{"total":30,"rows":[{"id":"2105.04213","title":"Temporal-Spatial Feature Pyramid for Video Saliency Detection","created":"2021-05-10","cited_by_count":22,"area":null},{"id":"2111.01628","title":"Human Attention in Fine-grained Classification","created":"2021-11-02","cited_by_count":21,"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":"2107.05825","title":"Recent Advances in Leveraging Human Guidance for Sequential Decision-Making Tasks","created":"2021-07-13","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":"2604.14816","title":"NTIRE 2026 Challenge on Video Saliency Prediction: Methods and Results","created":"2026-04-16","cited_by_count":10,"area":null},{"id":"2110.08610","title":"MAAD: A Model and Dataset for \"Attended Awareness\" in Driving","created":"2021-10-16","cited_by_count":9,"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":"2409.14827","title":"AIM 2024 Challenge on Video Saliency Prediction: Methods and Results","created":"2024-09-23","cited_by_count":7,"area":null},{"id":"2408.05411","title":"How Does Audio Influence Visual Attention in Omnidirectional Videos? Database and Model","created":"2024-08-10","cited_by_count":4,"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":"2102.07682","title":"A Gated Fusion Network for Dynamic Saliency Prediction","created":"2021-02-15","cited_by_count":3,"area":null},{"id":"2404.08749","title":"Data Limitations for Modeling Top-Down Effects on Drivers' Attention","created":"2024-04-12","cited_by_count":3,"area":null},{"id":"2102.13378","title":"Where to look at the movies : Analyzing visual attention to understand movie editing","created":"2021-02-26","cited_by_count":2,"area":null},{"id":"2203.17257","title":"Modeling Long-Term Memory and Temporal Attention Shifts for Video Salient Object Ranking with a New Benchmark","created":"2022-03-31","cited_by_count":2,"area":null},{"id":"2212.01222","title":"Evaluation of Explanation Methods of AI -- CNNs in Image Classification Tasks with Reference-based and No-reference Metrics","created":"2022-12-02","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":"2508.09478","title":"GazeLT: Visual attention-guided long-tailed disease classification in chest radiographs","created":"2025-08-13","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":"2109.03575","title":"Deriving Explanation of Deep Visual Saliency Models","created":"2021-09-08","cited_by_count":0,"area":null},{"id":"2305.11729","title":"ViDaS Video Depth-aware Saliency Network","created":"2023-05-19","cited_by_count":0,"area":null},{"id":"2503.00657","title":"Artificially Generated Visual Scanpath Improves Multi-label Thoracic Disease Classification in Chest X-Ray Images","created":"2025-03-01","cited_by_count":0,"area":null},{"id":"2508.13546","title":"GazeProphet: Software-Only Gaze Prediction for VR Foveated Rendering","created":"2025-08-19","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":"2511.19988","title":"GazeProphetV2: Head-Movement-Based Gaze Prediction Enabling Efficient Foveated Rendering on Mobile VR","created":"2025-11-25","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},{"id":"2610.03276","title":"Moving Forward with Video Saliency: A New Dataset and Benchmark where Motion Matters","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}