mlsanityData to 7 Oct 2026

Detecting Attended Visual Targets in Video

arXiv 2003.02501 ↗First posted 5 Mar 2020cs.CVcited by 76

Not on the map. Why?

Abstract (arXiv)

We address the problem of detecting attention targets in video. Our goal is to identify where each person in each frame of a video is looking, and correctly handle the case where the gaze target is out-of-frame. Our novel architecture models the dynamic interaction between the scene and head features and infers time-varying attention targets. We introduce a new annotated dataset, VideoAttentionTarget, containing complex and dynamic patterns of real-world gaze behavior. Our experiments show that our model can effectively infer dynamic attention in videos. In addition, we apply our predicted attention maps to two social gaze behavior recognition tasks, and show that the resulting classifiers significantly outperform existing methods. We achieve state-of-the-art performance on three datasets: GazeFollow (static images), VideoAttentionTarget (videos), and VideoCoAtt (videos), and obtain the first results for automatically classifying clinically-relevant gaze behavior without wearable cameras or eye trackers.

Key facts. Cited by 76 papers in the map (data through 7 Oct 2026). First posted on arXiv 5 Mar 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 7; 2022: 6; 2023: 11; 2024: 16; 2025: 15; 2026: 21.

76 papers.

Sort:

By area:

  1. 2021Ego4D: Around the World in 3,000 Hours of Egocentric Videocited by 1,530
  2. 2022In the Eye of Transformer: Global-Local Correlation for Egocentric Gaze Estimationcited by 51
  3. 2022End-to-End Human-Gaze-Target Detection with Transformerscited by 47
  4. 2024Gaze-LLE: Gaze Target Estimation via Large-Scale Learned Encoderscited by 36
  5. 2023ChildPlay: A New Benchmark for Understanding Children's Gaze Behaviourcited by 35
  6. 2021Automatic Gaze Analysis: A Survey of Deep Learning based Approachescited by 33
  7. 2023A Modular Multimodal Architecture for Gaze Target Prediction: Application to Privacy-Sensitive Settingscited by 31
  8. 2021Weakly-Supervised Physically Unconstrained Gaze Estimationcited by 28
  9. 2023Object-aware Gaze Target Detectioncited by 27
  10. 2021GOO: A Dataset for Gaze Object Prediction in Retail Environmentscited by 26
  11. 2022Multimodal Across Domains Gaze Target Detectioncited by 22
  12. 2022Patch-level Gaze Distribution Prediction for Gaze Followingcited by 22
38 more
  1. 2021GaTector: A Unified Framework for Gaze Object Predictioncited by 18
  2. 2024Modeling Multimodal Social Interactions: New Challenges and Baselines with Densely Aligned Representationscited by 18
  3. 2022Understanding Embodied Reference with Touch-Line Transformercited by 16
  4. 2023M2LADS: A System for Generating MultiModal Learning Analytics Dashboards in Open Educationcited by 15
  5. 2024ViTGaze: Gaze Following with Interaction Features in Vision Transformerscited by 15
  6. 2023Human-Object Interaction Prediction in Videos through Gaze Followingcited by 13
  7. 2024Exploring the Zero-Shot Capabilities of Vision-Language Models for Improving Gaze Followingcited by 13
  8. 2025Towards Online Multi-Modal Social Interaction Understandingcited by 12
  9. 2024Biometrics and Behavior Analysis for Detecting Distractions in e-Learningcited by 10
  10. 2025Enhancing 3D Gaze Estimation in the Wild using Weak Supervision with Gaze Following Labelscited by 9
  11. 2025GazeVLM: A Vision-Language Model for Multi-Task Gaze Understandingcited by 9
  12. 2025UniGaze: Towards Universal Gaze Estimation via Large-scale Pre-Trainingcited by 8
  13. 2024A Gaze-grounded Visual Question Answering Dataset for Clarifying Ambiguous Japanese Questionscited by 7
  14. 2023Interaction-aware Joint Attention Estimation Using People Attributescited by 6
  15. 2023Joint Gaze-Location and Gaze-Object Detectioncited by 6
  16. 2023Multi-Modal Gaze Following in Conversational Scenarioscited by 6
  17. 2024TransGOP: Transformer-Based Gaze Object Predictioncited by 6
  18. 2024GazeHTA: End-to-end Gaze Target Detection with Head-Target Associationcited by 6
  19. 2024Diffusion-Refined VQA Annotations for Semi-Supervised Gaze Followingcited by 4
  20. 2025Multi-view Gaze Target Estimationcited by 4
  21. 2024A Novel Framework for Multi-Person Temporal Gaze Following and Social Gaze Predictioncited by 3
  22. 2025GA3CE: Unconstrained 3D Gaze Estimation with Gaze-Aware 3D Context Encodingcited by 3
  23. 2025VL4Gaze: Unleashing Vision-Language Models for Gaze Followingcited by 3
  24. 2026Omni-MMSI: Toward Identity-attributed Social Interaction Understandingcited by 3
  25. 2021Gaze Perception in Humans and CNN-Based Modelcited by 2
  26. 2023Uncovering the Unseen: Discover Hidden Intentions by Micro-Behavior Graph Reasoningcited by 2
  27. 2024Merging Multiple Datasets for Improved Appearance-Based Gaze Estimationcited by 2
  28. 2025Leveraging Multi-Modal Saliency and Fusion for Gaze Target Detectioncited by 2
  29. 2022Learning Video-independent Eye Contact Segmentation from In-the-Wild Videoscited by 1
  30. 2023Sharingan: A Transformer-based Architecture for Gaze Followingcited by 1
  31. 2024Driver Attention Tracking and Analysiscited by 1
  32. 2024Socially Pertinent Robots in Gerontological Healthcarecited by 1
  33. 20243D Gaze Tracking for Studying Collaborative Interactions in Mixed-Reality Environmentscited by 1
  34. 2024Upper-Body Pose-based Gaze Estimation for Privacy-Preserving 3D Gaze Target Detectioncited by 1
  35. 2024AL-GTD: Deep Active Learning for Gaze Target Detectioncited by 1
  36. 2025GazeTarget360: Towards Gaze Target Estimation in 360-Degree for Robot Perceptioncited by 1
  37. 2025GazeDETR: Gaze Detection using Disentangled Head and Gaze Representationscited by 1
  38. 2025GaTector+: A Unified Head-free Framework for Gaze Object and Gaze Following Predictioncited by 1

50 most cited of 76 All 76 (JSON)