{"total":61,"rows":[{"id":"2102.10274","title":"Concealed Object Detection","created":"2021-02-20","cited_by_count":212,"area":null},{"id":"2312.17432","title":"Video Understanding with Large Language Models: A Survey","created":"2023-12-29","cited_by_count":206,"area":null},{"id":"2207.14096","title":"Towards Large-Scale Small Object Detection: Survey and Benchmarks","created":"2022-07-28","cited_by_count":122,"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":"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":"2306.07532","title":"Referring Camouflaged Object Detection","created":"2023-06-13","cited_by_count":19,"area":null},{"id":"2204.04615","title":"Learning Pixel-Level Distinctions for Video Highlight Detection","created":"2022-04-10","cited_by_count":16,"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":"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":"2111.02368","title":"Video Salient Object Detection via Contrastive Features and Attention Modules","created":"2021-11-03","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":"2205.07179","title":"Promoting Saliency From Depth: Deep Unsupervised RGB-D Saliency Detection","created":"2022-05-15","cited_by_count":12,"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":"2206.13390","title":"A Comprehensive Survey on Video Saliency Detection with Auditory Information: the Audio-visual Consistency Perceptual is the Key!","created":"2022-06-20","cited_by_count":9,"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":"2504.05517","title":"L3GS: Layered 3D Gaussian Splats for Efficient 3D Scene Delivery","created":"2025-04-07","cited_by_count":6,"area":null},{"id":"2205.06934","title":"A Saliency-Guided Street View Image Inpainting Framework for Efficient Last-Meters Wayfinding","created":"2022-05-14","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":"2209.12138","title":"Towards Stable Co-saliency Detection and Object Co-segmentation","created":"2022-09-25","cited_by_count":4,"area":null},{"id":"2310.09679","title":"What Do Deep Saliency Models Learn about Visual Attention?","created":"2023-10-14","cited_by_count":4,"area":null},{"id":"2107.11629","title":"ASOD60K: An Audio-Induced Salient Object Detection Dataset for Panoramic Videos","created":"2021-07-24","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":"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":"2203.01978","title":"Region-of-Interest Based Neural Video Compression","created":"2022-03-03","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":"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":"2311.14073","title":"Learning Saliency From Fixations","created":"2023-11-23","cited_by_count":2,"area":null},{"id":"2311.16462","title":"Viewport Prediction for Volumetric Video Streaming by Exploring Video Saliency and Trajectory Information","created":"2023-11-28","cited_by_count":2,"area":null},{"id":"2502.12723","title":"myEye2Wheeler: A Two-Wheeler Indian Driver Real-World Eye-Tracking Dataset","created":"2025-02-18","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":"2102.04046","title":"Towards Accurate RGB-D Saliency Detection with Complementary Attention and Adaptive Integration","created":"2021-02-08","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},{"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":"2408.01322","title":"A Robotics-Inspired Scanpath Model Reveals the Importance of Uncertainty and Semantic Object Cues for Gaze Guidance in Dynamic Scenes","created":"2024-08-02","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":"2601.11045","title":"Convolutions Need Registers Too: HVS-Inspired Dynamic Attention for Video Quality Assessment","created":"2026-01-16","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":"2104.08038","title":"Noise-Aware Video Saliency Prediction","created":"2021-04-16","cited_by_count":0,"area":null},{"id":"2109.03575","title":"Deriving Explanation of Deep Visual Saliency Models","created":"2021-09-08","cited_by_count":0,"area":null},{"id":"2208.05220","title":"Dual Domain-Adversarial Learning for Audio-Visual Saliency Prediction","created":"2022-08-10","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":"2501.15045","title":"Towards Robust Unsupervised Attention Prediction in Autonomous Driving","created":"2025-01-25","cited_by_count":0,"area":null},{"id":"2505.19178","title":"Saliency-guided Emotion Modeling: Predicting Viewer Reactions from Video Stimuli","created":"2025-05-25","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":"2512.07668","title":"EgoCampus: Egocentric Pedestrian Eye Gaze Model and Dataset","created":"2025-12-08","cited_by_count":0,"area":null},{"id":"2603.09613","title":"A Saccade-inspired Approach to Image Classification using Vision Transformer Attention Maps","created":"2026-03-10","cited_by_count":0,"area":null},{"id":"2603.24938","title":"Infinite Gaze Generation for Videos with Autoregressive Diffusion","created":"2026-03-26","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":"2604.24947","title":"Subjective Portrait Region Cropping in Landscape Videos with Temporal Annotation Smoothing","created":"2026-04-27","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":"2607.19040","title":"Gaze-DETR: Top-Down Guidance Through Priority Maps for Infrared Weak-Small UAV Detection with DETR","created":"2026-07-21","cited_by_count":0,"area":null},{"id":"2607.25465","title":"DensFiLM: Density-Conditioned Video Saliency for Crowd Scenes","created":"2026-07-28","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}