{"total":160,"rows":[{"id":"2204.01696","title":"Joint Hand Motion and Interaction Hotspots Prediction from Egocentric Videos","created":"2022-04-04","cited_by_count":111,"area":null},{"id":"2112.03184","title":"HIVE: Evaluating the Human Interpretability of Visual Explanations","created":"2021-12-06","cited_by_count":105,"area":null},{"id":"2106.09788","title":"Guided Integrated Gradients: An Adaptive Path Method for Removing Noise","created":"2021-06-17","cited_by_count":102,"area":null},{"id":"2203.09905","title":"Learning Affordance Grounding from Exocentric Images","created":"2022-03-18","cited_by_count":82,"area":null},{"id":"2303.10437","title":"Grounding 3D Object Affordance from 2D Interactions in Images","created":"2023-03-18","cited_by_count":62,"area":null},{"id":"2105.12441","title":"DeepGaze IIE: Calibrated prediction in and out-of-domain for state-of-the-art saliency modeling","created":"2021-05-26","cited_by_count":56,"area":null},{"id":"2110.03593","title":"TranSalNet: Towards perceptually relevant visual saliency prediction","created":"2021-10-07","cited_by_count":44,"area":null},{"id":"2205.10468","title":"Deep Learning for Omnidirectional Vision: A Survey and New Perspectives","created":"2022-05-21","cited_by_count":38,"area":null},{"id":"2303.15274","title":"Gazeformer: Scalable, Effective and Fast Prediction of Goal-Directed Human Attention","created":"2023-03-27","cited_by_count":38,"area":null},{"id":"2303.14644","title":"Affordance Grounding from Demonstration Video to Target Image","created":"2023-03-26","cited_by_count":34,"area":null},{"id":"2305.09664","title":"Understanding 3D Object Interaction from a Single Image","created":"2023-05-16","cited_by_count":33,"area":null},{"id":"2201.12260","title":"A Review on Deep-Learning Algorithms for Fetal Ultrasound-Image Analysis","created":"2022-01-28","cited_by_count":29,"area":null},{"id":"2104.10252","title":"Revisiting The Evaluation of Class Activation Mapping for Explainability: A Novel Metric and Experimental Analysis","created":"2021-04-20","cited_by_count":25,"area":null},{"id":"2108.05675","title":"Learning Visual Affordance Grounding from Demonstration Videos","created":"2021-08-12","cited_by_count":25,"area":null},{"id":"2301.02315","title":"TempSAL -- Uncovering Temporal Information for Deep Saliency Prediction","created":"2023-01-05","cited_by_count":25,"area":null},{"id":"2506.09284","title":"UAD: Unsupervised Affordance Distillation for Generalization in Robotic Manipulation","created":"2025-06-10","cited_by_count":23,"area":null},{"id":"2105.04213","title":"Temporal-Spatial Feature Pyramid for Video Saliency Detection","created":"2021-05-10","cited_by_count":22,"area":null},{"id":"2208.13196","title":"Grounded Affordance from Exocentric View","created":"2022-08-28","cited_by_count":22,"area":null},{"id":"2303.09383","title":"Unifying Top-down and Bottom-up Scanpath Prediction Using Transformers","created":"2023-03-16","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":"2303.09706","title":"Unsupervised Self-Driving Attention Prediction via Uncertainty Mining and Knowledge Embedding","created":"2023-03-17","cited_by_count":19,"area":null},{"id":"2309.02120","title":"Multi-label affordance mapping from egocentric vision","created":"2023-09-05","cited_by_count":18,"area":null},{"id":"2109.01980","title":"Deep Saliency Prior for Reducing Visual Distraction","created":"2021-09-05","cited_by_count":17,"area":null},{"id":"2204.08308","title":"Saliency in Augmented Reality","created":"2022-04-18","cited_by_count":17,"area":null},{"id":"2209.08956","title":"Panoramic Vision Transformer for Saliency Detection in 360{\\deg} Videos","created":"2022-09-19","cited_by_count":15,"area":null},{"id":"2302.03292","title":"Fine-grained Affordance Annotation for Egocentric Hand-Object Interaction Videos","created":"2023-02-07","cited_by_count":15,"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":"2408.02788","title":"GazeXplain: Learning to Predict Natural Language Explanations of Visual Scanpaths","created":"2024-08-05","cited_by_count":15,"area":null},{"id":"2206.08567","title":"Rectify ViT Shortcut Learning by Visual Saliency","created":"2022-06-17","cited_by_count":14,"area":null},{"id":"2405.09782","title":"Size-invariance Matters: Rethinking Metrics and Losses for Imbalanced Multi-object Salient Object Detection","created":"2024-05-16","cited_by_count":14,"area":null},{"id":"2405.12461","title":"WorldAfford: Affordance Grounding based on Natural Language Instructions","created":"2024-05-21","cited_by_count":14,"area":null},{"id":"2101.09176","title":"Understanding Visual Saliency in Mobile User Interfaces","created":"2021-01-22","cited_by_count":13,"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":"2403.01226","title":"DiffSal: Joint Audio and Video Learning for Diffusion Saliency Prediction","created":"2024-03-02","cited_by_count":13,"area":null},{"id":"2411.17261","title":"HEIE: MLLM-Based Hierarchical Explainable AIGC Image Implausibility Evaluator","created":"2024-11-26","cited_by_count":13,"area":null},{"id":"2406.10852","title":"IG2: Integrated Gradient on Iterative Gradient Path for Feature Attribution","created":"2024-06-16","cited_by_count":12,"area":null},{"id":"2409.06210","title":"INTRA: Interaction Relationship-aware Weakly Supervised Affordance Grounding","created":"2024-09-10","cited_by_count":12,"area":null},{"id":"2109.12227","title":"Bringing Generalization to Deep Multi-View Pedestrian Detection","created":"2021-09-24","cited_by_count":11,"area":null},{"id":"2409.19650","title":"Grounding 3D Scene Affordance From Egocentric Interactions","created":"2024-09-29","cited_by_count":11,"area":null},{"id":"2506.12199","title":"ViSAGe: Video-to-Spatial Audio Generation","created":"2025-06-13","cited_by_count":11,"area":null},{"id":"2101.10710","title":"Visual explanation of black-box model: Similarity Difference and Uniqueness (SIDU) method","created":"2021-01-26","cited_by_count":10,"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":"2112.03731","title":"SalFBNet: Learning Pseudo-Saliency Distribution via Feedback Convolutional Networks","created":"2021-12-07","cited_by_count":9,"area":null},{"id":"2303.17707","title":"Why is plausibility surprisingly problematic as an XAI criterion?","created":"2023-03-30","cited_by_count":9,"area":null},{"id":"2312.01060","title":"Spectrum-driven Mixed-frequency Network for Hyperspectral Salient Object Detection","created":"2023-12-02","cited_by_count":9,"area":null},{"id":"2402.18673","title":"Trends, Applications, and Challenges in Human Attention Modelling","created":"2024-02-28","cited_by_count":9,"area":null},{"id":"2404.02523","title":"Text-driven Affordance Learning from Egocentric Vision","created":"2024-04-03","cited_by_count":9,"area":null},{"id":"2107.00559","title":"SALYPATH: A Deep-Based Architecture for visual attention prediction","created":"2021-06-29","cited_by_count":7,"area":null},{"id":"2112.11716","title":"Comparing radiologists' gaze and saliency maps generated by interpretability methods for chest x-rays","created":"2021-12-22","cited_by_count":7,"area":null},{"id":"2312.10175","title":"UniAR: A Unified model for predicting human Attention and Responses on visual content","created":"2023-12-15","cited_by_count":7,"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":"2404.07537","title":"How is Visual Attention Influenced by Text Guidance? Database and Model","created":"2024-04-11","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":"2103.15438","title":"Learning to Predict Salient Faces: A Novel Visual-Audio Saliency Model","created":"2021-03-29","cited_by_count":6,"area":null},{"id":"2108.00273","title":"Towards explainable artificial intelligence (XAI) for early anticipation of traffic accidents","created":"2021-07-31","cited_by_count":6,"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":"2504.15650","title":"AffordanceSAM: Segment Anything Once More in Affordance Grounding","created":"2025-04-22","cited_by_count":6,"area":null},{"id":"2506.12009","title":"Affogato: Open-Vocabulary Affordance Grounding with Automated Data Generation at Scale","created":"2025-06-13","cited_by_count":6,"area":null},{"id":"2404.08756","title":"SCOUT+: Towards Practical Task-Driven Drivers' Gaze Prediction","created":"2024-04-12","cited_by_count":5,"area":null},{"id":"2407.19605","title":"Look Hear: Gaze Prediction for Speech-directed Human Attention","created":"2024-07-28","cited_by_count":5,"area":null},{"id":"2201.00096","title":"SalyPath360: Saliency and Scanpath Prediction Framework for Omnidirectional Images","created":"2022-01-01","cited_by_count":4,"area":null},{"id":"2202.07118","title":"Multi-task UNet: Jointly Boosting Saliency Prediction and Disease Classification on Chest X-ray Images","created":"2022-02-15","cited_by_count":4,"area":null},{"id":"2207.04250","title":"Improving saliency models' predictions of the next fixation with humans' intrinsic cost of gaze shifts","created":"2022-07-09","cited_by_count":4,"area":null},{"id":"2307.13345","title":"Do humans and Convolutional Neural Networks attend to similar areas during scene classification: Effects of task and image type","created":"2023-07-25","cited_by_count":4,"area":null},{"id":"2310.09275","title":"Understanding and Modeling the Effects of Task and Context on Drivers' Gaze Allocation","created":"2023-10-13","cited_by_count":4,"area":null},{"id":"2410.23409","title":"TPP-Gaze: Modelling Gaze Dynamics in Space and Time with Neural Temporal Point Processes","created":"2024-10-30","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":"2504.17023","title":"Are explainable AI (XAI) evaluation strategies aligned? Comparing subjective, objective, and mathematical evaluation measures using saliency maps","created":"2025-04-23","cited_by_count":4,"area":null},{"id":"2508.01668","title":"Measuring and Predicting Where and When Pathologists Focus their Visual Attention while Grading Whole Slide Images of Cancer","created":"2025-08-03","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":"2104.02548","title":"White Box Methods for Explanations of Convolutional Neural Networks in Image Classification Tasks","created":"2021-04-06","cited_by_count":3,"area":null},{"id":"2306.15692","title":"Utilizing Segment Anything Model For Assessing Localization of GRAD-CAM in Medical Imaging","created":"2023-06-24","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":"2407.02439","title":"Predicting Visual Attention in Graphic Design Documents","created":"2024-07-02","cited_by_count":3,"area":null},{"id":"2412.11998","title":"SAMIC: Segment Anything with In-Context Spatial Prompt Engineering","created":"2024-12-16","cited_by_count":3,"area":null},{"id":"2104.03864","title":"Modeling Object Dissimilarity for Deep Saliency Prediction","created":"2021-04-08","cited_by_count":2,"area":null},{"id":"2109.08371","title":"Audio-Visual Collaborative Representation Learning for Dynamic Saliency Prediction","created":"2021-09-17","cited_by_count":2,"area":null},{"id":"2206.08751","title":"Perceptual Quality Assessment of Virtual Reality Videos in the Wild","created":"2022-06-13","cited_by_count":2,"area":null},{"id":"2210.16933","title":"Context-empowered Visual Attention Prediction in Pedestrian Scenarios","created":"2022-10-30","cited_by_count":2,"area":null},{"id":"2211.08074","title":"Predicting Eye Gaze Location on Websites","created":"2022-11-15","cited_by_count":2,"area":null},{"id":"2308.13004","title":"Spherical Vision Transformer for 360-degree Video Saliency Prediction","created":"2023-08-24","cited_by_count":2,"area":null},{"id":"2311.14073","title":"Learning Saliency From Fixations","created":"2023-11-23","cited_by_count":2,"area":null},{"id":"2312.02576","title":"An Integrated System for Spatio-Temporal Summarization of 360-degrees Videos","created":"2023-12-05","cited_by_count":2,"area":null},{"id":"2403.09939","title":"Quantization Effects on Neural Networks Perception: How would quantization change the perceptual field of vision models?","created":"2024-03-15","cited_by_count":2,"area":null},{"id":"2410.11363","title":"Visual-Geometric Collaborative Guidance for Affordance Learning","created":"2024-10-15","cited_by_count":2,"area":null},{"id":"2504.05950","title":"AEGIS: Human Attention-based Explainable Guidance for Intelligent Vehicle Systems","created":"2025-04-08","cited_by_count":2,"area":null},{"id":"2506.21925","title":"Quality Assessment and Distortion-aware Saliency Prediction for AI-Generated Omnidirectional Images","created":"2025-06-27","cited_by_count":2,"area":null},{"id":"2507.17616","title":"Vision Transformer attention alignment with human visual perception in aesthetic object evaluation","created":"2025-07-23","cited_by_count":2,"area":null},{"id":"2510.21160","title":"Towards Physics-informed Spatial Intelligence with Human Priors: An Autonomous Driving Pilot Study","created":"2025-10-24","cited_by_count":2,"area":null},{"id":"2511.18470","title":"Gaze Beyond the Frame: Forecasting Egocentric 3D Visual Span","created":"2025-11-23","cited_by_count":2,"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":"2111.01906","title":"A trained humanoid robot can perform human-like crossmodal social attention and conflict resolution","created":"2021-11-02","cited_by_count":1,"area":null},{"id":"2111.08567","title":"Joint Learning of Visual-Audio Saliency Prediction and Sound Source Localization on Multi-face Videos","created":"2021-11-05","cited_by_count":1,"area":null},{"id":"2112.13697","title":"Weakly Supervised Visual-Auditory Fixation Prediction with Multigranularity Perception","created":"2021-12-27","cited_by_count":1,"area":null},{"id":"2201.12525","title":"Spherical Convolution empowered FoV Prediction in 360-degree Video Multicast with Limited FoV Feedback","created":"2022-01-29","cited_by_count":1,"area":null},{"id":"2207.02205","title":"Clustered Saliency Prediction","created":"2022-07-05","cited_by_count":1,"area":null},{"id":"2305.13901","title":"WinDB: HMD-free and Distortion-free Panoptic Video Fixation Learning","created":"2023-05-23","cited_by_count":1,"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}],"next_cursor":"100"}