders using Hierarchical Maps Distillation","created":"2023-01-11","cited_by_count":9,"area":null},{"id":"2401.07942","title":"Transformer-based Video Saliency Prediction with High Temporal Dimension Decoding","created":"2024-01-15","cited_by_count":7,"area":null},{"id":"2404.14232","title":"Shifting Focus with HCEye: Exploring the Dynamics of Visual Highlighting and Cognitive Load on User Attention and Saliency Prediction","created":"2024-04-22","cited_by_count":6,"area":null},{"id":"2502.00397","title":"Minimalistic Video Saliency Prediction via Efficient Decoder & Spatio Temporal Action Cues","created":"2025-02-01","cited_by_count":4,"area":null},{"id":"2604.08613","title":"ViSAGE @ NTIRE 2026 Challenge on Video Saliency Prediction","created":"2026-04-09","cited_by_count":2,"area":null},{"id":"2308.12163","title":"NPF-200: A Multi-Modal Eye Fixation Dataset and Method for Non-Photorealistic Videos","created":"2023-08-23","cited_by_count":1,"area":null},{"id":"2309.08220","title":"UniST: Towards Unifying Saliency Transformer for Video Saliency Prediction and Detection","created":"2023-09-15","cited_by_count":1,"area":null},{"id":"2411.11454","title":"Relevance-guided Audio Visual Fusion for Video Saliency Prediction","created":"2024-11-18","cited_by_count":1,"area":null},{"id":"2504.10070","title":"DTFSal: Audio-Visual Dynamic Token Fusion for Video Saliency Prediction","created":"2025-04-14","cited_by_count":1,"area":null},{"id":"2605.23790","title":"Exploring deep learning for Event-Based Saliency Prediction with a Transformer-based model","created":"2026-05-22","cited_by_count":1,"area":null},{"id":"2606.03540","title":"Attend to Anything: Foundation Model for Unified Human Attention Modeling","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2502.02172","title":"EditIQ: Automated Cinematic Editing of Static Wide-Angle Videos via Dialogue Interpretation and Saliency Cues","created":"2025-02-04","cited_by_count":0,"area":null},{"id":"2510.22208","title":"Simplifying Knowledge Transfer in Pretrained Models","created":"2025-10-25","cited_by_count":0,"area":null},{"id":"2603.13355","title":"Int3DNet: Scene-Motion Cross Attention Network for 3D Intention Prediction in Mixed Reality","created":"2026-03-09","cited_by_count":0,"area":null},{"id":"2604.08858","title":"BIAS: A Biologically Inspired Algorithm for Video Saliency Detection","created":"2026-04-10","cited_by_count":0,"area":null},{"id":"2605.29302","title":"ViASNet: A Video Ad Saliency Network for Predicting Dynamic Saliency and Viewer Engagement","created":"2026-05-28","cited_by_count":0,"area":null}],"next_cursor":null}